CN120534514A - Aircraft fault prediction and health management system, method, storage medium and aircraft - Google Patents
Aircraft fault prediction and health management system, method, storage medium and aircraftInfo
- Publication number
- CN120534514A CN120534514A CN202510891339.3A CN202510891339A CN120534514A CN 120534514 A CN120534514 A CN 120534514A CN 202510891339 A CN202510891339 A CN 202510891339A CN 120534514 A CN120534514 A CN 120534514A
- Authority
- CN
- China
- Prior art keywords
- model
- target
- aircraft
- analysis
- unit
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D45/00—Aircraft indicators or protectors not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D47/00—Equipment not otherwise provided for
- B64D47/02—Arrangements or adaptations of signal or lighting devices
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B64—AIRCRAFT; AVIATION; COSMONAUTICS
- B64D—EQUIPMENT FOR FITTING IN OR TO AIRCRAFT; FLIGHT SUITS; PARACHUTES; ARRANGEMENT OR MOUNTING OF POWER PLANTS OR PROPULSION TRANSMISSIONS IN AIRCRAFT
- B64D45/00—Aircraft indicators or protectors not otherwise provided for
- B64D2045/0085—Devices for aircraft health monitoring, e.g. monitoring flutter or vibration
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Alarm Systems (AREA)
Abstract
本发明涉及一种飞机故障预测与健康管理系统、方法、存储介质和飞机，通过飞行参数获取模块获取飞行参数，通过告警监控模块来确定飞行参数是否超过告警事件的告警阈值，在超过告警阈值时生成告警信息以提示用户，同时，利用分析模块的故障诊断单元、健康评估单元和可视化分析单元调用算法模型来实现对飞机的故障诊断、健康评估和飞行参数的可视化分析，可以更加全面地监控飞机的健康状态，提高飞机运行的安全性、可靠性和运营效益，减少因故障导致的延误和停飞，降低运营成本。
The present invention relates to an aircraft fault prediction and health management system, method, storage medium, and aircraft. The system acquires flight parameters through a flight parameter acquisition module, determines whether the flight parameters exceed an alarm threshold of an alarm event through an alarm monitoring module, and generates an alarm message to prompt a user when the alarm threshold is exceeded. At the same time, the fault diagnosis unit, health assessment unit, and visualization analysis unit of the analysis module are used to call an algorithm model to implement fault diagnosis, health assessment, and visualization analysis of the aircraft's flight parameters. This system can more comprehensively monitor the aircraft's health status, improve the safety, reliability, and operational efficiency of aircraft operations, reduce delays and groundings caused by faults, and lower operating costs.
Description
Technical Field
The invention relates to the field of aircrafts, in particular to an aircraft fault prediction and health management system, an aircraft fault prediction and health management method, a storage medium and an aircraft.
Background
The aircraft health monitoring system is used for monitoring the running state of the aircraft in real time, so that an airline company can be helped to find faults of the aircraft in time and maintain the faults, and the flight safety of the aircraft is improved.
The traditional aircraft health monitoring system is used for determining whether the aircraft has faults or not by collecting the flight parameters of the aircraft during flight and comparing the flight parameters with preset flight parameter thresholds, however, the mode is easy to cause misjudgment of the faults of the aircraft, and the flight safety is affected.
Disclosure of Invention
The embodiment of the application provides an aircraft fault prediction and health management system, an aircraft fault prediction and health management method, a storage medium and an aircraft, which can monitor the health state of the aircraft more comprehensively and improve the running safety of the aircraft.
In a first aspect, an embodiment of the present application provides an aircraft fault prediction and health management system, including a flight parameter acquisition module, an alarm monitoring module, a model storage module, and an analysis module;
The flight parameter acquisition module is used for acquiring flight parameters;
the alarm monitoring module is used for determining whether the flight parameter meets the triggering condition of the alarm event or not based on the triggering condition of the preset alarm event, and generating alarm information when the triggering condition is met;
the model storage module stores at least one diagnosis model, at least one health evaluation model and at least one analysis model, wherein one diagnosis model corresponds to one diagnosis item, one health evaluation model corresponds to one health evaluation item, and one analysis model corresponds to one analysis item;
the analysis module comprises a fault diagnosis unit, a health evaluation unit and a visual analysis unit;
The fault diagnosis unit is used for acquiring a target diagnosis model corresponding to a target diagnosis item from the model storage module according to the target diagnosis item in the diagnosis task when the diagnosis task is received, and acquiring a diagnosis result of the target diagnosis item based on the target diagnosis model and the flight parameter;
The health evaluation unit is used for acquiring a target health evaluation model corresponding to a target health evaluation item from the model storage module according to the target health evaluation item in the health evaluation task when the health evaluation task is received, and acquiring an evaluation result of the target health evaluation item based on the target health evaluation model and the flight parameter;
And the visual analysis unit is used for acquiring a target analysis model corresponding to the target analysis item from the model storage module according to the target analysis item of the analysis task when the analysis task is received, and performing visual analysis on the flight parameter based on the target analysis model to generate a visual interface.
In a second aspect, an embodiment of the present application provides a method for predicting an aircraft failure and managing health, including:
acquiring flight parameters;
Based on the preset triggering conditions of the alarm event, determining whether the flight parameters meet the triggering conditions of the alarm event, and generating alarm information when the triggering conditions are met;
When a diagnosis task is received, acquiring a target diagnosis model corresponding to the target diagnosis project from a model storage module according to the target diagnosis project in the diagnosis task, and acquiring a diagnosis result of the target diagnosis project based on the target diagnosis model and the flight parameter;
When a health assessment task is received, acquiring a target health assessment model corresponding to a target health assessment item from the model storage module according to the target health assessment item in the health assessment task, and acquiring an assessment result of the target health assessment item based on the target health assessment model and the flight parameter;
when an analysis task is received, a target analysis model corresponding to the target analysis project is obtained from the model storage module according to the target analysis project of the analysis task, and visual analysis is performed on the flight parameters based on the target analysis model to generate a visual interface.
In a third aspect, embodiments of the present application provide a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the aircraft fault prediction and health management method as described in any one of the preceding claims.
In a fourth aspect, embodiments of the present application provide a computer device comprising a memory, a processor, and a computer program stored in the memory and executable by the processor;
The steps of the aircraft fault prediction and health management method according to any one of the preceding claims are implemented when the processor executes the computer program.
In a fifth aspect, embodiments of the present application provide an aircraft comprising an aircraft fault prediction and health management system as defined in any one of the preceding claims.
In the embodiment of the application, the flight parameters are acquired through the flight parameter acquisition module, whether the flight parameters exceed the alarm threshold value of the alarm event is determined through the alarm monitoring module, the alarm information is generated to prompt a user when the flight parameters exceed the alarm threshold value, meanwhile, the fault diagnosis unit, the health assessment unit and the visual analysis unit of the analysis module are utilized to call the algorithm model to realize the fault diagnosis, the health assessment and the visual analysis of the flight parameters of the aircraft, the health state of the aircraft can be monitored more comprehensively, the safety, the reliability and the operation benefit of the operation of the aircraft are improved, the delay and the stop of the flight caused by the fault are reduced, and the operation cost is reduced.
For a better understanding and implementation, the present invention is described in detail below with reference to the drawings.
Drawings
FIG. 1 is a schematic diagram of an aircraft failure prediction and health management system in accordance with one embodiment of the present invention;
FIG. 2 is a schematic diagram of a display interface of a terminal according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a visual interface in one embodiment of the invention;
FIG. 4 is a schematic diagram of a flight parameter acquisition module according to an embodiment of the present invention;
FIG. 5 is a diagram of a decoding library determination interface according to an embodiment of the present invention;
FIG. 6 is a schematic diagram of a decoding library according to an embodiment of the present invention;
FIG. 7 is a schematic diagram of an alarm monitoring module according to an embodiment of the present invention;
FIG. 8 is a schematic diagram of a model memory module according to one embodiment of the invention;
FIG. 9 is a graph of loss in one embodiment of the invention;
FIG. 10 is a graph comparing predicted and actual values in one embodiment of the invention;
FIG. 11 is a schematic diagram of an image recognition model in one embodiment of the invention;
FIG. 12 is a schematic diagram of a computer device in one embodiment of the invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the following detailed description of the embodiments of the present application will be given with reference to the accompanying drawings.
It should be understood that the described embodiments are merely some, but not all embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the application, are intended to be within the scope of the embodiments of the present application.
The terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of embodiments of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with certain aspects of the application as detailed in the accompanying claims. In the description of the present application, it should be understood that the terms "first," "second," "third," and the like are used merely to distinguish between similar objects and are not necessarily used to describe a particular order or sequence, nor should they be construed to indicate or imply relative importance. The specific meaning of the above terms in the present application can be understood by those of ordinary skill in the art according to the specific circumstances.
Furthermore, in the description of the present application, unless otherwise indicated, "a number" means two or more. "and/or" describes the correspondence of the associated objects, and indicates that there may be three relationships, for example, A and/or B, and that there may be three cases where A exists alone, while A and B exist together, and B exists alone. The character "/" generally indicates that the context-dependent object is an "or" relationship. The aircraft fault prediction and health management system of the embodiment of the application can be realized wholly or partly by software, hardware and combination thereof, and when the aircraft fault prediction and health management system is realized by software, the aircraft fault prediction and health management system can be installed in hardware equipment such as a singlechip, a processor and the like in the form of a computer program.
Referring to fig. 1, an embodiment of the present application provides an aircraft fault prediction and health management system, which includes a flight data decoding module 110, an alarm monitoring module 120, a model storage module and an analysis module 140;
The flight data decoding module 110 is configured to obtain flight data and decode the flight data to obtain flight parameters;
The flight parameters may include parameters for determining the state of motion of the aircraft, such as attitude, track, speed, acceleration, longitude and latitude, heading, etc., as well as parameters of external forces acting on the aircraft, such as drag, lift, thrust, etc., and parameters of the state of the various systems of the aircraft, such as engines, landing gear, flight control systems, etc.
The alarm monitoring module 120 is configured to determine whether the flight parameter meets a triggering condition of an alarm event based on a preset triggering condition of the alarm event, and generate alarm information when the triggering condition is met;
The triggering condition is used for triggering an alarm event, so that alarm information is generated to prompt a user that the aircraft is abnormal. The trigger conditions may include a number of triggers, a trigger interval, a threshold, and the like.
Optionally, the determination that the flight parameter meets the triggering condition of the alarm event may be that the flight parameter exceeds a preset flight parameter threshold range. Or the number of times that the flight parameter exceeds the preset flight parameter threshold range in the target time is greater than the target number of times, and the like.
According to different alarm requirements, alarm events with different alarm levels can be set, and for the alarm events with different alarm levels, alarm modes corresponding to the different alarm levels can be set, wherein the higher the alarm level is, the higher the trigger condition is, and the more alarm modes are. For example, for the alarm event with a lower alarm level, alarm information is only displayed on the local terminal device, for the alarm event with a higher alarm level, not only alarm information is displayed on the local terminal device, but also alarm information can be sent to a set terminal (such as a terminal where a manager is located) through a network or other wireless communication technology, so that a serious alarm event can be timely processed.
In another embodiment, the alarm event may also be a combination of multiple alarm events, for example, an alarm event that is a combination of two or more alarm events, where the combined alarm event has a higher alarm level.
The model storage module 130 stores at least one diagnosis model, at least one health evaluation model and at least one analysis model, wherein one diagnosis model corresponds to one diagnosis item, one health evaluation model corresponds to one health evaluation item, and one analysis model corresponds to one analysis item;
The diagnostic models are used to diagnose a diagnostic item of the aircraft to determine whether the diagnostic item has a fault, each diagnostic model corresponds to a diagnostic item of the aircraft, or the diagnostic models may correspond to a model and a diagnostic item of the aircraft.
For example, the diagnostic model may include a leak detection model for detecting whether a leak has occurred, a grease pressure trend monitoring model for predicting a grease pressure trend, a landing gear detection model for detecting whether the landing gear is being properly lowered, and so on.
Or in an alternative embodiment, the model storage module 130 stores diagnostic models corresponding to models and diagnostic items, such as a 73N-landing gear detection model for detecting whether landing gear of a boeing 73N aircraft is properly lowered, etc.
The health assessment model is used for assessing the health condition of the aircraft, and the health assessment model may include a whole machine health assessment model for assessing the health condition of the whole machine of the aircraft, a system health assessment model (such as an air conditioning system health assessment model) for assessing the health condition of a certain system of the aircraft, a component health assessment model (such as an engine life health assessment model) for assessing the health condition of a certain component of the aircraft, and so on.
The visual analysis model can comprise a correlation analysis model, a QAR visual analysis model, a STREAMLIT analysis model and the like, wherein the correlation analysis model can be used for realizing quantitative correlation analysis of parameters such as valve, EGT, FF, delta N1, delta N2 and the like of an airplane.
The analysis module 140 includes a fault diagnosis unit 141, a health assessment unit 142, and a visual analysis unit 143;
The fault diagnosis unit 141 is configured to, when receiving a diagnosis task, obtain, from the model storage module 130, a target diagnosis model corresponding to a target diagnosis item according to the target diagnosis item in the diagnosis task, and obtain a diagnosis result of the target diagnosis item based on the target diagnosis model and the flight parameter;
The health evaluation unit 142 is configured to, when receiving a health evaluation task, obtain, from the model storage module 130, a target health evaluation model corresponding to a target health evaluation item according to the target health evaluation item in the health evaluation task, and obtain an evaluation result of the target health evaluation item based on the target health evaluation model and the flight parameter;
the visual analysis unit 143 is configured to, when receiving an analysis task, obtain, from the model storage module 130, a target analysis model corresponding to the target analysis item according to a target analysis item of the analysis task, perform visual analysis on the flight parameter based on the target analysis model, and generate a visual interface.
Diagnostic tasks, health assessment tasks, analysis tasks may be tasks created by the user at the terminal.
Optionally, as shown in FIG. 2, a schematic diagram of a display interface 200 of the terminal in one embodiment includes a fault diagnosis control 210, a health assessment control 220, and a visual analysis control 230. The user may generate a diagnostic task, a health assessment task, an analysis task by triggering the fault diagnosis control 210, the health assessment control 220, or the visual analysis control 230.
In the embodiment of the present application, after the fault diagnosis control 210 is triggered, a plurality of diagnosis item controls (such as 73M-landing gear down detection and 787-hydraulic oil mass slope calculation) are displayed on the display interface, when a user selects one of the diagnosis item controls, a diagnosis item corresponding to the diagnosis item control is used as a target diagnosis item, and a corresponding target diagnosis model is acquired from the model storage module 130 to perform diagnosis of the target diagnosis item.
As shown in fig. 3, the visual interface in one embodiment includes a parameter selection area and a display area, where a user may select a flight parameter to be displayed in the parameter selection area, and display a graph of the flight parameter in the display area, so as to realize the visualization of the flight parameter. In the embodiment of the application, the flight parameters are acquired through the flight parameter acquisition module, whether the flight parameters exceed the alarm threshold value of the alarm event is determined through the alarm monitoring module, the alarm information is generated to prompt a user when the flight parameters exceed the alarm threshold value, meanwhile, the fault diagnosis unit, the health assessment unit and the visual analysis unit of the analysis module are utilized to call the algorithm model to realize the fault diagnosis, the health assessment and the visual analysis of the flight parameters of the aircraft, the health state of the aircraft can be monitored more comprehensively, the safety, the reliability and the operation benefit of the operation of the aircraft are improved, the delay and the stop of the flight caused by faults are reduced, and the operation cost is reduced.
As shown in fig. 4, in one embodiment, the flight parameter acquisition module 110 may include:
an aircraft data acquisition unit 111 for acquiring flight data from the data recording device of the aircraft:
A decoding library determining unit 112, configured to receive aircraft information, and determine a decoding library corresponding to the aircraft information;
And the decoding unit 113 is configured to determine a target field to be decoded, and decode the target field of the flight data by using the decoding library to obtain a flight parameter.
The flight data may be data stored by a flight recorder of the aircraft, for example, QAR data or DAR data. The data recording device may be a fast access recorder (QAR) of an aircraft, a Digital ACMS Recorder (DAR), a Flight Data Recorder (FDR), etc.
In the embodiment of the application, the flight data are QAR data or DAR data after the aircraft is returned. The flight data records the flight data of the aircraft in the whole sailing process from take-off to landing.
The QAR (Quick access recorder ) data can be used to record flight parameters of the aircraft during the whole course of sailing from engine start, take-off, cruising, landing, including longitude and latitude, altitude, wind speed, wind direction angle of attack, fuel consumption, temperature, air pressure, etc.
DAR (DIGITAL ACMS Recorder, digital aircraft state monitoring Recorder) data can be used to record and process various data related to aircraft state, and the aircraft parameters of the DAR data record can be customized according to user requirements.
The flight recorder may record and store flight data in accordance with preset specifications and formats. For example, data is stored in frames (frames) according to the specifications of RINC573, ARINC717, ARINC747, etc., each Frame of data records 4 seconds of flight data, and each Frame of data includes a plurality of subframes (subframes), each Subframe including a number of Word slots (words), each Word slot recording a specific flight parameter. The aircraft information may include information such as the model number of the aircraft.
The correspondence between the aircraft information and the decoding library may be pre-stored in the decoding library determining unit 112, as shown in fig. 5, which is a schematic diagram of a decoding library determining interface in an embodiment, where it may be determined that the decoding library corresponding to the aircraft information of B737-8 is 1024.
As shown in fig. 6, the decoding library is a schematic diagram of a decoding library in an embodiment, where the decoding library includes a plurality of flight parameters, and a user selects a flight parameter to be decoded as a target field, and decodes the target field in the flight data by using the decoding library, so as to convert the flight data into the flight parameter with an engineering value having an actual physical meaning, for example, convert binary data of airspeed into an actual airspeed value.
In order to improve the system security, before the user obtains the flight parameters through the flight parameter obtaining module 110, the user needs to send login information to the administrator, and after the administrator authorizes the login information, the user obtains the flight parameters according to the authorization code sent by the administrator.
In other embodiments, the flight data may be all types of data, including ACARS messages, job card tag data, SAP data, and the like;
The flight parameter obtaining module 110 may include a message parsing unit, where the message parsing unit stores parsing rules corresponding to all types of messages, such as ACARS messages, work card tag data, SAP data, and the like, of the engine;
specifically, all engine ACARS messages can be analyzed based on ACARS message analysis specifications, analysis rules can be analyzed based on specific arrangements of all work cards for work card tag data, and analysis can be performed based on specific part numbers, serial numbers, disassembly time, installation time and other arrangements for SAP data.
The message analysis unit is used for calling corresponding analysis rules to analyze the flight data according to the message type of the flight data, and flight parameters obtained after analysis can be arranged according to a set format, so that the use of other modules of the aircraft fault prediction and health management system is facilitated.
In the embodiment of the application, the decoding library corresponding to the airplane information is determined by receiving the airplane information, the target field to be decoded is selected, the target field of the flight data is decoded by using the decoding library, the flight parameters are obtained, the precise decoding of the flight data is realized, and the decoding efficiency is improved.
As shown in fig. 7, in one embodiment, the alarm monitoring module 120 further includes:
an event creating unit 121, configured to receive creation information of an alarm event, and create the alarm event according to the creation information, where the creation information includes a flight parameter and a trigger condition corresponding to the alarm event;
The creation information may include information such as the name, description, number, flight parameters to be measured, and trigger conditions of the alert event.
And the alarm unit 122 is configured to determine a target alarm event requiring to send alarm information and terminal information corresponding to the target alarm event, and send the alarm information to a corresponding terminal according to the terminal information when the trigger condition of the target alarm event is satisfied.
The target alarm event may be an alarm event with a higher alarm level, and for an alarm event with a lower alarm level, no alarm information may be sent, thereby saving resources of the device.
The terminal information is used for determining a terminal which needs to send the alarm information when the target alarm event occurs, for example, a terminal where a person related to the target alarm event is located. The terminal may include a mobile phone, a tablet computer, etc.
The alarm information can be sent to the terminal of the corresponding user in a short message or mail mode. In the embodiment of the application, the alarm event is created by the event creation unit, and the target alarm event and the terminal which need to send the alarm information are determined by the alarm unit, so that the corresponding user is timely notified, and the processing efficiency of the alarm event is improved.
As shown in fig. 8, in one embodiment, the model storage module 130 includes an algorithm storage unit 131, a model configuration unit 132, a model training unit 133, a visualization unit 134, and a publishing unit 135;
the algorithm storage unit 131 stores a plurality of algorithms;
specifically, the algorithm storage unit 131 may store a preprocessing algorithm, a feature extraction algorithm, a statistical analysis algorithm, a clustering algorithm, a classification algorithm, a machine learning algorithm, a deep learning algorithm, an image recognition algorithm, and the like.
The model configuration unit 132 is used for calling the algorithm stored in the algorithm storage unit, and constructing and configuring an algorithm model;
The model configuration unit 132 may be used to construct an algorithm model, and configure the input, output, and algorithm used for the algorithm model.
The model training unit 133 is configured to load test data, and train and verify accuracy of the algorithm model based on the test data;
The test data may be historical usage data or simulation data related to the function to be implemented by the algorithm model.
A visualization unit 134, configured to invoke a third party visualization engine to visualize the accuracy verification process and the accuracy verification result;
The third party visual engine can be an existing visual engine, and when the third party visual engine is called, the call of the third party visual engine can be realized by accessing a program interface corresponding to the third party visual engine.
The publishing unit 135 is configured to publish the model as a microservice for the analysis module to make a call to the model.
For example, in constructing the engine remaining life prediction model for predicting the remaining life of the engine, the model configuration unit 132 invokes the feature extraction algorithm and the correlation analysis algorithm stored in the algorithm storage unit 131, extracts features from the engine simulation data using the feature extraction algorithm, and determines features related to the engine health therein using the correlation analysis algorithm. Wherein the engine simulation data includes all simulation data of the engine from the start of operation to the occurrence of a fault. The model configuration unit 132 invokes the LSTM algorithm stored by the algorithm storage unit 131, and constructs a remaining life prediction model of the engine based on the LSTM algorithm.
The model training unit 133 uses the engine simulation data as a training set, uses externally collected data of the actual remaining service life of the engine as a test set, uses the training set and the test set to realize training and accuracy verification of the remaining service life prediction model of the engine, and uses common accuracy evaluation indexes such as a Mean Square Error (MSE) loss function, RMSE, R 2 and the like to realize evaluation of the accuracy of the remaining service life prediction model of the engine.
The visualization unit 134 may generate a loss graph (as shown in fig. 8), a predicted value, and a true value versus graph (as shown in fig. 9) to enable visualization of an accuracy assessment of the engine remaining life prediction model.
The embodiment of the application can realize the construction and training of models such as a machine learning model, a deep learning model, an image recognition model and the like, wherein the machine learning model is a model constructed based on a machine learning algorithm, such as a decision tree model, a random forest model, a K-means clustering model and the like. The deep learning model is a model constructed based on a deep learning algorithm, such as a convolutional neural network model, a cyclic neural network model and the like. The image recognition model may be used to implement recognition of objects in an image, as shown in fig. 11, where the image recognition model recognizes that the object in the image is an aircraft.
In the embodiment of the application, the configuration, training and release of the model are realized by utilizing the model configuration unit, the model training unit and the release unit, the requirements of constructing different algorithm models by users are met, the third party visualization engine is called by utilizing the visualization unit, the accuracy verification process and the accuracy verification result are visualized, and the accuracy verification process of the algorithm model is displayed so as to facilitate the users to adjust the algorithm model.
In an alternative embodiment, the analysis module 140 may further include:
the data updating detection unit is used for detecting whether the flight data is updated or not, creating a preset analysis task when the flight data is detected to be updated, and calling a module corresponding to the analysis task to execute the analysis task.
The analysis task can be a diagnosis task, a health assessment task and/or an analysis task, and the analysis task is automatically executed to perform abnormal analysis of the flight data when the flight data is updated each time, so that problems existing in the aircraft can be found in time, and the accuracy of monitoring the aircraft is improved.
In one embodiment, the aircraft fault prediction and health management system further comprises a troubleshooting module;
The fault elimination module is used for receiving fault information, and acquiring files related to the fault information from a preset database for display.
The troubleshooting module can store a plurality of keywords, file identifications and corresponding relations between the keywords and the file identifications, and can acquire the keywords in the fault information when the fault information is received, determine relevant file identifications based on the corresponding relations between the keywords and the file identifications, and acquire files corresponding to the file identifications from the database.
The documents related to the fault information may include documents of troubleshooting manuals, repair, part drawings, and the like.
When an aircraft fails, maintenance personnel need to read a large amount of documents and data to remove the fault of the aircraft. In the embodiment of the application, the troubleshooting module is utilized to acquire and display the file related to the fault information from the preset database, thereby facilitating the troubleshooting of users and improving the troubleshooting efficiency.
In one embodiment, the aircraft fault prediction and health management system further comprises a permission distribution module, wherein the permission distribution module is used for distributing roles and the permission of the assigned roles to users based on a static responsibility separation rule and a dynamic responsibility separation rule, and the permission of different roles is different.
A static responsibility separation rule (SSD) refers to a responsibility separation rule that is determined at the role assignment stage. Under this rule, certain roles may not be owned by the same user at the same time, as the tasks performed by these roles may present potential collision of interests or security risks.
Dynamic responsibility separation rules (DSD) refer to responsibility separation rules that are dynamically executed during a user session. In dynamic responsibility separation rules, even if a user is assigned multiple roles, these roles may be restricted from being activated simultaneously due to the current operating context. For example, in a particular session, when the user has both "system administrator" and "general user" roles, the user is only allowed to activate one of the roles, thereby reducing security risks.
The permission distribution module can realize access control of the aircraft fault prediction and health management system based on RBAC (Role-Based Access Control based access control) model, and by distributing the permission to the roles, the complexity of permission management can be reduced and the maintainability, expandability and safety of the system can be improved relative to the permission distribution to users.
Optionally, the permission assignment module may be further configured to add a role, delete a role, query a role, modify a permission of a role, modify an association relationship between a role and a user.
The permission distribution module can distribute roles according to departments where the users are and positions in the departments when the roles are distributed to the users.
The embodiment of the application also provides an aircraft fault prediction and health management method, which comprises the following steps:
acquiring flight parameters;
Based on the preset triggering conditions of the alarm event, determining whether the flight parameters meet the triggering conditions of the alarm event, and generating alarm information when the triggering conditions are met;
When a diagnosis task is received, acquiring a target diagnosis model corresponding to the target diagnosis project from a model storage module according to the target diagnosis project in the diagnosis task, and acquiring a diagnosis result of the target diagnosis project based on the target diagnosis model and the flight parameter;
When a health assessment task is received, acquiring a target health assessment model corresponding to a target health assessment item from the model storage module according to the target health assessment item in the health assessment task, and acquiring an assessment result of the target health assessment item based on the target health assessment model and the flight parameter;
when an analysis task is received, a target analysis model corresponding to the target analysis project is obtained from the model storage module according to the target analysis project of the analysis task, and visual analysis is performed on the flight parameters based on the target analysis model to generate a visual interface.
In one embodiment, obtaining the flight parameters includes:
acquiring flight data from a data recording device of the aircraft:
receiving aircraft information and determining a decoding library corresponding to the aircraft information;
And determining a target field to be decoded, and decoding the target field of the flight data by using the decoding library to obtain flight parameters.
In one embodiment, the algorithm storage unit stores a plurality of algorithms;
invoking an algorithm stored in the algorithm storage unit, and constructing and configuring an algorithm model;
Loading test data, and training and verifying the accuracy of the algorithm model based on the test data;
invoking a third party visualization engine to visualize the accuracy verification process and the accuracy verification result;
the model is published as a microservice for the analysis module to invoke.
In one embodiment, further comprising:
receiving creation information of an alarm event, and creating the alarm event according to the creation information, wherein the creation information comprises flight parameters and triggering conditions corresponding to the alarm event;
Determining a target alarm event needing to send alarm information and terminal information corresponding to the target alarm event, and sending the alarm information to a corresponding terminal according to the terminal information when the triggering condition of the target alarm event is met.
In one embodiment, further comprising:
and receiving fault information, and acquiring and displaying files related to the fault information from a preset database.
In one embodiment, further comprising:
based on the static responsibility separation rule and the dynamic responsibility separation rule, the roles and the authority of the roles are allocated to the users, wherein the authorities of different roles are different.
It should be noted that, the method for predicting and managing an aircraft fault provided in the foregoing embodiment and the system for predicting and managing an aircraft fault in the foregoing embodiment belong to the same concept, and detailed implementation processes of the method are shown in the foregoing embodiment, which is not repeated herein.
The embodiment of the application also provides a computer readable storage medium, on which a computer program is stored, which when being executed by a processor, implements the steps of the aircraft fault prediction and health management method as described in any one of the above.
Embodiments of the application may take the form of a computer program product embodied on one or more storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) having program code embodied therein. Computer-readable storage media include both non-transitory and non-transitory, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of storage media for a computer include, but are not limited to, phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), electrically Erasable Programmable Read Only Memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices, or any other non-transmission medium which can be used to store information that can be accessed by a computing device.
As shown in fig. 12, an embodiment of the present application further provides a computer apparatus 300 including a memory 310, a processor 320, and a computer program stored in the memory 310 and executable by the processor 320;
the processor 320, when executing the computer program, implements the steps of the aircraft fault prediction and health management method as described in any one of the preceding claims.
The Memory 310 includes Read-Only Memory (ROM), programmable Read-Only Memory (PROM), erasable programmable Read-Only Memory (EPROM), one-time programmable Read-Only Memory (One-timeProgrammable Read-Only Memory, OTPROM), electrically erasable programmable Read-Only Memory (EEPROM), compact disc Read-Only Memory (CD-ROM) or other optical disk Memory, magnetic disk Memory, tape Memory, or any other medium from which a computer can be used to carry or store data.
The processor 320 is a Control Unit (Control Unit) of the computer device 300, connects the respective components of the entire computer device 300 using various interfaces and lines, and performs various functions of the computer device 300 and processes data by running or executing programs or modules stored in the memory 310, and calling data stored in the memory 310. For example, the processor 320 may implement all or part of the steps of the method for predicting an aircraft failure and managing health in an embodiment of the present application, or may implement all or part of the functions of the system for predicting an aircraft failure and managing health when executing a computer program stored in the memory 310. The processor 320 may be formed by an integrated circuit, for example, a single packaged integrated circuit, or may be formed by a plurality of integrated circuits packaged with the same function or different functions, including one or more central processing units (CentralProcessing unit, CPU), a microprocessor, a digital processing chip, a graphics processor, a combination of various control chips, and the like.
The embodiment of the application also provides an aircraft, which comprises the aircraft fault prediction and health management system.
It should also be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises an element.
The foregoing is merely exemplary of the present application and is not intended to limit the present application. Various modifications and variations of the present application will be apparent to those skilled in the art. Any modification, equivalent replacement, improvement, etc. which come within the spirit and principles of the application are to be included in the scope of the claims of the present application.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510891339.3A CN120534514A (en) | 2025-06-30 | 2025-06-30 | Aircraft fault prediction and health management system, method, storage medium and aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202510891339.3A CN120534514A (en) | 2025-06-30 | 2025-06-30 | Aircraft fault prediction and health management system, method, storage medium and aircraft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN120534514A true CN120534514A (en) | 2025-08-26 |
Family
ID=96789607
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202510891339.3A Pending CN120534514A (en) | 2025-06-30 | 2025-06-30 | Aircraft fault prediction and health management system, method, storage medium and aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN120534514A (en) |
-
2025
- 2025-06-30 CN CN202510891339.3A patent/CN120534514A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10814883B1 (en) | Prognostics for improved maintenance of vehicles | |
| EP3486739B1 (en) | Real time streaming analytics for flight data processing | |
| Puranik et al. | Anomaly detection in general-aviation operations using energy metrics and flight-data records | |
| EP3413246A1 (en) | Reporting and prioritizing faults for aircraft downtime reduction | |
| RU2573735C2 (en) | Method and system for analysis of flight data recorded during aircraft flight | |
| EP2329459B1 (en) | Method and apparatus for obtaining vehicle data | |
| EP3336636B1 (en) | Machine fault modelling | |
| National Academies of Sciences et al. | In-time Aviation Safety Management: Challenges and Research for an Evolving Aviation System | |
| US11893907B2 (en) | Systems and methods for evidence-based training of aircraft operators | |
| US11068858B2 (en) | System for handling a fault of an aircraft and a method and computer equipment for achieving the same | |
| Wang et al. | Reliability assessment of autonomous vehicles based on the safety control structure | |
| Puranik et al. | Identification of instantaneous anomalies in general aviation operations using energy metrics | |
| JP2023536677A (en) | Vehicle level failure prediction for improved maintenance of vehicles | |
| US20230061096A1 (en) | Component record processing for aircraft maintenance | |
| JP2018185799A (en) | Data-driven unsupervised algorithm for analyzing sensor data and detecting abnormal valve behavior | |
| Keller et al. | An architecture to implement integrated vehicle health management systems | |
| Guo et al. | Flight safety assessment based on a modified human reliability quantification method | |
| US10730642B2 (en) | Operation and maintenance of avionic systems | |
| GB2529637A (en) | System for building and deploying inference model | |
| WO2021173356A1 (en) | Prognostics for improved maintenance of vehicles | |
| US20190377906A1 (en) | Aeronautical cybersecurity | |
| CN120534514A (en) | Aircraft fault prediction and health management system, method, storage medium and aircraft | |
| Chronopoulos et al. | Is smartness risky? A framework to evaluate smartness in cyber-physical systems | |
| Walker | Next generation prognostics and health management for unmanned aircraft | |
| Ortiz et al. | Multi source data integration for aircraft health management |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |