CN120246004A

CN120246004A - Wheel loosening warning method, device, medium and vehicle

Info

Publication number: CN120246004A
Application number: CN202510565192.9A
Authority: CN
Inventors: 陈臻鑫; 赵子龙; 杨慧凯; 徐珊珊; 王鹏鹏
Original assignee: FAW Group Corp
Current assignee: FAW Group Corp
Priority date: 2025-04-30
Filing date: 2025-04-30
Publication date: 2025-07-04

Abstract

The application discloses a wheel looseness early warning method, a device, a medium and a vehicle, which are applied to the technical field of vehicle control, wherein the method comprises the steps of acquiring a wheel image, wheel attribute data and driving attribute data of the vehicle; the method comprises the steps of obtaining target tire pressure detection information and target fastening detection information of a vehicle according to a wheel image and wheel attribute data, wherein the target tire pressure detection information is used for indicating whether the tire pressure of the wheel is normal, the target fastening detection information is used for indicating whether a mechanical structure of the wheel is fastened, and if the target tire pressure detection information is used for indicating that the tire pressure of the wheel is abnormal and/or the target fastening detection information is used for indicating that the mechanical structure of the wheel is not fastened, obtaining wheel movement track data of the vehicle according to the wheel image, the wheel attribute data and driving attribute data, and carrying out wheel looseness early warning treatment on the vehicle based on the wheel movement track data. The method and the device can effectively improve the accuracy of early warning of wheel looseness.

Description

Wheel looseness early warning method and device, medium and vehicle

Technical Field

The application relates to the technical field of vehicle control, in particular to a wheel looseness early warning method, a device, a medium and a vehicle.

Background

Vehicles are one of the most common and most common vehicles used most frequently in daily life. Wheel looseness is a serious hidden danger of vehicle safety, which affects the running stability of the vehicle and increases the risk of traffic accidents. Therefore, the looseness early warning of the wheels is important for the safety maintenance of the vehicle. In the related art, when a vehicle runs, variables such as a tire pressure value or a tire pressure change value of a wheel are detected in real time, and if the variables reach a set threshold value, a signal for early warning of wheel looseness is sent out so as to prompt that the risk of wheel looseness exists. However, the related art determines whether the wheel is loose only by the tire pressure state of the wheel, which depends on a single-dimensional factor, which results in low accuracy of early warning of the wheel loosening thereof.

Disclosure of Invention

The embodiment of the application provides a wheel looseness early warning method, a device, a medium and a vehicle, which are used for improving the accuracy of wheel looseness early warning.

In one aspect, an embodiment of the present application provides a wheel loosening early warning method, including the following steps:

Acquiring a wheel image, wheel attribute data and driving attribute data of a vehicle;

Obtaining target tire pressure detection information and target fastening detection information of the vehicle according to the wheel image and the wheel attribute data, wherein the target tire pressure detection information is used for indicating whether the tire pressure of the wheel is normal or not, and the target fastening detection information is used for indicating whether the mechanical structure of the wheel is fastened or not;

Obtaining wheel movement track data of the vehicle according to the wheel image, the wheel attribute data and the driving attribute data under the condition that the target tire pressure detection information is used for indicating that the tire pressure of the wheel is abnormal and/or the target fastening detection information is used for indicating that the mechanical structure of the wheel is not fastened;

and carrying out wheel looseness early warning processing on the vehicle based on the wheel movement track data.

In another aspect, an embodiment of the present application provides a wheel loosening warning device, including:

the acquisition module is used for acquiring the wheel image, the wheel attribute data and the driving attribute data of the vehicle;

the first processing module is used for obtaining target tire pressure detection information and target fastening detection information of the vehicle according to the wheel image and the wheel attribute data, wherein the target tire pressure detection information is used for indicating whether the tire pressure of the wheel is normal or not, and the target fastening detection information is used for indicating whether the mechanical structure of the wheel is fastened or not;

The second processing module is used for obtaining wheel movement track data of the vehicle according to the wheel image, the wheel attribute data and the driving attribute data when the target tire pressure detection information is used for indicating that the tire pressure of the wheel is abnormal and/or the target fastening detection information is used for indicating that the mechanical structure of the wheel is not fastened;

and the third processing module is used for carrying out wheel looseness early warning processing on the vehicle based on the wheel movement track data.

In yet another aspect, an embodiment of the present application provides a computer readable storage medium, where a program executable by a processor is used to implement the above-mentioned wheel looseness warning method when executed by the processor.

In yet another aspect, an embodiment of the present application provides a vehicle including:

at least one processor;

At least one memory for storing at least one program;

and when the at least one program is executed by the at least one processor, the at least one processor is enabled to realize the wheel looseness early warning method.

The method, the device, the medium and the vehicle for early warning of the looseness of the wheels are characterized in that firstly, a wheel image, wheel attribute data and driving attribute data of the vehicle are obtained, then target tire pressure detection information and target fastening detection information of the vehicle are obtained according to the wheel image and the wheel attribute data, the target tire pressure detection information is used for indicating whether the tire pressure of the wheels is normal or not, the target fastening detection information is used for indicating whether the mechanical structure of the wheels is fastened or not, then, if the target tire pressure detection information is used for indicating that the tire pressure of the wheels is abnormal, and/or the target fastening detection information is used for indicating that the mechanical structure of the wheels is not fastened, wheel movement track data of the vehicle are obtained according to the wheel image, the wheel attribute data and the driving attribute data, and finally, the early warning of the looseness of the wheels is carried out on the vehicle on the basis of the wheel movement track data. According to the technical scheme, the multi-dimensional factors such as the image data and the attribute data related to the wheels of the vehicle and the attribute data related to the running of the vehicle are fully considered, and the wheel looseness early warning processing is realized according to the multi-dimensional factors, so that the looseness erroneous judgment interference caused by the single-dimensional factors can be eliminated, and the accuracy of the wheel looseness early warning is effectively improved.

Additional features and advantages of the application will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the application. The objectives and other advantages of the application will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

Drawings

FIG. 1 is a flow chart of a wheel looseness early warning method provided by the application;

FIG. 2 is a specific flowchart of step S102 in FIG. 1;

FIG. 3 is another specific flowchart of step S102 in FIG. 1;

Fig. 4 is a specific flowchart of step S103 in fig. 1;

FIG. 5 is a specific flowchart of step S104 in FIG. 1;

FIG. 6 is a flow chart of model training provided by the present application;

FIG. 7 is a diagram illustrating a specific implementation process of a wheel looseness warning method provided by the application;

FIG. 8 is a block diagram of a wheel looseness warning device provided by the application;

fig. 9 is an exemplary diagram of a vehicle provided by the present application.

Detailed Description

The present application will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present application more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the application.

The application will be further described with reference to the drawings and specific examples. The described embodiments should not be taken as limitations of the present application, and all other embodiments that would be obvious to one of ordinary skill in the art without making any inventive effort are intended to be within the scope of the present application.

In the following description, reference is made to "some embodiments" which describe a subset of all possible embodiments, but it is to be understood that "some embodiments" can be the same subset or different subsets of all possible embodiments and can be combined with one another without conflict.

Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of the application only and is not intended to be limiting of the application.

With the rapid development of technology, vehicles are one of the most common and most common vehicles with the highest frequency of use in daily life, and have become important commuting tools and production tools. When the vehicle runs, if the wheels are in a problem, the running stability of the vehicle is affected, the situations such as noise increase, vehicle body shake, vehicle deviation and the like can occur, and if serious, tire burst or wheel falling can be caused, so that the risk of traffic accidents is increased. Therefore, the loosening of the wheels is a great hidden danger for the safety of the vehicle, and the early warning of the loosening of the wheels is important for the safety maintenance of the vehicle.

In the related art, when a vehicle runs, variables such as a tire pressure value or a tire pressure change value of a wheel are detected in real time, and if the tire pressure value or the tire pressure change value reaches a set threshold value, a signal of early warning of loosening of the wheel is sent out so as to prompt that the risk of loosening of the wheel exists. However, the tire pressure is easily interfered by factors such as temperature, load, altitude and the like, and the related art only judges whether the wheel is loose according to the tire pressure state of the wheel, and the related art depends on the tire pressure which is a single-dimensional factor, so that the situation such as misjudgment of the wheel loosening and the like is easy to occur, and the early warning precision of the wheel loosening is low.

In view of the above, the embodiment of the application provides a wheel looseness early warning method, a device, a medium and a vehicle, which aim to monitor the tire pressure state and the fastening state of a wheel and the deviation state of the vehicle in real time, and perform corresponding wheel looseness early warning according to the monitoring result, so that the accuracy of the wheel looseness early warning is effectively improved.

Firstly, the implementation steps of the wheel looseness early warning method provided by the embodiment of the application will be described in detail below with reference to the accompanying drawings.

The wheel looseness early warning method provided by the embodiment of the application can be applied to a terminal, a server, software running in the terminal or the server and the like. The terminal may be, but is not limited to, a tablet computer, a notebook computer, a desktop computer, etc. The server may be an independent physical server, a server cluster or a distributed system formed by a plurality of physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, a content distribution network (Content Delivery Network, CDN), basic cloud computing services such as big data and an artificial intelligent platform. In addition, the server may also be a node server in a blockchain network, but is not limited thereto. The blockchain is a novel application mode of computer technologies such as distributed data storage, point-to-point transmission, a consensus mechanism, an encryption algorithm and the like.

Referring to fig. 1, fig. 1 is a flowchart of a wheel looseness early-warning method provided by the application, which may include the following steps S101-S104:

S101, acquiring a wheel image, wheel attribute data and driving attribute data of a vehicle;

S102, obtaining target tire pressure detection information and target fastening detection information of a vehicle according to a wheel image and wheel attribute data, wherein the target tire pressure detection information is used for indicating whether the tire pressure of the wheel is normal or not, and the target fastening detection information is used for indicating whether the mechanical structure of the wheel is fastened or not;

s103, obtaining wheel movement track data of the vehicle according to the wheel image, the wheel attribute data and the driving attribute data under the condition that the target tire pressure detection information is used for indicating abnormal tire pressure of the wheel and/or the target fastening detection information is used for indicating that the mechanical structure of the wheel is not fastened;

S104, performing wheel looseness early warning processing on the vehicle based on the wheel movement track data.

In the above step S101, image data and attribute data associated with wheels of the vehicle are acquired as wheel images and wheel attribute data of the vehicle before and at the time of running of the vehicle, and attribute data associated with running of the vehicle is acquired as running attribute data of the vehicle, so that it is possible to detect and early warn whether the wheels are loose or not with these data as references in the subsequent steps.

Here, the above-described wheel image may include, but is not limited to, image data associated with a wheel shape before the vehicle runs, and image data associated with a local temperature of the wheel while the vehicle runs. The above-described wheel attribute data may include, but is not limited to, attribute data associated with physical characteristics of the wheels while the vehicle is running, and these attribute data are numerical text data. The driving attribute data may include, but is not limited to, attribute data associated with physical characteristics of the vehicle while the vehicle is driving, and the attribute data is numerical text data.

In the step S102, in the early warning of wheel looseness, firstly, whether the tire pressure of the wheel is normal or not is detected based on the wheel image and the wheel attribute data, and whether the mechanical structure of the wheel is installed and fastened is detected, so that the target tire pressure detection information and the target fastening detection information of the vehicle are obtained. The target tire pressure detection information is used for indicating whether the tire pressure of the wheel is normal or not, and the target fastening detection information is used for indicating whether the mechanical structure of the wheel is fastened or not.

Here, the tire pressure of the wheel is highly correlated with the wheel looseness. When the tire pressure is abnormal because it is lower than a normal value, it is indicated that the tire leaks, and at this time, there may be cases such as the fixing bolts of the wheel are not tightened, the bearings are damaged, the hub is deformed, and the like, thereby causing the wheel to loosen. In other words, the tire pressure abnormality of the wheel can indirectly reflect the wheel looseness. Therefore, in the early warning of wheel looseness, whether the tire pressure of the wheel is normal is detected first, and the potential risk of whether the wheel looseness exists in the vehicle can be recognized quickly.

Likewise, the tightness of the mechanical structure of the wheel is highly correlated with the wheel looseness. The tightness of the mechanical structure of the wheel generally refers to the tightness of a fixing bolt, a hub bearing, etc. of the wheel, and when there are cases such as the fixing bolt or the bearing bolt of the wheel being not tightened, the hub bearing being deformed, etc., the tightness of the mechanical structure of the wheel is insufficient, and at this time, the fixing constraint of the wheel may be lost, thereby causing the wheel to become loose. In other words, the lack of tightness of the mechanical structure of the wheel can indirectly reflect the wheel loosening. Therefore, in the early warning of wheel looseness, whether the mechanical structure of the wheel is fastened is detected first, and the potential risk of whether the wheel looseness exists in the vehicle can be quickly identified.

In step S103, if the target tire pressure detection information is used for indicating that the tire pressure of the wheel is abnormal and/or the target fastening detection information is used for indicating that the mechanical structure of the wheel is not fastened, it is indicated that the tire pressure of the wheel is abnormal and/or the mechanical structure of the wheel is not fastened, and the potential risk of loosening of the wheel exists in the vehicle, and at this time, the movement track of the wheel in the future time period is predicted based on the wheel image, the wheel attribute data and the driving attribute data, so as to obtain the wheel movement track data of the vehicle.

Here, during the running of the vehicle, if the movement track of the wheel is not a perfect circle, the running path is regularly curved or the track moves transversely relative to the vehicle body, the wheel is illustrated as being deviated, otherwise, the wheel is illustrated as not being deviated. Whether the wheel is off tracking is highly correlated to wheel looseness. When the wheel is deviated, the conditions of insufficient dynamic balance, hub displacement and the like of the wheel are described, for example, the steering wheel is dithered due to the insufficient dynamic balance of the wheel, the wheel is deviated, and for example, the wheel is transversely displaced due to the hub displacement of the wheel, and the wheel is deviated, so that the wheel is loosened. In other words, wheel misalignment can directly reflect wheel looseness. Therefore, on the premise of determining that the potential risk of wheel looseness exists in the vehicle, the detection of the wheel movement track data of the vehicle is helpful for quickly and accurately determining whether the wheel looseness exists. It should be understood that if the target tire pressure detection information is used for indicating that the tire pressure of the wheel is normal and the target fastening detection information is used for indicating that the mechanical structure of the wheel is fastened, it is indicated that the tire pressure of the wheel is normal and the mechanical structure of the wheel is fastened, and the vehicle does not have the potential risk of loosening the wheel, and at this time, the process returns to the step S101 to implement the cycle detection.

In the step S104, after determining the wheel movement track data of the vehicle, it is determined whether the wheels of the vehicle are loose or not based on the wheel movement track data, and the wheel loosening warning process is performed on the vehicle according to the determined wheel movement track data.

Through the steps S101-S104, the embodiment of the application detects whether the tire pressure of the wheel is normal or not and whether the mechanical structure of the wheel is fastened or not on the basis of the image data and the attribute data associated with the wheel, so as to primarily identify whether the vehicle has potential risk of wheel loosening or not, and then predicts the wheel movement track data of the vehicle on the basis of the image data and the attribute data associated with the wheel of the vehicle and the attribute data associated with the running of the vehicle if the vehicle has potential risk of wheel loosening, and accordingly carries out the wheel loosening early warning processing.

In some embodiments, referring to fig. 2, the wheel image may include a ground contact image of a wheel before the vehicle is driven and an infrared image of the wheel while the vehicle is driven, the wheel attribute data may include first tire pressure data of the wheel before the vehicle is driven, and second tire pressure data, effective radius data, and hub vibration frequency data of the wheel while the vehicle is driven, and the obtaining of the target tire pressure detection information and the target fastening detection information of the vehicle according to the wheel image and the wheel attribute data in the step S102 may include the steps S201 to S202:

S201, determining a tire pressure risk coefficient of the vehicle before running according to the ground image and the first tire pressure data;

S202, tire pressure detection processing is carried out according to the tire pressure risk coefficient, the infrared image, the second tire pressure data, the effective radius data and the hub vibration frequency data, and tire pressure detection information of a vehicle during running is obtained as target tire pressure detection information.

Here, in the above-described wheel image, the ground contact image refers to a depression image of the tire ground contact shape of the wheel, which indicates the form of the wheel before the vehicle runs, in association with the tire pressure height of the wheel. Under normal conditions, the tire grounding area is uniformly elliptic, and if the tire grounding area is widened and the edge deformation is obvious, the situation that the tire pressure is insufficient is possibly indicated. The infrared image refers to an infrared thermal imaging image of the wheel, which indicates a change in thermal distribution of the wheel while rolling during running of the vehicle, in association with the tire pressure height of the wheel. Under normal conditions, the heat distribution change of the wheel during rolling should be uniform, and if the local temperature of the wheel during rolling is increased, the situation that the side wall is repeatedly bent is possibly indicated, so that the tire pressure is insufficient. Therefore, it is useful to detect whether the tire pressure of the vehicle is abnormal or not by the ground image and the infrared image.

Alternatively, but not limited to, the ground image is acquired by integrating a common camera in the wheel arch and the infrared image is acquired by integrating an infrared camera in the wheel arch.

Among the above-described wheel attribute data, the tire pressure data refers to the tire pressure of the wheel, which directly indicates the tire pressure of the wheel. When the tire pressure data is lower than the normal value, the tire pressure is insufficient. The effective radius data refers to an equivalent radius of the tire of the wheel when actually rolling under load, which is highly correlated with the tire pressure of the wheel. If the effective radius data is reduced, the situation that the tire pressure is insufficient is indicated, for example, when the tire pressure of the left front wheel is insufficient, the rotating speed of the left front wheel is slightly higher than that of the right front wheel, because the effective radius data of the left front wheel is reduced, and more turns are needed to maintain the same vehicle speed. The wheel hub vibration frequency data refers to the frequency of free vibration of the wheel hub without external excitation, and is highly related to the tire pressure of the wheel. If the wheel hub vibration frequency data is reduced, the tire rigidity is reduced, and the condition of insufficient tire pressure can be possibly caused. Therefore, it is useful to detect whether the tire pressure of the vehicle is abnormal or not by the tire pressure data, the effective radius data, and the hub vibration frequency data.

Alternatively, the tire pressure data is collected by a tire pressure sensor, the hub vibration frequency data is collected by a hub vibration sensor, the vehicle speed data of the vehicle is obtained by a vehicle speed sensor, the wheel speed data of the vehicle is obtained by a wheel speed sensor, and the ratio of the vehicle speed data relative to the wheel speed data is obtained as effective radius data, but the method is not limited to the method.

In the related art, whether the tire pressure of the wheel is abnormal is generally detected only by the tire pressure value or the tire pressure variation value of the wheel, but the tire pressure is easily interfered by factors such as temperature, load, altitude, etc., the related art easily misjudges that the tire pressure is abnormal, and the tire pressure detection accuracy thereof is to be improved. In this regard, the present embodiment introduces multi-mode data and adopts a dynamic-static two-stage tire pressure detection mode, so as to improve the accuracy of tire pressure detection.

In the above step S201, the tire pressure risk prediction is performed with the ground image of the wheel and the first tire pressure data before the vehicle is driven as references, so as to obtain the tire pressure risk coefficient of the vehicle before the vehicle is driven, and the tire pressure risk coefficient can reflect the abnormal probability of the tire pressure of the wheel of the vehicle before the vehicle is driven.

Here, the vehicle is in a stationary state before running, while the wheel is in a cold tire state, and the probability of abnormality of the tire pressure of the wheel of the vehicle before running is determined by the ground image of the wheel in the cold tire state and the tire pressure data, thereby realizing tire pressure detection in a stationary stage. The data of image mode can effectively catch the physical deformation characteristic (such as ground area is unusual, edge is irregular etc.) of wheel under cold child state, and the data of text mode can effectively catch the physical tire pressure characteristic of wheel under cold child state, and this embodiment realizes tire pressure risk prediction through introducing multi-mode data, so, can effectively promote the tire pressure detection precision of static stage, discovers the potential condition of suspected tire pressure abnormality fast, accurately to help accelerating tire pressure detection's efficiency.

In some embodiments, the determining the tire pressure risk coefficient of the vehicle before driving according to the ground contact image and the first tire pressure data may include performing feature extraction on the ground contact image to obtain a ground contact image feature, performing feature extraction on the first tire pressure data to obtain a first tire pressure feature, and determining the tire pressure risk coefficient of the vehicle before driving according to the ground contact image feature and the first tire pressure feature in combination with a machine learning method.

Here, in the tire pressure detection in the static stage, first, feature extraction is performed on the ground image to obtain the ground image feature. The grounding image features can be width features and edge deformation features of the wheels, the width features reflect the width conditions of the wheels, and the edge deformation features reflect the deformation conditions of the wheels when the wheels are grounded, so that the feature information of the wheels when the wheels are grounded can be reflected more comprehensively. And simultaneously, extracting features of the first tire pressure data to obtain first tire pressure features. The specific implementation of feature extraction may be flexibly set according to practical situations, which is not limited in this embodiment. Then, the grounding image features and the first tire pressure features are input into a first tire pressure risk prediction model trained in advance, and tire pressure risk coefficients of the vehicle before running are obtained, wherein the risk coefficients are prediction probabilities. The first tire pressure risk prediction model is a machine learning model obtained through training a plurality of first feature samples and label information corresponding to each first feature sample, the first feature samples comprise ground image feature samples and tire pressure feature samples, the label information corresponding to the first feature samples is a tire pressure risk coefficient, and the label information can be determined through expert labeling, historical data statistics and the like. In addition, the type of the first tire pressure risk prediction model may be flexibly set according to practical situations, for example, a model such as a support vector machine, a logistic regression, and the like, but is not limited thereto. In this way, the tire pressure risk prediction processing is performed by the machine learning method, and since the machine learning method has excellent performance, the accuracy of the tire pressure risk prediction can be effectively improved by introducing the machine learning method in the tire pressure risk prediction.

In some embodiments, the determining the tire pressure risk coefficient of the vehicle before driving according to the ground-contact image and the first tire pressure data may include performing tire pressure risk prediction according to the ground-contact image to obtain a first risk coefficient, performing tire pressure risk prediction according to the first tire pressure data to obtain a second risk coefficient, and determining the tire pressure risk coefficient of the vehicle before driving according to the first risk coefficient and the second risk coefficient.

In the tire pressure detection in the static stage, firstly, tire pressure risk prediction is performed according to a ground image and a second tire pressure prediction model trained in advance, so as to obtain a first risk coefficient, wherein the first risk coefficient indicates the probability of abnormal tire pressure of wheels of the vehicle before the vehicle runs, and the risk coefficient is the prediction probability. The second tire pressure risk prediction model is a model obtained through training of a plurality of ground-connected image samples and label information corresponding to each ground-connected image sample, the label information corresponding to the ground-connected image sample is a risk coefficient, and the risk coefficient can be determined through expert labeling, historical data statistics and other modes. In addition, the type of the second tire pressure risk prediction model may be flexibly set according to the actual situation, for example, may be a convolutional neural network, but is not limited thereto. Meanwhile, tire pressure risk prediction is carried out according to the first tire pressure data and a third tire pressure prediction model trained in advance, so that a second risk coefficient is obtained, the second risk coefficient indicates the probability of abnormal tire pressure of the wheels of the vehicle before the vehicle runs, and the risk coefficient is the prediction probability. The third tire pressure prediction model is a model obtained by training a plurality of tire pressure data samples and label information corresponding to each tire pressure data sample, the label information corresponding to the tire pressure data sample is a risk coefficient, and the label information can be determined through expert labeling, historical data statistics and other modes. In addition, the type of the third tire pressure risk prediction model may be flexibly set according to the actual situation, and may be, for example, a model such as a support vector machine, logistic regression, etc., but is not limited thereto. And then, integrating the first risk coefficient and the second risk coefficient to obtain the tire pressure risk coefficient of the vehicle before driving. For example, the average of the first risk coefficient and the second risk coefficient is calculated as the tire pressure risk coefficient of the vehicle before running. For another example, the first risk coefficient and the second risk coefficient are weighted and summed to obtain the tire pressure risk coefficient of the vehicle before driving. In this way, the tire pressure risk prediction is performed from the aspect of the data of the image mode, the tire pressure risk on the basis of the physical deformation characteristics can be accurately determined, the tire pressure risk on the basis of the physical tire pressure characteristics can be accurately determined from the aspect of the data of the text mode, the tire pressure risk reflected by the data of different modes is considered to be different, and the final tire pressure risk is determined by integrating the tire pressure risks corresponding to the multiple modes, so that the accuracy of the tire pressure risk prediction is further improved.

In the above step S202, the target tire pressure detection information indicating whether the tire pressure of the wheel of the vehicle is abnormal while the vehicle is running is determined by the multidimensional factors such as the infrared image, the second tire pressure data, the effective radius data, the hub vibration frequency data, and the like of the wheel in the running state on the basis of the probability that the tire pressure of the wheel is abnormal before the vehicle is running.

Here, on the one hand, the present embodiment sufficiently considers the multi-modal data highly correlated with the tire pressure of the wheel, by which the tire pressure detection in the dynamic stage is achieved, compared to the manner in which the tire pressure detection is achieved by only the tire pressure value or the tire pressure variation value. On the other hand, compared with the way of realizing tire pressure detection only by real-time data when the vehicle is traveling, the present embodiment considers not only real-time data related to the tire pressure height when the vehicle is traveling but also the tire pressure risk probability of the vehicle before traveling in the tire pressure detection in the dynamic stage. In this way, the multi-dimensional data is introduced during the tire pressure detection in the dynamic stage, and the tire pressure conditions of the vehicle in the static state and the non-static state are considered, so that the comprehensiveness, the accuracy and the reliability of the tire pressure detection can be effectively improved, and the misjudgment risk is reduced.

In some embodiments, considering that the tire pressure detection of the vehicle at the current time is important, the longest cycle time of the above step S202 is thirty seconds, that is, the above step S202 is performed every thirty seconds or less (for example, every twenty seconds), and the newly performed result overlaps the last performed result, thereby realizing the real-time tire pressure detection.

In some embodiments, the tire pressure detection processing is performed according to the tire pressure risk coefficient, the infrared image, the second tire pressure data, the effective radius data and the hub vibration frequency data to obtain tire pressure detection information of the vehicle during driving, which may include performing feature extraction on the infrared image, the second tire pressure data, the effective radius data and the hub vibration frequency data to obtain an infrared temperature field feature, a second tire pressure feature, an effective radius feature and a hub vibration frequency feature, and obtaining the tire pressure detection information of the vehicle during driving according to the tire pressure risk coefficient, the infrared temperature field feature, the second tire pressure feature, the effective radius feature and the hub vibration frequency feature in combination with a machine learning method.

Here, when tire pressure is detected, first, the infrared image, the second tire pressure data, the effective radius data and the hub vibration frequency data are respectively subjected to feature extraction to obtain an infrared temperature field feature, a second tire pressure feature, an effective radius feature and a hub vibration frequency feature. This makes it possible to extract characteristic information related to the tire pressure height while the vehicle is running. The specific implementation of feature extraction may be flexibly set according to practical situations, which is not limited in this embodiment. Then, the tire pressure risk coefficient, the infrared temperature field characteristic, the second tire pressure characteristic, the effective radius characteristic and the hub vibration frequency characteristic are input into a tire pressure detection model trained in advance, and tire pressure detection information of the vehicle during running is obtained through the tire pressure detection model. The tire pressure detection model is a model obtained through training a plurality of second characteristic samples and label information corresponding to each second characteristic sample, wherein the second characteristic samples comprise a tire pressure risk coefficient sample, an infrared temperature field characteristic sample, a tire pressure characteristic sample, an effective radius characteristic sample and a hub vibration frequency characteristic sample, the label information corresponding to the second characteristic sample represents whether the tire pressure of a wheel is normal or not, the label information is usually represented as one or zero, the first label represents that the tire pressure is normal, and the zero represents that the tire pressure is abnormal. In addition, the tire pressure detection model may be flexibly set according to practical situations, for example, a support vector machine, a random forest, etc., but is not limited thereto. In this way, the tire pressure detection processing is performed by the machine learning method, and since the machine learning method has superior performance, the method of introducing the machine learning at the time of tire pressure detection can effectively improve the accuracy of tire pressure detection.

In some embodiments, the tire pressure detection processing is performed according to the tire pressure risk coefficient, the infrared image, the second tire pressure data, the effective radius data and the hub vibration frequency data to obtain tire pressure detection information of the vehicle during driving, which may include performing temperature detection according to the infrared image to obtain temperature detection information, wherein the temperature detection information is used for indicating whether a wheel temperature field of the vehicle is abnormal, if any one of the temperature detection information, the tire pressure risk coefficient, the second tire pressure data, the effective radius data or the hub vibration frequency data meets a first preset condition, determining the tire pressure detection information of the vehicle during driving as being used for indicating that the tire pressure of the vehicle is abnormal, otherwise determining the tire pressure detection information of the vehicle during driving as being used for indicating that the tire pressure of the vehicle is normal, wherein the first preset condition includes that the temperature detection information is used for indicating that the wheel temperature field of the vehicle is abnormal, the tire pressure risk coefficient is higher than a tire pressure risk threshold, the second tire pressure data is out of a tire pressure range, and the effective radius data is out of a radius range, and the hub vibration frequency data is out of the first frequency range.

Here, in tire pressure detection, first, an infrared image is input into a temperature detection model trained in advance, and temperature detection information indicating whether or not a wheel temperature field of a vehicle is abnormal is obtained by the temperature detection model. The temperature detection model is a model obtained through training of a plurality of infrared image samples and label information corresponding to each infrared image sample, the label information corresponding to the infrared image sample indicates whether a wheel temperature field is abnormal or not, the temperature detection model is usually indicated as one or zero, the one indicates that the wheel temperature field is normal, and the zero indicates that the wheel temperature field is abnormal. In addition, the temperature detection model can be flexibly set according to practical situations, for example, a convolutional neural network, but is not limited to the above. And then judging whether any one of temperature detection information, tire pressure risk coefficient, second tire pressure data, effective radius data or wheel hub vibration frequency data meets a first preset condition, if so, determining that the tire pressure of the vehicle at the current moment is abnormal, determining the tire pressure detection information of the vehicle at the moment as being used for indicating that the tire pressure of the vehicle is abnormal, otherwise, determining that the tire pressure of the vehicle at the current moment is normal, and determining the tire pressure detection information of the vehicle at the moment as being used for indicating that the tire pressure of the vehicle is normal. Therefore, the infrared image is converted into the characteristic information which can be used for comparison, the tire pressure detection in the dynamic stage is realized through simple comparison operation, the tire pressure detection efficiency can be improved while the tire pressure detection accuracy is ensured, and the real-time requirement is met. Alternatively, the tire pressure risk threshold value, the tire pressure range, the radius range, and the first frequency range may be set according to actual situations, which is not particularly limited in this embodiment.

In some embodiments, referring to fig. 3, the above-mentioned wheel attribute data includes fastening torque data, axial displacement data and radial displacement data of the wheel before the vehicle is driven, and driving torque data, wheel speed data, working sound data and wheel hub vibration frequency data of the wheel while the vehicle is driven, and the above-mentioned step S102 of obtaining the target tire pressure detection information and target fastening detection information of the vehicle according to the wheel image and the wheel attribute data may include the following steps S301 to S302:

S301, determining a fastening risk coefficient of the vehicle before running according to fastening torque data, axial displacement data and radial displacement data;

S302, fastening detection processing is carried out according to the fastening risk coefficient, the driving torque data, the wheel speed data, the working sound data and the wheel hub vibration frequency data, and fastening detection information of a vehicle during running is obtained as target fastening detection information.

Here, in the above-described wheel attribute data, the tightening torque data refers to tightening torque of the wheel nut, and is highly correlated with the tightness of the wheel. The tightening torque data should normally be higher than a standard value (for example, 80-120N m in a car) and when the tightening torque data is lower than the standard value, it is indicated that the wheel nuts are loosened, and the tightness of the wheel may be insufficient. The axial displacement data refers to displacement of the wheel in the axial direction, and is highly correlated with the tightness of the wheel. The axial displacement data should normally be higher than a standard value (for example, higher than 0.5 mm), and when the axial displacement data is lower than the standard value, it is indicated that the wheel is loose in the axial direction, and the tightness of the wheel may be insufficient. The radial displacement data represents the displacement of the wheel in the radial direction, and is highly correlated with the tightness of the wheel. The radial displacement data should normally be higher than a standard value (for example, higher than 0.5 mm), and when the radial displacement data is lower than the standard value, it is indicated that the wheel is loose in the radial direction, and the tightness of the wheel may be insufficient. The driving torque data refers to driving torque of the wheel, and is highly correlated with the tightness of the wheel. When the driving torque data exceeds the preset range, the abnormal distribution of the driving torque data is indicated, the wheel end resistance is reduced, at the moment, the condition that the wheels are loose possibly exists, and the tightness of the wheels is insufficient. The wheel speed data refers to the rotational speed of the wheel, and is highly correlated with the tightness of the wheel. When the variation value of the wheel speed data exceeds the preset range, the fluctuation of the wheel speed data is abnormal, the gap between the contact surface of the wheel hub and the brake disc is changed, and at the moment, the condition of loose wheels possibly exists, and the tightness of the wheels is insufficient. The working sound data is frequency data of the wheel during rotation, and is highly correlated with the tightness of the wheel. When the working sound data is abnormal (e.g., high-frequency knocks or low-frequency resonance sounds occur), it is indicated that there may be a case where the wheels are loose, and the tightness of the wheels is insufficient. The hub vibration frequency data refers to the frequency at which the hub of the wheel freely vibrates without external excitation, which is highly correlated with the tightness of the wheel. In normal cases, the hub vibration frequency data is usually concentrated at a low frequency (for example, less than 200 Hz), and if the hub vibration frequency data is increased, the high frequency component energy is significantly increased, and in such cases, such as bolt knocking, friction resonance and the like, the wheel may be loose, and the tightness of the wheel is insufficient. Therefore, it is useful to detect whether the wheel tightness of the vehicle is abnormal by tightening torque data, axial displacement data, radial displacement data, driving torque data, wheel speed data, operating sound data, and wheel hub vibration frequency data.

Alternatively, the fastening torque data is collected by an electronic torque sensor, the axial displacement data and the radial displacement data are collected by a displacement sensor, the driving torque data are collected by a torque sensor, the wheel speed data are collected by a wheel speed sensor, and the working sound data are collected by an acoustic sensor, but not limited thereto.

In the related art, generally, only the degree of tightening of the wheels before the vehicle runs is detected, and there is little method of detecting the degree of tightening of the wheels while the vehicle runs. In contrast, the present embodiment introduces multi-modal data and adopts a dynamic-static two-stage fastening detection method, so as to accurately detect the fastening degree of the wheels when the vehicle is running.

In the step S301, the risk prediction of the tightness of the wheel is performed based on the tightening torque data, the axial displacement data, and the radial displacement data of the wheel before the vehicle runs, so as to obtain the tightening risk coefficient of the vehicle before the vehicle runs, which can reflect the probability of the insufficient tightness of the wheel of the vehicle before the vehicle runs.

Here, the vehicle is in a stationary state before running, and at this time, the wheel is in a cold tire state, and the probability of insufficient tightness of the wheel of the vehicle before running is determined by the tightening torque data, the axial displacement data, and the radial displacement data of the wheel in the cold tire state, thereby realizing the wheel tightening detection in the stationary stage. The data of text modes such as fastening torque data, axial displacement data, radial displacement data and the like can effectively capture physical characteristics related to the tightness of the wheel, and the risk prediction of the tightness of the wheel is realized by introducing multidimensional data, so that the detection precision of the tightness of the wheel in a static stage can be effectively improved, the potential condition of insufficient tightness of a suspected wheel can be rapidly and accurately found, and the detection efficiency of the tightness of the wheel can be improved.

In some embodiments, the determining the fastening risk coefficient of the vehicle before driving according to the fastening torque data, the axial displacement data and the radial displacement data may include performing feature extraction on the fastening torque data, the axial displacement data and the radial displacement data to obtain a fastening torque feature, an axial displacement feature and a radial displacement feature, and determining the fastening risk coefficient of the vehicle before driving according to the fastening torque feature, the axial displacement feature and the radial displacement feature in combination with a machine learning method.

Here, in the wheel tightness detection in the static stage, first, the tightening torque data, the axial displacement data, and the radial displacement data are respectively subjected to feature extraction to obtain the tightening torque feature, the axial displacement feature, and the radial displacement feature, so that the tightening feature information reflecting the wheel in the cold state can be extracted. The specific implementation of feature extraction may be flexibly set according to practical situations, which is not limited in this embodiment. And then, inputting the fastening torque characteristic, the axial displacement characteristic and the radial displacement characteristic into a first fastening risk prediction model to obtain a fastening risk coefficient of the vehicle before running, wherein the risk coefficient is the prediction probability. The first fastening risk prediction model is a model obtained through training a plurality of third characteristic samples and label information corresponding to each third characteristic sample, the third characteristic samples comprise fastening torque characteristic samples, axial displacement characteristic samples and radial displacement characteristic samples, and the label information corresponding to the third characteristic samples is a fastening risk coefficient which can be determined through expert labeling, historical data statistics and the like. In addition, the type of the first tightening risk prediction model may be flexibly set according to the actual situation, and may be, for example, a model such as a support vector machine, a logistic regression, etc., but is not limited thereto. In this way, the wheel-tightness risk prediction processing is performed by the machine learning method, and since the machine learning method has excellent performance, the accuracy of the wheel-tightness risk prediction can be effectively improved by introducing the machine learning method in the wheel-tightness risk prediction.

In some embodiments, the determining the fastening risk coefficient of the vehicle before driving according to the fastening torque data, the axial displacement data and the radial displacement data may include performing wheel tightness risk prediction according to the fastening torque data to obtain a third risk coefficient, performing wheel tightness risk prediction according to the axial displacement data to obtain a fourth risk coefficient, performing wheel tightness risk prediction according to the radial displacement data to obtain a fifth risk coefficient, and determining the fastening risk coefficient of the vehicle before driving according to the third risk coefficient, the fourth risk coefficient and the fifth risk coefficient.

Here, in the wheel-tightness detection in the static stage, first, the wheel-tightness risk prediction is performed based on the tightening torque data in combination with the second tightening risk prediction model trained in advance, and a third risk coefficient is obtained. The second tightening risk prediction model is a model obtained through training of a plurality of tightening torque data samples and label information corresponding to each tightening torque data sample. And simultaneously, carrying out wheel tightness risk prediction according to the axial displacement data and a pre-trained third tightening risk prediction model to obtain a fourth risk coefficient. The third fastening risk prediction model is a model obtained through training of a plurality of axial displacement data samples and label information corresponding to each axial displacement data sample. And carrying out wheel tightness risk prediction according to the radial displacement data and a fourth pre-trained tightening risk prediction model to obtain fifth risk data. The fourth fastening risk prediction model is a model obtained through training of a plurality of radial displacement data samples and label information corresponding to each radial displacement data sample. It should be understood that, in each fastening risk prediction model, the risk coefficient output by the fastening risk prediction model is the prediction probability, and the label information corresponding to the data sample during training is the risk coefficient, which can be determined by expert labeling, historical data statistics and other manners. In addition, the types of the tightening risk prediction models may be flexibly set according to actual situations, for example, random forest, logistic regression, etc., but not limited thereto. And then, integrating the third risk coefficient, the fourth risk coefficient and the fifth risk coefficient to obtain a fastening risk coefficient of the vehicle before driving. For example, the average of the third risk coefficient, the fourth risk coefficient, and the fifth risk coefficient is calculated as the fastening risk coefficient of the vehicle before running. For another example, the third risk coefficient, the fourth risk coefficient and the fifth risk coefficient are weighted and summed to obtain a fastening risk coefficient of the vehicle before driving. In this way, the fastening torque data, the axial displacement data and the radial displacement data can respectively reflect the fastening risks on different physical characteristics, and the final fastening risk is determined by integrating the fastening risks corresponding to multiple dimensions in consideration of different fastening risks reflected by the three dimensional data, so that the accuracy of predicting the fastening risk of the wheel is further improved.

In step S302 described above, the target fastening detection information indicating whether the mechanical structure of the wheel of the vehicle is fastened while the vehicle is running is determined by multidimensional factors such as driving torque data, wheel speed data, operating sound data, and hub vibration frequency data of the wheel in a running state, on the basis of the probability that the fastening of the wheel is insufficient before the vehicle is running.

Here, on the one hand, the present embodiment fully considers the multi-dimensional data highly correlated with the wheel-tightness, and realizes the wheel-tightness detection in the dynamic stage by these multi-dimensional data. On the other hand, in the present embodiment, in the dynamic-stage wheel-tightness detection, not only real-time data highly correlated with the wheel-tightness at the time of vehicle running but also the risk probability of the wheel-tightness of the vehicle before running is considered. In this way, the multi-dimensional data is introduced in the wheel tightness detection in the dynamic stage, and the wheel tightness conditions of the vehicle when the vehicle is stationary and when the vehicle is not stationary are considered, so that the comprehensiveness, accuracy and reliability of the wheel tightness detection can be effectively improved, and the misjudgment risk is reduced.

In some embodiments, considering that the wheel tightness detection of the vehicle at the current moment is important, the longest cycle time of the above step S302 is thirty seconds, that is, the above step S302 is performed every thirty seconds or less (for example, every twenty seconds), and the newly performed result overlaps the last performed result, thereby realizing the real-time wheel tightness detection.

In some embodiments, the fastening detection processing is performed according to the fastening risk coefficient, the driving torque data, the wheel speed data, the working sound data and the wheel hub vibration frequency data to obtain fastening detection information of the vehicle during running as target fastening detection information, which may include performing feature extraction on the driving torque data, the wheel speed data, the working sound data and the wheel hub vibration frequency data to obtain driving torque features, wheel speed features, working sound features and wheel hub vibration frequency features, and combining a machine learning method to obtain fastening detection information of the vehicle during running according to the fastening risk coefficient, the driving torque features, the wheel speed features, the working sound features and the wheel hub vibration frequency features.

Here, in the wheel tightness detection, first, the driving torque data, the wheel speed data, the working sound data, and the hub vibration frequency data are respectively subjected to feature extraction to obtain the driving torque feature, the wheel speed feature, the working sound feature, and the hub vibration frequency feature. This makes it possible to extract characteristic information highly correlated with the wheel tightness when the vehicle is running. The specific implementation of feature extraction may be flexibly set according to practical situations, which is not limited in this embodiment. Then, the fastening risk coefficient, the driving torque characteristic, the wheel speed characteristic, the working sound characteristic and the hub vibration frequency characteristic are input into a pre-trained fastening detection model to obtain fastening detection information of the vehicle during running. The fastening detection model is a model obtained through training a plurality of fourth characteristic samples and label information corresponding to each fourth characteristic sample, the fourth characteristic samples comprise a fastening risk coefficient sample, a driving torque characteristic sample, a wheel speed characteristic sample, a working sound characteristic sample and a wheel hub vibration frequency characteristic sample, the label information corresponding to the fourth characteristic sample indicates whether the fastening performance of the wheel is normal or not, the label information is usually indicated as one or zero, the first characteristic sample indicates that the fastening performance of the wheel is normal, and the zero indicates that the fastening performance of the wheel is abnormal. In addition, the fastening detection model may be flexibly set according to practical situations, for example, a support vector machine, a random forest, and the like, but is not limited thereto. In this way, the wheel-tightness detection processing is performed by the machine learning method, and since the machine learning method has excellent performance, the accuracy of the wheel-tightness detection can be effectively improved by introducing the machine learning method at the time of the wheel-tightness detection.

In some embodiments, the fastening detection processing is performed according to the fastening risk coefficient, the driving torque data, the wheel speed data, the working sound data and the wheel hub vibration frequency data to obtain fastening detection information of the vehicle during driving as target fastening detection information, which may include performing sound detection according to the working sound data to obtain sound detection information, wherein the sound detection information is used for indicating whether working sound of the wheel is abnormal, if any one of the fastening risk coefficient, the driving torque data, the wheel speed data, the sound detection information or the wheel hub vibration frequency data meets a second preset condition, determining the fastening detection information of the vehicle during driving as mechanical structure fastening for indicating the wheel is not fastened, and otherwise determining the fastening detection information of the vehicle during driving as mechanical structure fastening for indicating the wheel, wherein the second preset condition includes that the sound detection information is used for indicating that the working sound of the wheel is abnormal, the fastening risk coefficient is higher than a fastening risk threshold, the driving torque data is located outside a driving torque range, and the wheel speed vibration frequency data is located outside a wheel speed range.

Here, in the wheel tightness detection, first, the operation sound data is input into a sound detection model trained in advance, and sound detection information indicating whether or not the wheel operation sound of the vehicle is abnormal is obtained by the sound detection model. The sound detection model is a model obtained by training a plurality of working sound samples and label information corresponding to each working sound sample, wherein the label information corresponding to the working sound sample indicates whether working sound of a wheel is abnormal or not, the model is usually represented as one or zero, the working sound of the wheel is normal, and the zero indicates that the working sound of the wheel is abnormal. In addition, the sound detection model may be flexibly set according to practical situations, for example, a support vector machine, a decision tree, etc., but is not limited thereto. Then, judging whether any one of the fastening risk coefficient, the driving torque data, the wheel speed data, the sound detection information or the wheel hub vibration frequency data meets a second preset condition, if yes, determining that the fastening of the wheel of the vehicle at the current moment is insufficient, determining that the mechanical structure of the wheel is not fastened when the vehicle is running, otherwise, determining that the fastening of the wheel of the vehicle at the current moment meets the requirement, and determining that the fastening of the wheel is not fastened when the vehicle is running. Therefore, the working sound data are converted into the characteristic information which can be used for comparison, and the wheel tightness detection in the dynamic stage is realized through simple comparison operation, so that the accuracy of the wheel tightness detection is ensured, the efficiency of the wheel tightness detection is improved, and the real-time requirement is met. Alternatively, the fastening risk threshold value, the driving torque range, the wheel speed range, and the second frequency range may all be set according to actual conditions, which is not particularly limited in the present embodiment.

In some embodiments, referring to fig. 4, the wheel image may include an infrared image of a wheel when the vehicle is traveling, and the step S103 of obtaining the wheel movement track data of the vehicle according to the wheel image, the wheel attribute data, and the traveling attribute data may include the following steps S401 to S403:

s401, track prediction processing is carried out according to driving attribute data and wheel attribute data, and initial wheel movement track data of a vehicle are obtained;

s402, determining a track correction coefficient of the vehicle according to the infrared image;

S403, correcting the initial wheel movement track data according to the track correction coefficient to obtain the wheel movement track data.

In the step S401, the driving attribute data and the wheel attribute data are input into the first track prediction model trained in advance, so as to obtain initial wheel movement track data of the vehicle, where the initial wheel movement track data is in a line shape, and may include coordinate positions of the wheels in a vehicle body coordinate system at a plurality of future moments. The wheel attribute data input into the first trajectory prediction model may be second tire pressure data, effective radius data, hub vibration frequency data, driving torque data, wheel speed data, working sound data, and hub vibration frequency data of the wheel while the vehicle is running. The first track prediction model may be a model obtained by training a plurality of first data samples and wheel motion track samples corresponding to each first data sample, where the first data samples include a driving attribute data sample and a wheel attribute data sample. The type of the first trajectory prediction model may be flexibly set according to practical situations, for example, but not limited to, a support vector machine, a logistic regression, and the like. Here, the driving attribute data can reflect the real condition of the vehicle during driving, the wheel attribute data can reflect the real condition of the wheels during driving, the real condition of the vehicle during driving and the real condition of the wheels during driving affect the movement track of the wheels together, and when the potential risk of loosening of the wheels of the vehicle is determined, the embodiment performs track prediction by comprehensively considering the factors of the two dimensions, so that the initial wheel movement track data of the vehicle can be obtained, and the accuracy of the wheel movement track prediction is effectively improved.

Alternatively, the driving attribute data may be flexibly set according to actual situations, which is not specifically limited in this embodiment. For example, the driving attribute data may include, but is not limited to, vehicle speed data, steering angle data, yaw rate data, lateral acceleration data, longitudinal acceleration data, braking force data, and the like.

In step S402, since the driving attribute data and the wheel attribute data are mostly data acquired by the sensor, the sensor is easily affected by environmental factors, and thus there may be an error in the initial wheel movement trace data obtained therefrom. In contrast, the present embodiment determines a trajectory correction coefficient of the vehicle for correcting the initial wheel movement trajectory data based on the infrared image of the wheel when the vehicle is running. Here, since the infrared image of the wheel when the vehicle is running is data obtained by the infrared camera, which is not easily affected by environmental factors, and the real condition of the wheel can be accurately reflected, it is helpful to accurately correct the initial wheel movement track data by determining the track correction coefficient from the infrared image of the wheel when the vehicle is running.

In some embodiments, determining the track correction coefficient of the vehicle according to the infrared image may include extracting features of the infrared image to obtain infrared temperature field features, and searching a preset database according to the infrared temperature field features to obtain the track correction coefficient of the vehicle.

Here, first, the infrared image is subjected to feature extraction to obtain infrared temperature field features, so that feature information representing the actual condition of the wheel can be extracted. The specific implementation of feature extraction is not particularly limited. In this embodiment, the infrared temperature field is characterized by a specific value that is indicative of the average temperature in the temperature field of the wheel. And then searching a preset database according to the infrared temperature field characteristics, wherein the preset database is pre-stored with a plurality of infrared temperature field characteristic samples and coefficient values corresponding to the infrared temperature field characteristic samples, and the coefficient values corresponding to the infrared temperature field characteristics can be obtained through searching and used as the track correction coefficients of the vehicle. Here, the required track correction coefficient can be quickly found through simple database traversal operation, and the acquisition efficiency of the track correction coefficient can be effectively improved.

In some embodiments, determining the trajectory correction coefficient of the vehicle according to the infrared image may include extracting features of the infrared image to obtain infrared temperature field features, and obtaining the trajectory correction coefficient of the vehicle according to the infrared temperature field features and combining a machine learning method.

Here, first, the infrared image is subjected to feature extraction to obtain infrared temperature field features, so that feature information representing the actual condition of the wheel can be extracted. The specific implementation of feature extraction is not particularly limited. Then, the infrared temperature field characteristics are input into a coefficient prediction model to obtain the track correction coefficient of the vehicle. The coefficient prediction model is a machine learning model obtained through training a plurality of infrared temperature field feature samples and label information corresponding to each infrared temperature field feature sample, and the label information corresponding to the infrared temperature field feature sample is a track correction coefficient. In addition, the type of the coefficient prediction model may be flexibly set according to practical situations, for example, a support vector machine, logistic regression, etc., but is not limited thereto. Here, the prediction processing of the trajectory correction coefficient is performed by a machine learning method, which has excellent performance, so that the accuracy of the trajectory correction coefficient can be effectively improved by introducing the machine learning method in determining the trajectory correction coefficient.

In the step S403, after the track correction coefficient is obtained, the initial wheel movement track data is corrected on the basis of the track correction coefficient, so as to obtain the wheel movement track data, thereby improving the accuracy of the wheel movement track data. Therefore, on the premise of determining that the potential risk of wheel looseness exists in the vehicle, the wheel movement track data of the vehicle are accurately determined, and whether the wheels are loosened or not can be quickly and accurately determined.

In some embodiments, the correcting the initial wheel movement track data according to the track correction coefficient to obtain the wheel movement track data may include obtaining the wheel movement track data according to the track correction coefficient and the initial wheel movement track data in combination with a machine learning method.

Here, a machine learning method is introduced, and the trajectory correction coefficient and the initial wheel movement trajectory data are input into a second trajectory prediction model trained in advance, so as to obtain the wheel movement trajectory data. The second track prediction model is a model obtained by training a plurality of second data samples and wheel motion track samples corresponding to the second data samples, and the second data samples can comprise the wheel motion track samples and track correction coefficient samples. The type of the second trajectory prediction model may be flexibly set according to practical situations, for example, but not limited to, a support vector machine, a logistic regression, and the like. Here, the operation of the trajectory correction is performed by the machine learning method, and since the machine learning method has superior performance, the method of introducing the machine learning when correcting the trajectory can effectively improve the accuracy of the trajectory correction.

In some embodiments, the correcting the initial wheel movement track data according to the track correction coefficient to obtain the wheel movement track data may include multiplying the track correction coefficient and the initial wheel movement track data to obtain the wheel movement track data.

Here, since the initial wheel movement locus data includes coordinate positions of the wheels at a plurality of future times in the vehicle body coordinate system, when the locus is corrected, the locus correction coefficient may be multiplied by the coordinate position for each coordinate position, and the coordinate position to which the locus correction coefficient is given may be obtained as a new coordinate position. By traversing the coordinate positions, new coordinate positions can be obtained, thereby obtaining final wheel movement track data. Here, by performing the operation of track correction by means of giving coefficients, the initial wheel movement track data can be corrected quickly, the track correction accuracy is ensured, and at the same time, the track correction rate is increased, thereby meeting the real-time requirement.

In some embodiments, referring to fig. 5, in the step S104, the wheel looseness early warning process is performed on the vehicle based on the wheel movement track data, and the steps may include the following steps S501-S502:

S501, performing deviation detection processing according to the wheel movement track data to obtain deviation detection information of the vehicle, wherein the deviation detection information is used for indicating whether the wheel deviates in a future time period;

s502, performing wheel looseness early warning processing on the vehicle according to the deviation detection information.

In the above step S501, the wheel deviation detection process is performed with the wheel movement track data as a reference, so as to obtain deviation detection information for indicating whether the wheel is deviated in a future time period. Here, whether the wheel is deviated in the future time period is determined based on the movement track data of the wheel in the future time period, so that the deviation degree of the wheel in the future time period can be accurately determined, meanwhile, the wheel looseness can be directly reflected by considering the deviation of the wheel, and therefore, the determination of the deviation degree by the movement track data can be helpful for quickly and accurately determining whether the wheel looseness is caused.

In some embodiments, the performing the deviation detection process according to the wheel movement track data to obtain the deviation detection information of the vehicle may include inputting the wheel movement track data into a deviation detection model to obtain the deviation detection information.

Here, the wheel movement track data is input into the deviation detection model, and the deviation detection information is obtained through the identification of the deviation detection model. The deviation detection model is a model obtained by training a plurality of wheel movement track samples and label information corresponding to each wheel movement track sample, wherein the label information corresponding to the wheel movement track sample indicates whether a wheel deviates, and is usually one or zero, and one indicates that the wheel deviates, and zero indicates that the wheel does not deviate. In addition, the type of the deviation detection model may be flexibly set according to the actual situation, for example, it may be a support vector machine, a logistic regression, a convolutional neural network, etc., but is not limited thereto. Therefore, the deviation detection model is introduced to realize automatic deviation detection, and the deviation detection model has excellent performance, so that the accuracy of deviation detection can be effectively improved.

In the step S502, when the wheel is off-tracking, it is indicated that there are conditions such as insufficient dynamic balance and hub displacement, for example, the insufficient dynamic balance of the wheel will cause steering wheel shake, the wheel is off-tracking, for example, the hub displacement of the wheel will cause lateral displacement, and the wheel is off-tracking, at this time, the wheel will be loosened. In other words, wheel misalignment can directly reflect wheel looseness. Therefore, the vehicle is subjected to the wheel looseness early warning processing with the deviation detection information as a reference.

In some embodiments, in the step S501, the performing the deviation detection process according to the wheel movement track data to obtain the deviation detection information of the vehicle may include:

Determining expected wheel movement trace data of the vehicle and similarity data of the wheel movement trace data;

And if the similarity data is smaller than or equal to a preset threshold value, determining the deviation detection information to be used for indicating the deviation of the wheel in a future time period, otherwise, determining the deviation detection information to be used for indicating that the wheel is not deviated in the future time period.

Here, in the running deviation detection, first, expected wheel movement track data of the vehicle is acquired, where the expected wheel movement track data includes expected coordinate positions of the wheels at a plurality of future moments in a vehicle body coordinate system, which may be stored in a preset database in advance, and may be determined by means of expert labeling, statistics of historical data, and the like. Then, similarity data of expected wheel movement track data and wheel movement track data of the vehicle are calculated, so that the difference between the actual movement track and the expected movement track of the vehicle can be effectively measured. The type of the similarity may be flexibly set according to practical situations, for example, the similarity may be cosine similarity, euclidean distance, or the like, but is not limited thereto. It should be understood that since the desired wheel movement trace data and the wheel movement trace data each include a plurality of coordinate positions, the desired wheel movement trace data and the wheel movement trace data can be actually expressed as one series of data, and thus the similarity between the two can be directly calculated. Then, whether the similarity data is smaller than or equal to a preset threshold value is judged. If so, the fact that the difference between the actual movement track and the expected movement track of the wheel is large is indicated, and the wheel is deviated, and at the moment, deviation detection information is determined to be used for indicating the deviation of the wheel in a future time period. If not, the difference between the actual movement track and the expected movement track of the wheel is smaller, and the wheel is not deviated, and at the moment, deviation detection information is determined to be used for indicating that the wheel is not deviated in a future time period. Therefore, the abstract track difference is converted into the numerical index through similarity calculation, the difference between the actual motion track and the expected motion track of the wheel can be accurately measured, and then whether the wheel is deviated in a future time period or not is judged on the basis of the difference between the actual motion track and the expected motion track, so that the accuracy of deviation detection can be effectively improved.

In some embodiments, in the step S502, the performing the wheel loosening warning process on the vehicle according to the deviation detection information may include:

if the deviation detection information is used for indicating the deviation of the vehicle in a future time period, performing wheel looseness early warning processing on the vehicle;

or if the deviation detection information is used for indicating that the vehicle is not deviated in the future time period, the looseness early warning processing is not carried out.

Here, if the deviation detection information is used for indicating that the vehicle deviates in a future time period, the vehicle is subjected to wheel loosening early warning processing, for example, the vehicle body domain controller can output an early warning display signal to the cabin domain controller when the vehicle is subjected to the wheel loosening early warning processing, so that the cabin domain controller generates a wheel loosening early warning icon based on the early warning display signal and displays the wheel loosening early warning icon on an instrument panel so as to prompt a driver that the potential risk of wheel loosening currently exists. If the deviation detection information is used for indicating that the vehicle is not deviated in a future time period, loosening early warning processing is not carried out. Therefore, the deviation detection information is used as a reference to realize the wheel looseness early warning processing, and the accuracy of the wheel looseness early warning can be further improved.

In some embodiments, after the wheel looseness early warning process is performed on the vehicle, the process returns to the step S101 to implement the cycle detection until the deviation detection information is used to indicate that the vehicle is not deviated in the future time period, and the wheel looseness early warning is stopped. Similarly, after the looseness early-warning process is not performed, the process returns to step S101 described above to realize loop detection.

In some embodiments, all of the models involved are integrated in the same artificial intelligence module to form a multi-task learning model.

In some embodiments, referring to FIG. 6, the training process of the related model may include building a training set and a test set, starting training the model, inputting the training set of the current round into the model, performing accuracy test on the model of the current round by using the test set under the condition that one round of training is finished, obtaining accuracy of the model of the current round, determining that the model training is completed if the accuracy of the model of the current round is greater than an accuracy threshold, outputting the model of the current round as a trained model, and otherwise jumping to the next round. Alternatively, the accuracy threshold may be flexibly set according to the actual situation, for example, the accuracy threshold may be 98%, but is not limited thereto.

In order to facilitate understanding of the wheel looseness early-warning method of the present application, a practical application scenario of the wheel looseness early-warning method of the present application is illustrated herein.

In the application scene, the vehicle is a truck, the truck needs to frequently run on a highway due to the application of the truck, and compared with a common car, a sport utility vehicle and the like, the truck has higher probability of loosening wheels. Referring to fig. 7, the method according to the embodiment of the present application performs the following loosening pre-warning treatment on each wheel of the truck:

The data source acquires a ground image of the wheel before the vehicle runs and an infrared image of the wheel while the vehicle runs as a wheel image of the vehicle S601. First tire pressure data, tightening torque data, axial displacement data, and radial displacement data of a wheel before the vehicle runs, and second tire pressure data, effective radius data, driving torque data, wheel speed data, operating sound data, and wheel hub vibration frequency data of the wheel while the vehicle runs are acquired as wheel attribute data of the vehicle. Vehicle speed data, steering angle data, yaw rate data, lateral acceleration data, longitudinal acceleration data, and braking force data of the vehicle while the vehicle is running are acquired as running attribute data of the vehicle.

And S602, tire pressure detection and tightness detection, namely determining a tire pressure risk coefficient of the vehicle before running according to the grounding image and the first tire pressure data, wherein the tire pressure risk coefficient can reflect the abnormal probability of the tire pressure of the vehicle before running, and then performing tire pressure detection according to the tire pressure risk coefficient, the infrared image, the second tire pressure data, the effective radius data and the hub vibration frequency data to obtain tire pressure detection information of the vehicle during running as target tire pressure detection information, wherein the target tire pressure detection information is used for indicating whether the tire pressure of the wheel is normal or not.

Meanwhile, according to the fastening torque data, the axial displacement data and the radial displacement data, a fastening risk coefficient of the vehicle before running is determined, the fastening risk coefficient can reflect the probability of insufficient fastening performance of the wheel of the vehicle before running, and then fastening detection processing is carried out according to the fastening risk coefficient, the driving torque data, the wheel speed data, the working sound data and the wheel hub vibration frequency data, fastening detection information of the vehicle during running is obtained and is used as target fastening detection information, and the target fastening detection information is used for indicating whether the mechanical structure of the wheel is fastened or not.

And S603, track detection, namely, if the target tire pressure detection information is used for indicating abnormal tire pressure of the wheels and/or the target fastening detection information is used for indicating that the mechanical structure of the wheels is not fastened, indicating that the vehicle has potential risk of loosening the wheels, firstly, inputting second tire pressure data, effective radius data, hub vibration frequency data, driving torque data, wheel speed data, working sound data and hub vibration frequency data of the wheels when the vehicle runs, and vehicle speed data, steering angle data, yaw rate data, transverse acceleration data, longitudinal acceleration data and braking force data of the vehicle when the vehicle runs into a pre-trained first track prediction model to obtain initial wheel movement track data of the vehicle, wherein the initial wheel movement track data is in a linear shape and can comprise coordinate positions of the wheels at a plurality of future moments under a vehicle body coordinate system. Then, a trajectory correction coefficient of the vehicle is determined for correcting the initial wheel movement trajectory data based on the infrared image of the wheel while the vehicle is running. And finally, correcting the initial wheel movement track data on the basis of the track correction coefficient to obtain the wheel movement track data.

S604, looseness early warning is carried out, wherein first, expected wheel movement track data of a vehicle and similarity data of the wheel movement track data are determined. And then, if the similarity data is smaller than or equal to a preset threshold value, determining the deviation detection information to be used for indicating that the wheel is deviated in a future time period, otherwise, determining the deviation detection information to be used for indicating that the wheel is not deviated in the future time period. And finally, if the deviation detection information is used for indicating the deviation of the vehicle in a future time period, carrying out wheel looseness early warning processing on the vehicle, otherwise, not carrying out looseness early warning processing.

Furthermore, referring to fig. 8, an embodiment of the present application further provides a wheel loosening warning device, which includes:

an acquiring module 701, configured to acquire a wheel image, wheel attribute data, and driving attribute data of a vehicle;

a first processing module 702, configured to obtain target tire pressure detection information and target fastening detection information of a vehicle according to a wheel image and the wheel attribute data, where the target tire pressure detection information is used to indicate whether the tire pressure of the wheel is normal, and the target fastening detection information is used to indicate whether the mechanical structure of the wheel is fastened;

A second processing module 703, configured to obtain wheel movement track data of the vehicle according to the wheel image, the wheel attribute data and the driving attribute data, when the target tire pressure detection information is used for indicating that the tire pressure of the wheel is abnormal and/or the target fastening detection information is used for indicating that the mechanical structure of the wheel is not fastened;

And the third processing module 704 is used for performing wheel looseness early warning processing on the vehicle based on the wheel movement track data.

The content in the method embodiment is applicable to the embodiment of the device, and the functions specifically realized by the embodiment of the device are the same as those of the method embodiment, and the obtained beneficial effects are the same as those of the method embodiment.

In addition, the embodiment of the application also provides a computer readable storage medium, wherein a program executable by a processor is stored, and the program executable by the processor is used for realizing the wheel looseness early warning method when being executed by the processor.

The content in the method embodiment is applicable to the medium embodiment, and functions specifically realized by the medium embodiment are the same as those of the method embodiment, and the obtained beneficial effects are the same as those of the method embodiment.

Finally, referring to fig. 9, an embodiment of the present application also provides a vehicle, including:

At least one processor 801;

At least one memory 802 for storing at least one program;

The at least one program, when executed by the at least one processor 801, causes the at least one processor 801 to implement the wheel looseness warning method described above.

The vehicle may be a private car, such as a sedan, a sport utility vehicle (Sport Utility Vehicle, SUV), a utility vehicle (MPV), a pick-up, or the like, or an operator vehicle, such as a minibus, a bus, a minivan, or a large trailer, or an oil vehicle, or a new energy vehicle such as a hybrid vehicle, a pure electric vehicle, or the like.

The memory 802 is used as a non-transitory network system for storing non-transitory software programs and non-transitory computer-executable programs. In addition, memory 802 may include high-speed random access memory, and may also include non-transitory memory, such as at least one magnetic disk storage device, flash memory device, or other non-transitory solid state storage device. In some implementations, the memory 802 may optionally include memory 802 located remotely from the processor 801, the remote memory 802 being connectable to the processor 801 through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.

The memory 802 may be implemented in the form of a read-only memory (ReadOnly Memory, ROM), a static storage device, a dynamic storage device, or a random access memory (Random Access Memory, RAM). The memory 802 may store an operating system and other application programs, and when the technical solutions provided in the embodiments of the present disclosure are implemented by software or firmware, relevant program codes are stored in the memory 802, and the processor 801 invokes a method for executing the embodiments of the present disclosure.

The above processor 801 may be implemented by a general purpose central processing unit (Central Processing Unit, CPU), a microprocessor, an Application SPECIFIC INTEGRATED Circuit (ASIC), or one or more integrated circuits, etc. for executing related programs, so as to implement the technical solutions provided by the embodiments of the present application.

In some embodiments, the vehicle may further include:

the input/output interface is used for realizing information input and output;

the communication interface is used for realizing communication interaction between the device and other devices, and can realize communication in a wired mode (such as USB, network cable and the like) or in a wireless mode (such as mobile network, WIFI, bluetooth and the like);

a bus that transfers information between the various components of the device (e.g., processor 801, memory 802, input/output interfaces, and communication interfaces);

Wherein the processor 801, the memory 802, the input/output interface, and the communication interface may be communicatively coupled to each other within the device via a bus.

The content in the method embodiment is applicable to the vehicle embodiment, and functions specifically realized by the vehicle embodiment are the same as those of the method embodiment, and the achieved beneficial effects are the same as those of the method embodiment.

In some alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may in fact be executed substantially concurrently or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flowcharts of the present application are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed, and in which sub-operations described as part of a larger operation are performed independently.

Furthermore, while the application is described in the context of functional modules, it should be appreciated that, unless otherwise indicated, one or more of the functions and/or features may be integrated in a single physical device and/or software module or may be implemented in separate physical devices or software modules. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary to an understanding of the present application. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be apparent to those skilled in the art from consideration of their attributes, functions and internal relationships. Accordingly, one of ordinary skill in the art can implement the application as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative and are not intended to be limiting upon the scope of the application, which is to be defined in the appended claims and their full scope of equivalents.

The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in the form of a software product stored in a storage medium, including several programs for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. The storage medium includes a U disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, an optical disk, or other various media capable of storing program codes.

Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable programs for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with a program execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the programs from the program execution system, apparatus, or device and execute the programs. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the program execution system, apparatus, or device.

More specific examples (a non-exhaustive list) of the computer-readable medium would include an electrical connection (an electronic device) having one or more wires, a portable computer diskette (a magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.

It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable program execution system. For example, if implemented in hardware, as in another embodiment, may be implemented using any one or combination of techniques known in the art, discrete logic circuits with logic gates for implementing logic functions on data signals, application specific integrated circuits with appropriate combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.

In the foregoing description of the present specification, reference has been made to the terms "one embodiment/example", "another embodiment/example", "certain embodiments/examples", and the like, means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.

Although embodiments of the present application have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made therein without departing from the spirit and scope of the application as defined by the appended claims and their equivalents.

While the preferred embodiment of the present application has been described in detail, the present application is not limited to the embodiments described above, and various equivalent modifications and substitutions can be made by those skilled in the art without departing from the spirit of the present application, and these equivalent modifications and substitutions are intended to be included in the scope of the present application as defined in the appended claims.

Claims

1. The wheel looseness early warning method is characterized by comprising the following steps of:

2. The method of claim 1, wherein the wheel image comprises a ground contact image of the wheel prior to the vehicle traveling and an infrared image of the wheel while the vehicle is traveling, wherein the wheel attribute data comprises first tire pressure data of the wheel prior to the vehicle traveling and second tire pressure data, effective radius data, and hub vibration frequency data of the wheel while the vehicle is traveling;

The obtaining the target tire pressure detection information and the target fastening detection information of the vehicle according to the wheel image and the wheel attribute data comprises the following steps:

determining a tire pressure risk coefficient of the vehicle before running according to the grounding image and the first tire pressure data;

And performing tire pressure detection processing according to the tire pressure risk coefficient, the infrared image, the second tire pressure data, the effective radius data and the hub vibration frequency data to obtain tire pressure detection information of the vehicle when the vehicle is running as the target tire pressure detection information.

3. The method of claim 1, wherein the wheel attribute data includes tightening torque data, axial displacement data, and radial displacement data of the wheel before the vehicle is running, and driving torque data, wheel speed data, operating sound data, and hub vibration frequency data of the wheel while the vehicle is running;

Determining a fastening risk coefficient of the vehicle before running according to the fastening torque data, the axial displacement data and the radial displacement data;

And performing fastening detection processing according to the fastening risk coefficient, the driving torque data, the wheel speed data, the working sound data and the wheel hub vibration frequency data to obtain fastening detection information of the vehicle during running as the target fastening detection information.

4. The method of claim 1, wherein the wheel image comprises an infrared image of the wheel while the vehicle is traveling, wherein the obtaining wheel movement trace data of the vehicle from the wheel image, the wheel attribute data, and the travel attribute data comprises:

Track prediction processing is carried out according to the driving attribute data and the wheel attribute data, so that initial wheel movement track data of the vehicle are obtained;

Determining a track correction coefficient of the vehicle according to the infrared image;

And correcting the initial wheel movement track data according to the track correction coefficient to obtain the wheel movement track data.

5. The method of claim 1, wherein the performing a wheel looseness warning process on the vehicle based on the wheel movement trajectory data comprises:

performing deviation detection processing according to the wheel movement track data to obtain deviation detection information of the vehicle, wherein the deviation detection information is used for indicating whether the wheel deviates in a future time period or not;

And carrying out wheel looseness early warning treatment on the vehicle according to the deviation detection information.

6. The method according to claim 5, wherein the performing the deviation detection process according to the wheel movement track data to obtain the deviation detection information of the vehicle includes:

Determining expected wheel movement trace data and similarity data of the wheel movement trace data of the vehicle;

And if the similarity data is smaller than or equal to a preset threshold value, determining the deviation detection information to be used for indicating that the wheel is deviated in a future time period, otherwise, determining the deviation detection information to be used for indicating that the wheel is not deviated in the future time period.

7. The method of claim 5, wherein the performing a wheel looseness warning process on the vehicle based on the deviation detection information comprises:

If the deviation detection information is used for indicating the vehicle to deviate in a future time period, performing wheel looseness early warning processing on the vehicle;

Or if the deviation detection information is used for indicating that the vehicle does not deviate in a future time period, loosening early warning processing is not carried out.

8. The utility model provides a wheel looseness early warning device which characterized in that includes:

9. A computer-readable storage medium in which a processor-executable program is stored, characterized in that the processor-executable program is for implementing the wheel looseness warning method of any of claims 1-7 when executed by a processor.

10. A vehicle, characterized by comprising:

at least one processor;

At least one memory for storing at least one program;

The at least one program, when executed by the at least one processor, causes the at least one processor to implement the wheel looseness warning method of any of claims 1-7.