CN119203007A - An emergency landing method based on abnormal battery voltage of eVTOL aircraft - Google Patents
An emergency landing method based on abnormal battery voltage of eVTOL aircraft Download PDFInfo
- Publication number
- CN119203007A CN119203007A CN202411699579.5A CN202411699579A CN119203007A CN 119203007 A CN119203007 A CN 119203007A CN 202411699579 A CN202411699579 A CN 202411699579A CN 119203007 A CN119203007 A CN 119203007A
- Authority
- CN
- China
- Prior art keywords
- voltage
- aircraft
- battery voltage
- evtol
- time
- 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
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/2433—Single-class perspective, e.g. one-against-all classification; Novelty detection; Outlier detection
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
- G06N3/0442—Recurrent networks, e.g. Hopfield networks characterised by memory or gating, e.g. long short-term memory [LSTM] or gated recurrent units [GRU]
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- General Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Health & Medical Sciences (AREA)
- Secondary Cells (AREA)
Abstract
一种基于eVTOL飞行器电池电压异常的紧急迫降方法，属于eVTOL飞行器系统检测技术领域。为保障eVTOL飞行器的飞行安全，本发明包括采集同一时刻的eVTOL飞行器电池电压和eVTOL飞行器电池电压的影响因素的数据，构建飞行器电池电压数据预测数据集；基于改进的LSTM神经网络构建eVTOL飞行器电池电压数据预测模型；对预测得到的电压进行电压异常情况识别，提取电压异常情况的电压数据；构建电压异常情况分类模型，对电压异常情况的电压数据进行电压异常情况分类；基于不同类别的电压异常情况，构建eVTOL飞行器紧急迫降点选择方法。本发明极大提高了飞行安全性和应急响应能力。
An emergency landing method based on abnormal battery voltage of an eVTOL aircraft belongs to the technical field of eVTOL aircraft system detection. In order to ensure the flight safety of the eVTOL aircraft, the present invention includes collecting data on the battery voltage of the eVTOL aircraft and the factors affecting the battery voltage of the eVTOL aircraft at the same time, and constructing an aircraft battery voltage data prediction data set; constructing an eVTOL aircraft battery voltage data prediction model based on an improved LSTM neural network; identifying voltage anomalies on the predicted voltage, and extracting voltage data of the voltage anomalies; constructing a voltage anomaly classification model, and classifying the voltage data of the voltage anomalies; and constructing an eVTOL aircraft emergency landing point selection method based on different categories of voltage anomalies. The present invention greatly improves flight safety and emergency response capabilities.
Description
Technical Field
The invention belongs to the technical field of eVTOL aircraft system detection, and particularly relates to an emergency forced landing method based on eVTOL aircraft battery voltage abnormality.
Background
The stability of the battery voltage is critical for eVTOL aircraft, which directly affects the safety of the flight, performance efficiency, system life and energy management. The stable voltage ensures that the motor and flight control system of the aircraft can operate in an optimal state, thereby improving the stability of the flight and the consistency of the power output. In addition, voltage stabilization also helps to extend battery and electronic component life, maintaining device performance by reducing wear from fluctuations. Efficient battery management and energy usage prediction also relies on voltage stabilization, which is essential to ensure that the aircraft is able to complete a predetermined mission and return safely.
However, abnormal fluctuations in voltage can have a number of serious consequences, including failure of the power system, failure of the control system, and even damage to the battery itself. These problems can lead to unstable power output of the aircraft, delayed control response, and even emergency landing or accidents of the aircraft in severe cases, endangering personnel safety.
EVTOL the lack of a voltage anomaly identification method for an aircraft faces various problems and risks. First, voltage anomalies can lead to failure or unstable performance of critical systems of the aircraft, such as propulsion systems, navigation systems, and communication systems, which directly threatens flight safety, increasing the risk of accidents. For example, too low a voltage or large fluctuations may cause unstable motor power output, affect the lift and driving forces of the aircraft, and may even cause the aircraft to run away. Secondly, the voltage abnormality is not recognized and processed in time, and permanent damage can be caused to electronic equipment of the aircraft, so that maintenance cost and maintenance difficulty are increased. Long-term voltage instability can also affect the state of health and the useful life of the battery, thereby affecting the economic efficiency and operational efficiency of the overall aircraft.
Disclosure of Invention
The invention aims to solve the problem of ensuring the flight safety of eVTOL aircraft and provides an emergency forced landing method based on eVTOL aircraft battery voltage abnormality.
In order to achieve the above purpose, the present invention is realized by the following technical scheme:
an emergency forced landing method based on eVTOL aircraft battery voltage anomalies comprises the following steps:
S1, collecting data of influence factors of eVTOL aircraft battery voltage and eVTOL aircraft battery voltage at the same moment, and constructing an aircraft battery voltage data prediction dataset comprising a training set, a verification set and a test set;
s2, constructing eVTOL an aircraft battery voltage data prediction model based on the improved LSTM neural network;
s3, training the eVTOL aircraft battery voltage data prediction model by using the training set obtained in the step S1 to obtain a trained eVTOL aircraft battery voltage data prediction model;
s4, acquiring data of battery voltage and influence factors of eVTOL aircraft battery voltage in the flight process of eVTOL aircraft in real time, predicting eVTOL aircraft battery voltage by using the trained eVTOL aircraft battery voltage data prediction model obtained in the step S3, identifying voltage abnormality based on the predicted voltage, and extracting voltage data of the voltage abnormality;
s5, constructing a voltage abnormal condition classification model, and classifying the voltage abnormal conditions of the voltage data obtained in the step S4;
S6, constructing eVTOL an aircraft emergency forced landing point selection method based on the different types of voltage abnormal conditions obtained in the step S5.
Further, the specific implementation method of the step S1 includes the following steps:
S1.1, collecting data of influence factors of eVTOL aircraft battery voltage and eVTOL aircraft battery voltage at the same time, wherein the data of the influence factors of the eVTOL aircraft battery voltage comprise ambient temperature, charge and discharge cycle times, flight speed, flight resistance, initial battery charge, flight height and unmanned plane weight;
collecting unmanned aerial vehicle flight process through thermal infrared imager The ambient temperature corresponding to the time is in turn;
Collecting unmanned aerial vehicle flight process by reading recorded values in battery management systemThe charge and discharge cycle times corresponding to the time are sequentially as follows;
Collecting unmanned aerial vehicle flight process by using aircraft-mounted navigation moduleThe flying speeds corresponding to the moments are in turn;
Measuring unmanned aerial vehicle flight process through pressure sensorThe flight resistances corresponding to the moments are in turn;
Collecting unmanned aerial vehicle in flight through coulometerThe initial charge amount of the battery corresponding to the moment is sequentially as follows;
Collecting unmanned aerial vehicle flight process through aircraft-mounted navigation moduleThe flying heights corresponding to the moments are in sequence;
Collecting unmanned aerial vehicle flight process through load sensorThe weight of the unmanned aerial vehicle corresponding to time is sequentially as follows;
Collecting unmanned aerial vehicle flight process through voltage sensorThe voltages of the batteries corresponding to the moments are sequentially as follows;
S1.2, dividing the data at t 1-tn obtained in the step S1.1 into a plurality of continuous time sequences, wherein the length of each time sequence is J, the number of the time sequences obtained by dividing is K, namely, the time corresponding to the first time sequence is t 1-tJ, the time corresponding to the second time sequence is t 2-t (J+1), the time corresponding to the third time sequence is t 3-t (J+2), and the time corresponding to the K time sequence is tK-t (J+K-1);
and dividing all the K time series data into a training set, a verification set and a test set according to the proportion relation of 8:1:1.
Further, the specific implementation method of the step S2 includes the following steps:
S2.1, setting an improved amnestic door activation value calculation expression in an improved LSTM neural network as follows:
;
Wherein, In order to forget the activation value of the door,For the sigmoid activation function,For the layer normalization,For the Dropout regularization,For the weight of the forgetting gate,As the final output of the last time step,For the input of the current time step,In order to perform the connection operation,In forgetting to leave the doorIs used for the weight of the (c),In order to be the cell state of the previous time step,Bias for forgetting the door;
S2.2, in the improved LSTM neural network, the method for calculating the activation value of the improved input gate is as follows:
;
Wherein, For the input of the activation value of the gate,For the weight of the input gate,Is input into the doorIs used for the weight of the (c),Bias for the input gate;
S2.3, in the improved LSTM neural network, the improved cell candidate value calculation method is as follows:
;
Wherein, As a candidate value for the cell,For the hyperbolic tangent activation function,As a weight for the candidate value of the cell,Among cell candidatesIs used for the weight of the (c),Bias for cell candidates;
s2.4, in the improved LSTM neural network, the improved calculation method of the cell state update is as follows:
;
Wherein, In order for the attention to be weighted,The function is activated for softmax and,For the coefficient of the attention weighting,In the attention weightingIs used for the weight of the (c),Bias for attention weight;
;
Wherein, Is in a cellular state; is a dot product operation;
S2.5, in the improved LSTM neural network, the improved output gate and the final output calculation method are as follows:
;
Wherein, In order to output the activation value of the gate,In order to output the weight of the gate,In order to output the weight of the gate,Offset for the output gate;
;
Wherein, Is the final output value;
S2.6, updating the improved LSTM model calculation formula into an algorithm corresponding to the LSTM model, and deploying the improved LSTM model calculation formula into a computer to complete eVTOL construction of the aircraft battery voltage data prediction model.
Further, the specific implementation method of the step S3 includes the following steps:
S3.1, inputting a training set into a eVTOL aircraft battery voltage data prediction model for training, wherein in the training process, a loss function adopts a mean square error MSE, and the calculation method is as follows:
;
Wherein, For the number of samples to be taken,Is a true value of the voltage of the battery,A predicted value of the battery voltage;
S3.2, error correction is achieved through a reverse propagation and random gradient descent SGD method, when the loss function value tends to be stable or reaches a preset training round, training is finished, training of a eVTOL aircraft battery voltage data prediction model is completed, and the model is used for predicting battery voltage in the flight process of the eVTOL aircraft.
Further, the method for identifying the voltage abnormality of the predicted voltage in step S4 includes the following steps:
Prediction of the first step based on step S3 Battery voltage value at timeThe battery voltage value obtained by actual monitoring by adopting the voltage sensor is;
Comparison ofAnd (3) withWhen (when)In whichAllowable battery voltage error determined for expert, indicating predicted firstBattery voltage value at time and actual monitoringThe battery voltage value at the moment is kept consistent;
When (when) When the predicted first is indicatedBattery voltage value at time and actual monitoringThe battery voltage value at the moment has larger difference and has abnormal voltage, and the actual monitoring is extractedTime and the battery voltage values at M times before and after the time.
Further, the specific implementation method of the step S5 includes the following steps:
S5.1, setting voltage abnormality conditions including voltage dip, voltage continuous drop, voltage abnormality fluctuation and instantaneous voltage spike;
S5.2, acquiring voltage dip, voltage continuous drop, voltage abnormal fluctuation and instantaneous voltage spike data from an aviation battery performance database of an industry database, and drawing a corresponding discount chart of voltage change along with time by adopting the data;
S5.3, labeling the abnormal voltage condition in the time-varying voltage fold-back chart obtained in the step S5.2 by using a labeling tool LabelImg, wherein labeling information comprises coordinates of a labeling frame and types of abnormal conditions;
S5.4, a YOLOv deep learning model is deployed in a computer, based on the training set, the verification set and the test set divided in the step S5.3, the learning rate and the batch size super-parameters of the model are set, an optimizer and a loss function are adopted to train the YOLOv deep learning model, and when the model loss function value tends to be stable or reaches a preset training round, the training is finished, and a voltage abnormal condition classification model is obtained;
S5.5, drawing a line graph of the change of the battery voltage value along with time according to the voltage data of the voltage abnormal situation obtained in the step S4, and then inputting the line graph into a voltage abnormal situation classification model to classify the voltage abnormal situation.
Further, the specific implementation method of the step S6 includes the following steps:
S6.1, constructing eVTOL an aircraft emergency forced landing point selection method;
s6.1.1 acquiring the current position of the aircraft by using a eVTOL aircraft-mounted navigation system And the current speedMeasuring residual charge of battery by coulometerMeasuring current using a current sensorMeasuring voltage using a voltage sensorOn the basis of this, the current power consumption is calculatedThe calculation formula is as follows:
;
then calculate eVTOL the remaining flying distance of the aircraft The calculation formula is as follows:
;
S6.1.2 emergency forced landing point selection:
identifying eVTOL potential drop points of the aircraft visual field range content by using a geographic information system, and selecting nm potential drop points, wherein the consideration factors of the potential drop points comprise terrain flatness PT, barrier density ZM, population density RM and ground surface type DB, and the consideration factor data of the drop points are obtained from a geographic information system platform as follows:
establishing a scoring standard for each potential drop point, and calculating an expression as follows:
;
Wherein, Is the firstThe scores corresponding to the individual potential drop points,Respectively the weight coefficient of the terrain flatness, the obstacle density, the population density and the earth surface type,Respectively the firstGrading the topography flatness, the obstacle density, the population density and the surface type corresponding to the potential drop points, wherein the grading of the topography flatness, the obstacle density, the population density and the surface type corresponding to the potential drop points is obtained by directly grading by staff;
all are scored from the big to the small Sorting the potential drop points, and sequentially calculating the potential drop points according to the sortingWith the current position of the aircraftDistance betweenThe calculation formula is as follows:
;
Comparison of And (3) withRelationships between whenWhen the potential drop point calculated at present is indicated to be within the range of the rest flight distance of the eVTOL aircraft, namely the potential drop point calculated at present is selected as an emergency forced landing point;
When (when) Indicating that the currently calculated potential drop point is not within the range of the rest flyable distance of eVTOL aircraft, continuously sequencing from large to small according to the score, and calculating the distance between the next potential drop point and the current position of the aircraft until the following potential drop point is satisfiedWhen the potential drop point calculated at present is selected as an emergency forced drop point, and then calculation is stopped;
And S6.2, setting the emergency forced landing by adopting a eVTOL aircraft emergency forced landing point selection method when the voltage abnormal situation obtained in the step S5 is classified, judging that the voltage is suddenly dropped, and recording the battery state when the voltage is not suddenly dropped, and carrying out battery maintenance.
The invention has the beneficial effects that:
The emergency forced landing method based on eVTOL aircraft battery voltage abnormality comprises the steps of judging voltage abnormality through monitoring battery voltage data in real time in the flight process of a VTOL aircraft, classifying the identified voltage abnormality by adopting an abnormal voltage classification model, and finally, providing a eVTOL aircraft emergency forced landing point selection method aiming at the situation that battery damage is serious. And finally, the comprehensive monitoring of the battery voltage in the flight process of the eVTOL aircraft can be realized, and the flight safety of the aircraft is ensured. The invention can comprehensively and accurately realize the identification of the abnormal voltage value, thereby finding and preventing potential faults of the power system in advance, ensuring the normal operation of equipment and the stability of the system and reducing the risk of unexpected power failure.
According to the emergency forced landing method based on eVTOL abnormal voltage of the aircraft battery, after serious abnormality occurs to the aircraft voltage, the emergency forced landing point can be rapidly determined according to surrounding environment information, so that the flight safety and emergency response capability are greatly improved. The accident risk caused by the voltage problem is reduced.
Drawings
FIG. 1 is a flow chart of an emergency forced landing method based on eVTOL aircraft battery voltage anomalies in accordance with the present invention;
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be further described in detail below with reference to the accompanying drawings and detailed description. It should be understood that the embodiments described herein are for purposes of illustration only and are not intended to limit the invention, i.e., the embodiments described are merely some, but not all, of the embodiments of the invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein can be arranged and designed in a wide variety of different configurations, and the present invention can have other embodiments as well.
Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the present invention without making any inventive effort, are intended to fall within the scope of the present invention.
For further understanding of the invention, the following detailed description is presented in conjunction with the accompanying drawings 1 to provide a further understanding of the invention in its aspects, features and efficacy:
Example 1:
an emergency forced landing method based on eVTOL aircraft battery voltage anomalies comprises the following steps:
S1, collecting data of influence factors of eVTOL aircraft battery voltage and eVTOL aircraft battery voltage at the same moment, and constructing an aircraft battery voltage data prediction dataset comprising a training set, a verification set and a test set;
further, the specific implementation method of the step S1 includes the following steps:
S1.1, collecting data of influence factors of eVTOL aircraft battery voltage and eVTOL aircraft battery voltage at the same time, wherein the data of the influence factors of the eVTOL aircraft battery voltage comprise ambient temperature, charge and discharge cycle times, flight speed, flight resistance, initial battery charge, flight height and unmanned plane weight;
collecting unmanned aerial vehicle flight process through thermal infrared imager The ambient temperature corresponding to the time is in turn;
Further, the ambient temperature refers to the ambient temperature of the operating environment of the unmanned aerial vehicle. The low temperature can increase the internal resistance of the battery, reduce the discharge efficiency, lead to voltage drop, and the high temperature can lead to overheating of the battery, affecting the performance and the service life of the battery.
Collecting unmanned aerial vehicle flight process by reading recorded values in battery management systemThe charge and discharge cycle times corresponding to the time are sequentially as follows;
Further, the number of charge and discharge cycles refers to the number of complete cycles for the battery to complete charging and discharging. Each time the battery is used from full charge to requiring recharging, it is counted as one cycle. As the number of charge and discharge cycles increases, the battery capacity gradually decreases, resulting in a faster voltage drop under the same load.
Collecting unmanned aerial vehicle flight process by using aircraft-mounted navigation moduleThe flying speeds corresponding to the moments are in turn;
Further, the flying speed refers to the speed at which the unmanned aerial vehicle moves in the air. High speed flights increase windage, require more power to overcome drag, result in greater current consumption and faster voltage drops.
Measuring unmanned aerial vehicle flight process through pressure sensorThe flight resistances corresponding to the moments are in turn;
Further, flight resistance refers to the force that impedes the movement of the drone in the air. Mainly comprising air resistance. Upwind flight consumes more energy than downwind flight and the accelerating voltage drops.
Collecting unmanned aerial vehicle in flight through coulometerThe initial charge amount of the battery corresponding to the moment is sequentially as follows;
Further, the initial charge of the battery refers to the state of charge of the battery before the unmanned aerial vehicle takes off. Typically expressed as a percentage, 100% indicates that the battery is fully charged. Insufficient initial charge results in lower voltage at take-off and faster voltage drop during flight. Overcharge may lead to reduced battery life, affecting long-term voltage stability.
Collecting unmanned aerial vehicle flight process through aircraft-mounted navigation moduleThe flying heights corresponding to the moments are in sequence;
Further, flying height refers to the vertical distance of the unmanned aerial vehicle relative to the ground or sea level. At high altitudes, the air density decreases, more power is required to sustain the flight, and the accelerating voltage decreases. Frequent height changes (both rising and falling) increase energy consumption, affecting voltage stability.
Collecting unmanned aerial vehicle flight process through load sensorThe weight of the unmanned aerial vehicle corresponding to time is sequentially as follows;
Further, the weight of the unmanned aerial vehicle refers to the total weight of the unmanned aerial vehicle, and the weight of all components including a machine body, a battery, a load and the like is added. The increased total weight of the drone directly increases the motor load, resulting in greater current consumption and faster voltage drop. The uneven weight distribution may cause some motors to be overloaded, resulting in uneven voltage consumption.
Collecting unmanned aerial vehicle flight process through voltage sensorThe voltages of the batteries corresponding to the moments are sequentially as follows;
S1.2, dividing the data at t 1-tn obtained in the step S1.1 into a plurality of continuous time sequences, wherein the length of each time sequence is J, the number of the time sequences obtained by dividing is K, namely, the time corresponding to the first time sequence is t 1-tJ, the time corresponding to the second time sequence is t 2-t (J+1), the time corresponding to the third time sequence is t 3-t (J+2), and the time corresponding to the K time sequence is tK-t (J+K-1);
and dividing all the K time series data into a training set, a verification set and a test set according to the proportion relation of 8:1:1.
S2, constructing eVTOL an aircraft battery voltage data prediction model based on the improved LSTM neural network;
And a voltage sensor is adopted to measure and monitor the voltage of the battery terminal in real time in the flight process of the eVTOL aircraft. And a battery voltage data prediction model is constructed, so that the prediction of battery voltage data in the flight process of the eVTOL aircraft is realized, and then the battery voltage data is compared with the monitoring data to judge the abnormal condition of the voltage data.
In the process of constructing the prediction model, two problems exist, namely (1) in the traditional model, the long-term dependency relationship between data is difficult to capture, namely, the model is difficult to memorize and use the battery voltage value at the earlier moment to predict the battery voltage value at the future moment. (2) When predicting the battery voltage value, not all the information at the earlier time is equally important, and it is necessary to distinguish the importance of the information at the existing time.
Aiming at the problems, an LSTM (long-short-term memory network) model is provided, and a gating mechanism comprising an input gate, a forgetting gate and an output gate is introduced into the model, so that the long-term storage and forgetting of control information are realized, and the long-term problem of data is effectively solved. At the same time, the gating mechanism of LSTM may allow the model to learn the information importance of different time nodes. However, in LSTM, there are still the following problems, (1) in training LSTM, since the data in time series fluctuates greatly, the performance of the model may be affected, especially in the case of uneven data distribution. (2) Conventional LSTM models may not be accurate enough to handle data that contains complex time dependencies, such as battery voltage value changes, because the method typically relies on short-term inputs and hidden states only. (3) Conventional LSTM may ignore information that is particularly important for prediction when processing long sequence data, which is typically used to process the entire sequence. (4) In training a complex LSTM network, the model may overfit the training data, resulting in performance degradation in practical applications.
The above problems will lead to a problem that it is difficult to accurately predict the battery voltage value based on the monitoring data during the flight of eVTOL aircraft.
Therefore, in the present invention, the LSTM model is improved. The method comprises the following steps:
(1) Layer normalization techniques are introduced. The layer normalization can stabilize the learning process of LSTM, and improve the adaptability of the model under different data conditions, which is very important for unmanned aerial vehicle to fly under different environments and load conditions. This technique can help the model adapt better to environmental changes, such as the effects of ambient temperature, load changes on the battery voltage value.
(2) Peak connection techniques are introduced. The peak connection allows the model to directly use long-term memory to adjust the opening and closing of the gate, which is useful for predicting voltage values as in continuous battery operation.
(3) Attention mechanisms are introduced. The attention mechanism may help the model identify the most critical flight phase to the effect of battery voltage variations.
(4) Dropout regularization technique was introduced. In the prediction model of the battery voltage value of the unmanned aerial vehicle, the Dropout can be used for increasing the generalization capability of the model and reducing the prediction error under new or unseen flight conditions. This helps to maintain the stability and accuracy of the predictions when the drone is subjected to different environmental conditions or flight modes.
The 4 techniques are adopted to improve forgetting gate, input gate, cell candidate value, cell state update value, output gate and final output in the traditional LSTM, and concretely, the cell state is the core part of network memory and information is transmitted through a series of time steps. The cell status can be seen as a flowing "information road" carrying all the information that may be important for future decisions. In LSTM this cell state can be transferred in a virtually constant fashion at different time steps, with only fine adjustments being made by means of gating.
Further, the specific implementation method of the step S2 includes the following steps:
S2.1, setting an improved amnestic door activation value calculation expression in an improved LSTM neural network as follows:
;
Wherein, In order to forget the activation value of the door,For the sigmoid activation function,For the layer normalization,For the Dropout regularization,For the weight of the forgetting gate,As the final output of the last time step,For the input of the current time step,In order to perform the connection operation,In forgetting to leave the doorIs used for the weight of the (c),In order to be the cell state of the previous time step,Bias for forgetting the door;
Further, the function of the forgetting gate is to determine the information to discard from the cell state. It calculates a value between 0 and 1 by a sigmoid activation function, which multiplies the cell state element by element, thus achieving "forgetting" of the state. For eVTOL aircraft flight, for battery voltage predictions, a forget gate may help the model ignore these insignificant changes if the battery voltage does not change much under certain conditions.
S2.2, in the improved LSTM neural network, the method for calculating the activation value of the improved input gate is as follows:
;
Wherein, For the input of the activation value of the gate,For the weight of the input gate,Is input into the doorIs used for the weight of the (c),Bias for the input gate;
Further, the input gate controls the importance of the new information, determining the new information to be added to the cell state. The cell candidate is then a transformation of the new information that may be added to the cell state. For eVTOL during the flight of the aircraft, the input gate controls the importance of new voltage input information for battery voltage value prediction, and the cell candidate value updates the voltage value state according to the information.
S2.3, in the improved LSTM neural network, the improved cell candidate value calculation method is as follows:
;
Wherein, As a candidate value for the cell,For the hyperbolic tangent activation function,As a weight for the candidate value of the cell,Among cell candidatesIs used for the weight of the (c),Bias for cell candidates;
Further, the cell state is where the LSTM stores past information, which is updated at each time step to maintain long-term dependent information. For eVTOL in the flight process of the aircraft, when the battery voltage value is predicted, the updating of the cell state allows the model to retain and forget information, so that only useful information is ensured to be retained, and the prediction accuracy is improved.
S2.4, in the improved LSTM neural network, the improved calculation method of the cell state update is as follows:
;
Wherein, In order for the attention to be weighted,The function is activated for softmax and,For the coefficient of the attention weighting,In the attention weightingIs used for the weight of the (c),Bias for attention weight;
;
Wherein, Is in a cellular state; is a dot product operation;
S2.5, in the improved LSTM neural network, the improved output gate and the final output calculation method are as follows:
;
Wherein, In order to output the activation value of the gate,In order to output the weight of the gate,In order to output the weight of the gate,Offset for the output gate;
;
Wherein, Is the final output value;
Further, the output gate controls the amount of information output from the LSTM cell. The final output is based on the current cell state and the output of the output gate, which is the output that is passed on to the next time step and the portion of the final output. For eVTOL during the flight of the aircraft, the output gates and final outputs help determine the voltage value for each step, providing data support for battery management.
S2.6, updating the improved LSTM model calculation formula into an algorithm corresponding to the LSTM model, and deploying the improved LSTM model calculation formula into a computer to complete eVTOL construction of the aircraft battery voltage data prediction model.
S3, training the eVTOL aircraft battery voltage data prediction model by using the training set obtained in the step S1 to obtain a trained eVTOL aircraft battery voltage data prediction model;
further, the specific implementation method of the step S3 includes the following steps:
S3.1, inputting a training set into a eVTOL aircraft battery voltage data prediction model for training, wherein in the training process, a loss function adopts a mean square error MSE, and the calculation method is as follows:
;
Wherein, For the number of samples to be taken,Is a true value of the voltage of the battery,A predicted value of the battery voltage;
S3.2, error correction is achieved through a reverse propagation and random gradient descent SGD method, when the loss function value tends to be stable or reaches a preset training round, training is finished, training of a eVTOL aircraft battery voltage data prediction model is completed, and the model is used for predicting battery voltage in the flight process of the eVTOL aircraft.
S4, acquiring data of battery voltage and influence factors of eVTOL aircraft battery voltage in the flight process of eVTOL aircraft in real time, predicting eVTOL aircraft battery voltage by using the trained eVTOL aircraft battery voltage data prediction model obtained in the step S3, identifying voltage abnormality based on the predicted voltage, and extracting voltage data of the voltage abnormality;
Further, the method for identifying the voltage abnormality of the predicted voltage in step S4 includes the following steps:
Prediction of the first step based on step S3 Battery voltage value at timeThe battery voltage value obtained by actual monitoring by adopting the voltage sensor is;
Comparison ofAnd (3) withWhen (when)In whichAllowable battery voltage error determined for expert, indicating predicted firstBattery voltage value at time and actual monitoringThe battery voltage value at the moment is kept consistent;
When (when) When the predicted first is indicatedBattery voltage value at time and actual monitoringThe battery voltage value at the moment has larger difference and has abnormal voltage, and the actual monitoring is extractedTime and the battery voltage values at M times before and after the time.
S5, constructing a voltage abnormal condition classification model, and classifying the voltage abnormal conditions of the voltage data obtained in the step S4;
Further, the specific implementation method of the step S5 includes the following steps:
S5.1, setting voltage abnormality conditions including voltage dip, voltage continuous drop, voltage abnormality fluctuation and instantaneous voltage spike;
furthermore, the abnormal voltage conditions comprise voltage dip, voltage continuous drop, voltage abnormal fluctuation and instantaneous voltage spike, the abnormal characteristics of the voltage abnormal conditions are obvious, and the abnormal voltage conditions can be identified and classified by an image identification mode.
A voltage dip refers to a significant and abrupt drop in battery voltage within a very short period of time. The dip appears as a nearly vertical line segment on the voltage-time graph, typically a sharp, nearly instantaneous drop, which may quickly rise (form a V) or last some time in the low position. Causes of voltage dips include transient high current loads, internal battery shorts, loose connections, or poor contact.
The continuous decrease in voltage means that the battery voltage is continuously decreased at a faster rate than the normal discharge. The continuous voltage drop appears as a drop curve with a larger slope on the voltage-time diagram, the drop speed is obviously faster than the normal discharge curve, and the drop is possible to be linear drop or nonlinear acceleration drop. The reason for the sustained drop in voltage includes battery capacity depletion, battery aging or damage, and sustained overload.
The abnormal voltage fluctuation means that the battery voltage frequently fluctuates up and down in a short time with a large amplitude. The abnormal voltage fluctuation is in an irregular saw-tooth or wave-like curve on a voltage-time diagram, the fluctuation amplitude is obviously larger than small fluctuation in a normal working state, and the fluctuation frequency can be higher but is not necessarily regular. Causes of abnormal voltage fluctuation include abrupt load change and unstable electrochemical reaction inside the battery.
Transient voltage spikes refer to a significant upward peak in battery voltage in a very short time. The transient voltage spike appears as a sharp upward "spike" on the voltage-time diagram, typically a very brief spike, which then drops back to normal levels quickly, and which may be much higher than normal operating voltage. Causes of transient voltage spikes include sudden load removal, electromagnetic interference, charging system failure, sensor or data acquisition system anomalies.
S5.2, acquiring voltage dip, voltage continuous drop, voltage abnormal fluctuation and instantaneous voltage spike data from an aviation battery performance database of an industry database, and drawing a corresponding discount chart of voltage change along with time by adopting the data;
S5.3, labeling the abnormal voltage condition in the time-varying voltage fold-back chart obtained in the step S5.2 by using a labeling tool LabelImg, wherein labeling information comprises coordinates of a labeling frame and types of abnormal conditions;
S5.4, a YOLOv deep learning model is deployed in a computer, based on the training set, the verification set and the test set divided in the step S5.3, the learning rate and the batch size super-parameters of the model are set, an optimizer and a loss function are adopted to train the YOLOv deep learning model, and when the model loss function value tends to be stable or reaches a preset training round, the training is finished, and a voltage abnormal condition classification model is obtained;
S5.5, drawing a line graph of the change of the battery voltage value along with time according to the voltage data of the voltage abnormal situation obtained in the step S4, and then inputting the line graph into a voltage abnormal situation classification model to classify the voltage abnormal situation.
S6, constructing eVTOL an aircraft emergency forced landing point selection method based on the different types of voltage abnormal conditions obtained in the step S5.
Further, the specific implementation method of the step S6 includes the following steps:
S6.1, constructing eVTOL an aircraft emergency forced landing point selection method;
s6.1.1 acquiring the current position of the aircraft by using a eVTOL aircraft-mounted navigation system And the current speedMeasuring residual charge of battery by coulometerMeasuring current using a current sensorMeasuring voltage using a voltage sensorOn the basis of this, the current power consumption is calculatedThe calculation formula is as follows:
;
then calculate eVTOL the remaining flying distance of the aircraft The calculation formula is as follows:
;
S6.1.2 emergency forced landing point selection:
identifying eVTOL potential drop points of the aircraft visual field range content by using a geographic information system, and selecting nm potential drop points, wherein the consideration factors of the potential drop points comprise terrain flatness PT, barrier density ZM, population density RM and ground surface type DB, and the consideration factor data of the drop points are obtained from a geographic information system platform as follows:
establishing a scoring standard for each potential drop point, and calculating an expression as follows:
;
Wherein, Is the firstThe scores corresponding to the individual potential drop points,Respectively the weight coefficient of the terrain flatness, the obstacle density, the population density and the earth surface type,Respectively the firstGrading the topography flatness, the obstacle density, the population density and the surface type corresponding to the potential drop points, wherein the grading of the topography flatness, the obstacle density, the population density and the surface type corresponding to the potential drop points is obtained by directly grading by staff;
all are scored from the big to the small Sorting the potential drop points, and sequentially calculating the potential drop points according to the sortingWith the current position of the aircraftDistance betweenThe calculation formula is as follows:
;
Comparison of And (3) withRelationships between whenWhen the potential drop point calculated at present is indicated to be within the range of the rest flight distance of the eVTOL aircraft, namely the potential drop point calculated at present is selected as an emergency forced landing point;
When (when) Indicating that the currently calculated potential drop point is not within the range of the rest flyable distance of eVTOL aircraft, continuously sequencing from large to small according to the score, and calculating the distance between the next potential drop point and the current position of the aircraft until the following potential drop point is satisfiedWhen the potential drop point calculated at present is selected as an emergency forced drop point, and then calculation is stopped;
And S6.2, setting the emergency forced landing by adopting a eVTOL aircraft emergency forced landing point selection method when the voltage abnormal situation obtained in the step S5 is classified, judging that the voltage is suddenly dropped, and recording the battery state when the voltage is not suddenly dropped, and carrying out battery maintenance.
Further, voltage dips are considered to be the most severe compared to continuous drops in voltage, abnormal fluctuations in voltage, transient voltage spikes, most likely resulting in crashes. The risk of voltage dips is mainly due to its bursty, comprehensive impact and difficult recovery characteristics. The propulsion system and the control system may fail simultaneously, causing the aircraft to lose lift and control capability momentarily. Once a voltage dip occurs, it is a vital safety measure to find an emergency forced landing point immediately. This is because of time-critical, the system may fail rapidly. The rapid landing prevents the aircraft from completely losing control, minimizes the risk of crashing, and makes efficient use of the remaining power for controlled landing. Quick decisions are needed to cope with the voltage dip, the optimal landing point is selected, and an emergency procedure is executed. Therefore, when the voltage continuously drops, the voltage abnormally fluctuates and the instantaneous voltage spikes are the intelligent classification result for the voltage abnormality, the battery needs to be overhauled. In the battery inspection process, if the damage of the battery is not serious, the maintenance can be directly carried out, for example, the damage of the battery is seriously detected due to the influence of environmental temperature change, slight charge-discharge cycle influence or short-time load fluctuation, and the unmanned aerial vehicle emergency forced landing needs to be carried out by selecting an emergency forced landing point if the damage of the battery is seriously detected, for example, the internal short circuit of the battery, the leakage of electrolyte or the expansion of the battery. When the voltage abnormality intelligent classification result is voltage dip, an emergency forced landing point needs to be selected immediately.
The key points and the points to be protected of the invention are as follows:
(1) Voltage abnormality identification and classification method
(2) A eVTOL aircraft emergency forced landing point selection method.
It is noted that relational terms such as "first" and "second", and the like, are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, 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.
Although the application has been described above with reference to specific embodiments, various modifications may be made and equivalents may be substituted for elements thereof without departing from the scope of the application. In particular, the features of the disclosed embodiments may be combined with each other in any manner so long as there is no structural conflict, and the exhaustive description of these combinations is not given in this specification solely for the sake of brevity and resource saving. Therefore, it is intended that the application not be limited to the particular embodiments disclosed herein, but that the application will include all embodiments falling within the scope of the appended claims.
Claims (7)
1. An emergency forced landing method based on eVTOL aircraft battery voltage abnormality is characterized by comprising the following steps:
S1, collecting data of influence factors of eVTOL aircraft battery voltage and eVTOL aircraft battery voltage at the same moment, and constructing an aircraft battery voltage data prediction dataset comprising a training set, a verification set and a test set;
s2, constructing eVTOL an aircraft battery voltage data prediction model based on the improved LSTM neural network;
s3, training the eVTOL aircraft battery voltage data prediction model by using the training set obtained in the step S1 to obtain a trained eVTOL aircraft battery voltage data prediction model;
s4, acquiring data of battery voltage and influence factors of eVTOL aircraft battery voltage in the flight process of eVTOL aircraft in real time, predicting eVTOL aircraft battery voltage by using the trained eVTOL aircraft battery voltage data prediction model obtained in the step S3, identifying voltage abnormality based on the predicted voltage, and extracting voltage data of the voltage abnormality;
s5, constructing a voltage abnormal condition classification model, and classifying the voltage abnormal conditions of the voltage data obtained in the step S4;
S6, constructing eVTOL an aircraft emergency forced landing point selection method based on the different types of voltage abnormal conditions obtained in the step S5.
2. The emergency forced landing method based on eVTOL aircraft battery voltage anomalies of claim 1, wherein the specific implementation method of step S1 includes the steps of:
S1.1, collecting data of influence factors of eVTOL aircraft battery voltage and eVTOL aircraft battery voltage at the same time, wherein the data of the influence factors of the eVTOL aircraft battery voltage comprise ambient temperature, charge and discharge cycle times, flight speed, flight resistance, initial battery charge, flight height and unmanned plane weight;
collecting unmanned aerial vehicle flight process through thermal infrared imager The ambient temperature corresponding to the time is in turn;
Collecting unmanned aerial vehicle flight process by reading recorded values in battery management systemThe charge and discharge cycle times corresponding to the time are sequentially as follows;
Collecting unmanned aerial vehicle flight process by using aircraft-mounted navigation moduleThe flying speeds corresponding to the moments are in turn;
Measuring unmanned aerial vehicle flight process through pressure sensorThe flight resistances corresponding to the moments are in turn;
Collecting unmanned aerial vehicle in flight through coulometerThe initial charge amount of the battery corresponding to the moment is sequentially as follows;
Collecting unmanned aerial vehicle flight process through aircraft-mounted navigation moduleThe flying heights corresponding to the moments are in sequence;
Collecting unmanned aerial vehicle flight process through load sensorThe weight of the unmanned aerial vehicle corresponding to time is sequentially as follows;
Collecting unmanned aerial vehicle flight process through voltage sensorThe voltages of the batteries corresponding to the moments are sequentially as follows;
S1.2, dividing the data at t 1-tn obtained in the step S1.1 into a plurality of continuous time sequences, wherein the length of each time sequence is J, the number of the time sequences obtained by dividing is K, namely, the time corresponding to the first time sequence is t 1-tJ, the time corresponding to the second time sequence is t 2-t (J+1), the time corresponding to the third time sequence is t 3-t (J+2), and the time corresponding to the K time sequence is tK-t (J+K-1);
and dividing all the K time series data into a training set, a verification set and a test set according to the proportion relation of 8:1:1.
3. The emergency forced landing method based on eVTOL aircraft battery voltage anomalies of claim 2, wherein the specific implementation method of step S2 includes the steps of:
S2.1, setting an improved amnestic door activation value calculation expression in an improved LSTM neural network as follows:
;
Wherein, In order to forget the activation value of the door,For the sigmoid activation function,For the layer normalization,For the Dropout regularization,For the weight of the forgetting gate,As the final output of the last time step,For the input of the current time step,In order to perform the connection operation,In forgetting to leave the doorIs used for the weight of the (c),In order to be the cell state of the previous time step,Bias for forgetting the door;
S2.2, in the improved LSTM neural network, the method for calculating the activation value of the improved input gate is as follows:
;
Wherein, For the input of the activation value of the gate,For the weight of the input gate,Is input into the doorIs used for the weight of the (c),Bias for the input gate;
S2.3, in the improved LSTM neural network, the improved cell candidate value calculation method is as follows:
;
Wherein, As a candidate value for the cell,For the hyperbolic tangent activation function,As a weight for the candidate value of the cell,Among cell candidatesIs used for the weight of the (c),Bias for cell candidates;
s2.4, in the improved LSTM neural network, the improved calculation method of the cell state update is as follows:
;
Wherein, In order for the attention to be weighted,The function is activated for softmax and,For the coefficient of the attention weighting,In the attention weightingIs used for the weight of the (c),Bias for attention weight;
;
Wherein, Is in a cellular state; is a dot product operation;
S2.5, in the improved LSTM neural network, the improved output gate and the final output calculation method are as follows:
;
Wherein, In order to output the activation value of the gate,In order to output the weight of the gate,In order to output the weight of the gate,Offset for the output gate;
;
Wherein, Is the final output value;
S2.6, updating the improved LSTM model calculation formula into an algorithm corresponding to the LSTM model, and deploying the improved LSTM model calculation formula into a computer to complete eVTOL construction of the aircraft battery voltage data prediction model.
4. The emergency forced landing method based on eVTOL aircraft battery voltage anomalies as claimed in claim 3, wherein the specific implementation method of step S3 includes the steps of:
S3.1, inputting a training set into a eVTOL aircraft battery voltage data prediction model for training, wherein in the training process, a loss function adopts a mean square error MSE, and the calculation method is as follows:
;
Wherein, For the number of samples to be taken,Is a true value of the voltage of the battery,A predicted value of the battery voltage;
S3.2, error correction is achieved through a reverse propagation and random gradient descent SGD method, when the loss function value tends to be stable or reaches a preset training round, training is finished, training of a eVTOL aircraft battery voltage data prediction model is completed, and the model is used for predicting battery voltage in the flight process of the eVTOL aircraft.
5. The method for emergency forced landing based on eVTOL aircraft battery voltage anomalies according to claim 4, wherein the method for voltage anomaly identification of the predicted voltage in step S4 includes the steps of:
Prediction of the first step based on step S3 Battery voltage value at timeThe battery voltage value obtained by actual monitoring by adopting the voltage sensor is;
Comparison ofAnd (3) withWhen (when)In whichAllowable battery voltage error determined for expert, indicating predicted firstBattery voltage value at time and actual monitoringThe battery voltage value at the moment is kept consistent;
When (when) When the predicted first is indicatedBattery voltage value at time and actual monitoringThe battery voltage value at the moment has larger difference and has abnormal voltage, and the actual monitoring is extractedTime and the battery voltage values at M times before and after the time.
6. The emergency forced landing method based on eVTOL aircraft battery voltage anomalies of claim 5, wherein the specific implementation method of step S5 includes the steps of:
S5.1, setting voltage abnormality conditions including voltage dip, voltage continuous drop, voltage abnormality fluctuation and instantaneous voltage spike;
S5.2, acquiring voltage dip, voltage continuous drop, voltage abnormal fluctuation and instantaneous voltage spike data from an aviation battery performance database of an industry database, and drawing a corresponding discount chart of voltage change along with time by adopting the data;
S5.3, labeling the abnormal voltage condition in the time-varying voltage fold-back chart obtained in the step S5.2 by using a labeling tool LabelImg, wherein labeling information comprises coordinates of a labeling frame and types of abnormal conditions;
S5.4, a YOLOv deep learning model is deployed in a computer, based on the training set, the verification set and the test set divided in the step S5.3, the learning rate and the batch size super-parameters of the model are set, an optimizer and a loss function are adopted to train the YOLOv deep learning model, and when the model loss function value tends to be stable or reaches a preset training round, the training is finished, and a voltage abnormal condition classification model is obtained;
S5.5, drawing a line graph of the change of the battery voltage value along with time according to the voltage data of the voltage abnormal situation obtained in the step S4, and then inputting the line graph into a voltage abnormal situation classification model to classify the voltage abnormal situation.
7. The emergency forced landing method based on eVTOL aircraft battery voltage anomalies of claim 6, wherein the specific implementation method of step S6 includes the steps of:
S6.1, constructing eVTOL an aircraft emergency forced landing point selection method;
s6.1.1 acquiring the current position of the aircraft by using a eVTOL aircraft-mounted navigation system And the current speedMeasuring residual charge of battery by coulometerMeasuring current using a current sensorMeasuring voltage using a voltage sensorOn the basis of this, the current power consumption is calculatedThe calculation formula is as follows:
;
then calculate eVTOL the remaining flying distance of the aircraft The calculation formula is as follows:
;
S6.1.2 emergency forced landing point selection:
identifying eVTOL potential drop points of the aircraft visual field range content by using a geographic information system, and selecting nm potential drop points, wherein the consideration factors of the potential drop points comprise terrain flatness PT, barrier density ZM, population density RM and ground surface type DB, and the consideration factor data of the drop points are obtained from a geographic information system platform as follows:
establishing a scoring standard for each potential drop point, and calculating an expression as follows:
;
Wherein, Is the firstThe scores corresponding to the individual potential drop points,Respectively the weight coefficient of the terrain flatness, the obstacle density, the population density and the earth surface type,Respectively the firstGrading the topography flatness, the obstacle density, the population density and the surface type corresponding to the potential drop points, wherein the grading of the topography flatness, the obstacle density, the population density and the surface type corresponding to the potential drop points is obtained by directly grading by staff;
all are scored from the big to the small Sorting the potential drop points, and sequentially calculating the potential drop points according to the sortingWith the current position of the aircraftDistance betweenThe calculation formula is as follows:
;
Comparison of And (3) withRelationships between whenWhen the potential drop point calculated at present is indicated to be within the range of the rest flight distance of the eVTOL aircraft, namely the potential drop point calculated at present is selected as an emergency forced landing point;
When (when) Indicating that the currently calculated potential drop point is not within the range of the rest flyable distance of eVTOL aircraft, continuously sequencing from large to small according to the score, and calculating the distance between the next potential drop point and the current position of the aircraft until the following potential drop point is satisfiedWhen the potential drop point calculated at present is selected as an emergency forced drop point, and then calculation is stopped;
And S6.2, setting the emergency forced landing by adopting a eVTOL aircraft emergency forced landing point selection method when the voltage abnormal situation obtained in the step S5 is classified, judging that the voltage is suddenly dropped, and recording the battery state when the voltage is not suddenly dropped, and carrying out battery maintenance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411699579.5A CN119203007A (en) | 2024-11-26 | 2024-11-26 | An emergency landing method based on abnormal battery voltage of eVTOL aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202411699579.5A CN119203007A (en) | 2024-11-26 | 2024-11-26 | An emergency landing method based on abnormal battery voltage of eVTOL aircraft |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN119203007A true CN119203007A (en) | 2024-12-27 |
Family
ID=94076437
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202411699579.5A Pending CN119203007A (en) | 2024-11-26 | 2024-11-26 | An emergency landing method based on abnormal battery voltage of eVTOL aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN119203007A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121150269A (en) * | 2025-11-19 | 2025-12-16 | 动子科技(宁波)有限公司 | A hot-swap system and a robot equipped with the system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110264312A1 (en) * | 2010-04-21 | 2011-10-27 | Spinelli Charles B | Determining Landing Sites for Aircraft |
| CN109739253A (en) * | 2019-01-28 | 2019-05-10 | 深圳市道通智能航空技术有限公司 | A kind of aircraft battery monitoring method, device, battery and aircraft |
| CN112731971A (en) * | 2021-04-02 | 2021-04-30 | 北京三快在线科技有限公司 | Method and device for controlling unmanned aerial vehicle to land, readable storage medium and electronic equipment |
| CN113589189A (en) * | 2021-08-30 | 2021-11-02 | 武汉理工大学 | Lithium battery health condition prediction method and device based on charging and discharging data characteristics |
| CN113625759A (en) * | 2021-08-25 | 2021-11-09 | 深圳市道通智能航空技术股份有限公司 | Unmanned aerial vehicle forced landing control method and device, remote control device and storage medium |
| CN116908699A (en) * | 2023-07-24 | 2023-10-20 | 中山大学 | Lithium battery health prediction method and system based on LSTM and multiple features |
| CN117251819A (en) * | 2023-11-20 | 2023-12-19 | 广东蘑菇物联科技有限公司 | Electric energy data anomaly detection method, device, storage medium and computer equipment |
| CN118070204A (en) * | 2024-04-23 | 2024-05-24 | 山东理工职业学院 | Unmanned aerial vehicle power data anomaly identification method and device based on neural network |
| CN118095106A (en) * | 2024-04-23 | 2024-05-28 | 珠海翔翼航空技术有限公司 | Method, system and device for predicting remaining fuel value of aircraft |
| CN119203006A (en) * | 2024-11-26 | 2024-12-27 | 深圳市城市交通规划设计研究中心股份有限公司 | A method for diagnosing abnormal flight status of an electric vertical take-off and landing aircraft |
-
2024
- 2024-11-26 CN CN202411699579.5A patent/CN119203007A/en active Pending
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20110264312A1 (en) * | 2010-04-21 | 2011-10-27 | Spinelli Charles B | Determining Landing Sites for Aircraft |
| CN109739253A (en) * | 2019-01-28 | 2019-05-10 | 深圳市道通智能航空技术有限公司 | A kind of aircraft battery monitoring method, device, battery and aircraft |
| CN112731971A (en) * | 2021-04-02 | 2021-04-30 | 北京三快在线科技有限公司 | Method and device for controlling unmanned aerial vehicle to land, readable storage medium and electronic equipment |
| CN113625759A (en) * | 2021-08-25 | 2021-11-09 | 深圳市道通智能航空技术股份有限公司 | Unmanned aerial vehicle forced landing control method and device, remote control device and storage medium |
| CN113589189A (en) * | 2021-08-30 | 2021-11-02 | 武汉理工大学 | Lithium battery health condition prediction method and device based on charging and discharging data characteristics |
| CN116908699A (en) * | 2023-07-24 | 2023-10-20 | 中山大学 | Lithium battery health prediction method and system based on LSTM and multiple features |
| CN117251819A (en) * | 2023-11-20 | 2023-12-19 | 广东蘑菇物联科技有限公司 | Electric energy data anomaly detection method, device, storage medium and computer equipment |
| CN118070204A (en) * | 2024-04-23 | 2024-05-24 | 山东理工职业学院 | Unmanned aerial vehicle power data anomaly identification method and device based on neural network |
| CN118095106A (en) * | 2024-04-23 | 2024-05-28 | 珠海翔翼航空技术有限公司 | Method, system and device for predicting remaining fuel value of aircraft |
| CN119203006A (en) * | 2024-11-26 | 2024-12-27 | 深圳市城市交通规划设计研究中心股份有限公司 | A method for diagnosing abnormal flight status of an electric vertical take-off and landing aircraft |
Non-Patent Citations (1)
| Title |
|---|
| 月末刀戈: ""LSTM模型精度提升技术要点整合"", 《CSDN》, 4 October 2024 (2024-10-04), pages 1 - 9 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN121150269A (en) * | 2025-11-19 | 2025-12-16 | 动子科技(宁波)有限公司 | A hot-swap system and a robot equipped with the system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Li et al. | Study on the environmental adaptability of lithium-ion battery powered UAV under extreme temperature conditions | |
| KR101992051B1 (en) | Method and system for predicting state of charge of battery | |
| CN119203006B (en) | A method for diagnosing abnormal flight status of an electric vertical take-off and landing aircraft | |
| EP3850551A1 (en) | Systems and methods for managing energy storage systems | |
| CN111680848A (en) | Battery life prediction method and storage medium based on prediction model fusion | |
| EP4064519B1 (en) | Evaluation device, computer program, and evaluation method | |
| CN102749589A (en) | Recession-mode predicting method of power battery of electric automobile | |
| CN111157898A (en) | New energy vehicle online battery fault detection and analysis method and device | |
| KR20160017416A (en) | Method and device to estimate battery life about user characteristic based on pattern information | |
| CN114460481B (en) | Bi-LSTM and attention mechanism-based energy storage battery thermal runaway early warning method | |
| CN119203007A (en) | An emergency landing method based on abnormal battery voltage of eVTOL aircraft | |
| US20250102582A1 (en) | Simulating battery dynamics with equivalent circuit models | |
| CN120161864B (en) | Decision-making methods and systems for low-battery autonomous landing of vertical takeoff and landing UAVs | |
| CN111626327A (en) | Aircraft heavy landing prediction method, device, computer equipment and storage medium | |
| KR102159817B1 (en) | Energy storage device through deep learning operation method and recording medium storing program for executing the same, and computer program stored in recording medium for executing the same | |
| US20250296580A1 (en) | System and method for electric vehicle operational optimization | |
| Uhm et al. | State-of-charge estimation for remaining flying time prediction of small UAV using adaptive robust extended Kalman filter | |
| CN106127407B (en) | Airplane travel scoring method and system based on multi-sensor information fusion | |
| CN116862079B (en) | Enterprise pollutant emission prediction method and prediction system | |
| CN120579277B (en) | Unmanned aerial vehicle structural fatigue prediction method and system | |
| CN116776255A (en) | GBDT and GS algorithm-based civil aircraft heavy landing risk prediction method and device | |
| CN120646242A (en) | Adaptive planning aviation fuel cell range-extending power system evaluation method and system | |
| CN112793797A (en) | Early warning method and system for landing bounce of airplane | |
| Goebel et al. | Prognostics applied to electric propulsion UAV | |
| Liu et al. | Battery fault diagnosis scheme based on improved RBF neural network |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20241227 |