Vehicle fault identification method and device, electronic equipment, vehicle, chip and medium

Abstract

The invention provides a vehicle fault identification method and apparatus, an electronic device, a vehicle, a chip and a medium. The method comprises the steps of obtaining multi-source fault feature data of the vehicle and a weight corresponding to the multi-source fault feature data; the multi-source fault feature data comprises fault feature data corresponding to a sensor, a vehicle-mounted diagnosis system and a vehicle communication system; determining a first fusion feature sequence based on the multi-source fault feature data and a weight corresponding to the multi-source fault feature data; determining a second fusion feature sequence within a preset duration, wherein the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence; respectively inputting the second fusion feature sequence into a plurality of classifiers to obtain a plurality of classification results of the vehicle fault type; and identifying a fault type of the vehicle based on the plurality of classification results. According to the vehicle fault identification scheme provided by the invention, the accuracy and comprehensiveness of vehicle fault diagnosis can be improved.

Description

Technical Field

[0001] The present application relates to the field of fault identification technology, and in particular to a vehicle fault identification method, device, electronic equipment, vehicle, chip and medium. Background Art

[0002] With the continuous development of automobile technology, vehicles are becoming more and more intelligent, and vehicle fault diagnosis is becoming more and more important. Traditional vehicle fault diagnosis methods mainly rely on manual experience and single sensor data, with low diagnostic accuracy and efficiency. In recent years, deep learning technology has achieved great success in image recognition, speech processing and other fields, providing new ideas for vehicle fault diagnosis.

[0003] However, most of the current deep learning-based vehicle fault diagnosis methods only utilize single sensor data, resulting in inaccurate and incomplete diagnostic results. Summary of the invention

[0004] In order to solve the above-mentioned problems in the prior art, the present application provides a vehicle fault identification method, device, electronic device, vehicle, chip and medium to improve the accuracy and comprehensiveness of vehicle fault diagnosis.

[0005] According to a first aspect of the present application, a vehicle fault identification method is provided, the method comprising:

[0006] Obtain multi-source fault characteristic data of the vehicle and weights corresponding to the multi-source fault characteristic data; the multi-source fault characteristic data includes fault characteristic data corresponding to sensors, on-board diagnostic systems, and vehicle communication systems;

[0007] Determine a first fusion feature sequence based on the multi-source fault feature data and weights corresponding to the multi-source fault feature data;

[0008] Determine a second fusion feature sequence within a preset time length, where the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence;

[0009] Inputting the second fused feature sequence into a plurality of classifiers respectively to obtain a plurality of classification results of vehicle fault types;

[0010] Based on multiple classification results, the fault type of the vehicle is identified.

[0011] In one embodiment, obtaining multi-source fault feature data of a vehicle includes:

[0012] Collect multi-source raw data of vehicles;

[0013] Preprocessing various multi-source raw data to obtain processed multi-source data;

[0014] Feature extraction is performed on the processed multi-source data to obtain multi-source fault feature data including time domain features and frequency domain features.

[0015] In one embodiment, obtaining multi-source fault feature data of a vehicle further includes:

[0016] Based on multi-source feature data including time domain features and frequency domain features, a generative adversarial network model is used to generate sample data with the same features as the multi-source fault feature data;

[0017] The sample data is used to train the generative adversarial network model, and the trained generative adversarial network model is used to generate multi-source fault feature data having the same features as the multi-source fault feature data.

[0018] In one embodiment, a plurality of multi-source raw data are preprocessed to obtain processed multi-source data, including:

[0019] Determine the mean and standard deviation of data from multiple sources;

[0020] Determine the normalized multi-source data based on the mean and standard deviation;

[0021] The normalized multi-source data is used as the processed multi-source data.

[0022] In one embodiment, determining the mean and standard deviation of the multi-source data;

[0023] Based on the mean and standard deviation, determine whether the multi-source data is abnormal data;

[0024] If the multi-source data is abnormal data, the average value of the adjacent data of the multi-source data is used as the processed multi-source data.

[0025] In one embodiment, a plurality of multi-source raw data are preprocessed to obtain processed multi-source data, including:

[0026] Logarithmic transformation of multi-source data.

[0027] In one embodiment, determining a second fusion feature sequence within a preset time length includes:

[0028] Get the sampling frequency within the preset time length;

[0029] According to the preset time length and sampling frequency, determine the number of data within the preset time length;

[0030] Based on the dimension of the first fused feature sequence and the number of data within a preset time length, a second fused feature sequence is constructed.

[0031] In one embodiment, the classification result includes the fault category of the vehicle and the probability of the fault category; based on the multiple classification results, identifying the fault type of the vehicle includes:

[0032] Based on the fault category probabilities, determining the fusion probabilities of the fault categories;

[0033] If the fusion probability is higher than a preset threshold, the fault type is determined to be the fault type of the vehicle.

[0034] According to a second aspect of the present application, a vehicle fault identification device is provided, the device comprising:

[0035] An acquisition unit, used to acquire multi-source fault characteristic data of the vehicle and weights corresponding to the multi-source fault characteristic data; the multi-source fault characteristic data includes fault characteristic data corresponding to sensors, on-board diagnostic systems, and vehicle communication systems;

[0036] A first determining unit, configured to determine a first fusion feature sequence based on multi-source fault feature data and weights corresponding to the multi-source fault feature data;

[0037] A second determining unit is used to determine a second fusion feature sequence within a preset time length, where the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence;

[0038] A classification unit, used for inputting the second fusion feature sequence into a plurality of classifiers respectively, and obtaining a plurality of classification results accordingly;

[0039] The identification unit is used to identify the fault type of the vehicle based on multiple classification results.

[0040] According to a third aspect of the present application, there is provided an electronic device, including a memory and a processor;

[0041] The memory is connected to the processor and is used for storing programs;

[0042] The processor is used to implement the vehicle fault identification method provided in the first aspect or any one embodiment of the first aspect by running the program in the memory.

[0043] According to a fourth aspect of the present application, a vehicle is provided, the vehicle comprising the electronic device provided in the third aspect.

[0044] According to the fifth aspect of the present application, a chip is provided, the chip including a processor and a data interface, the processor reads and runs the program stored in the memory through the data interface to execute the vehicle fault identification method provided in the first aspect or any one embodiment of the first aspect.

[0045] According to the sixth aspect of the present application, a storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the vehicle fault identification method provided in the first aspect or any one embodiment of the first aspect is implemented.

[0046] The present application provides a vehicle fault identification method, device, electronic device, vehicle, chip and medium, which obtains multi-source fault feature data of the vehicle and the weights corresponding to the multi-source fault feature data; determines a first fusion feature sequence based on the multi-source fault feature data and the weights corresponding to the multi-source fault feature data; determines a second fusion feature sequence within a preset time length, the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence; inputs the second fusion feature sequence into multiple classifiers respectively, and obtains multiple classification results; identifies the fault type of the vehicle based on the multiple classification results. The present application can more comprehensively and accurately reflect the fault status of the vehicle by fusing multi-source fault data and making full use of the complementarity of different sensor data, avoiding the incomplete diagnosis caused by a single sensor. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0048] Figure 1 A schematic diagram of an implementation environment provided for an embodiment of the present application;

[0049] Figure 2 A flow chart of a vehicle fault identification method provided in an embodiment of the present application;

[0050] Figure 3 A structural block diagram of a vehicle fault identification device provided in an embodiment of the present application;

[0051] Figure 4 A structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0053] With the continuous development of automobile technology, vehicles are becoming more and more intelligent, and vehicle fault diagnosis is becoming more and more important. Traditional vehicle fault diagnosis methods mainly rely on manual experience and single sensor data, with low diagnostic accuracy and efficiency. In recent years, deep learning technology has achieved great success in image recognition, speech processing and other fields, providing new ideas for vehicle fault diagnosis. However, most of the current vehicle fault diagnosis methods based on deep learning only use single sensor data, resulting in inaccurate and incomplete diagnostic results.

[0054] The present application provides a vehicle fault identification method, device, electronic device, vehicle, chip and medium, which obtains multi-source fault feature data of the vehicle and the weights corresponding to the multi-source fault feature data; determines a first fusion feature sequence based on the multi-source fault feature data and the weights corresponding to the multi-source fault feature data; determines a second fusion feature sequence within a preset time length, the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence; inputs the second fusion feature sequence into multiple classifiers respectively, and obtains multiple classification results; identifies the fault type of the vehicle based on the multiple classification results. The present application can more comprehensively and accurately reflect the fault status of the vehicle by fusing multi-source fault data and making full use of the complementarity of different sensor data, avoiding the incomplete diagnosis caused by a single sensor.

[0055] Exemplary Implementation Environment

[0056] Please refer to Figure 1 , Figure 1 It is a schematic diagram of an implementation environment involved in the present invention.

[0057] like Figure 1As shown, the application scenario involves server 1 and vehicle 2. Vehicle 2 can be equipped with VCU (Vehicle Control Unit, referred to as VCU), which is responsible for integrating and processing information from various sensors of vehicle 2, such as engine speed, oil temperature, oil pressure, vehicle speed, acceleration, vibration signal, sound signal, etc., wherein the vibration signal may include: engine vibration, transmission vibration, drive shaft vibration, wheel vibration, spring vibration of suspension system, shock absorber vibration, etc.; sound signal may include various sound signals emitted when the engine is running, such as: sound signals of scheduling systems such as exhaust pipes and mufflers, and sound signals emitted by equipment such as air-conditioning compressors and generators in the car when working. Vehicle 2 can also read various sensor data of vehicle 2 through the OBD-II interface. Vehicle 2 can also be equipped with TBOX (Telematics Box, Internet of Vehicles System, referred to as TBOX), which collects communication data of vehicle 2, including interaction information with surrounding vehicles, road condition data, traffic signal data, etc. After collecting multi-source data, the vehicle 2 may send the data to the server 1 , so that the server 1 processes the multi-source data to determine whether the vehicle 2 has a fault and the type of the fault.

[0058] Server 1 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms. The server can also become a node of the blockchain.

[0059] The server 1 may be one or more servers. When there are multiple servers 1, there are at least two servers for providing different services, and / or there are at least two servers for providing the same service, such as providing the same service in a load balancing manner, which is not limited in the embodiment of the present invention.

[0060] It should be understood that Figure 1 This is only an exemplary description and does not specifically limit the application scenarios of the embodiments of the present application. Figure 1 One vehicle and one server are shown as examples, but other numbers of vehicles and servers may actually be included, and this application does not impose any limitation on this.

[0061] Exemplary Methods

[0062] Figure 2 This is a flow chart of the vehicle fault identification method provided in the embodiment of the present application. Figure 2In an exemplary embodiment, a vehicle fault identification method is provided, and the method may include:

[0063] S202: Acquire multi-source fault feature data of the vehicle and weights corresponding to the multi-source fault feature data.

[0064] Multi-source fault characteristic data may include fault characteristic data corresponding to sensors, on-board diagnostic systems (OBD) and vehicle communication systems; wherein sensor data may include but is not limited to engine speed, oil temperature, oil pressure, vehicle speed, acceleration, vibration signals, sound signals, temperature signals, etc. The OBD system can help technicians and car owners identify and solve vehicle problems and ensure the normal operation of the vehicle. Modern vehicles usually read engine-related data, emission-related data, vehicle status data, fault codes and other data through the OBD-II interface. The vehicle communication system can use vehicle network technology to collect vehicle communication data, including interaction information with surrounding vehicles, road condition data, traffic signal data, etc.

[0065] S204: Determine a first fusion feature sequence based on multi-source fault feature data and weights corresponding to the multi-source fault feature data.

[0066] In practical applications, the corresponding weights of multi-source fault feature data are determined based on experience and the reliability or importance of different data sources. For example: suppose that after analysis and experimental verification, it is found that the vibration sensor data has a higher accuracy for engine mechanical fault diagnosis, and a weight of 0.5 is assigned; the temperature sensor data is relatively less important, and a weight of 0.3 is assigned; the sound sensor data is second in importance, and a weight of 0.2 is assigned. For the three modal data collected at the same time, their corresponding feature vectors are weighted averaged. For example, at a certain time t, the feature vector of the vibration sensor data is V t , the characteristic vector of the temperature sensor data is T t , the feature vector of the sound sensor data is S t , the fused feature vector is calculated as F t =0.5+0.3T t +0.2S t ; Such a weighted average operation is performed at each moment in the entire acquisition time period to obtain the first fusion feature sequence.

[0067] S206: Determine a second fusion feature sequence within a preset time length, where the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence.

[0068] By constructing a feature matrix based on the first fused feature sequence within a preset time period, the state change of the vehicle during operation can be reflected because the matrix contains comprehensive information at different times.

[0069] S208: Input the second fused feature sequence into a plurality of classifiers respectively to obtain a plurality of classification results of vehicle fault types.

[0070] In practical applications, multiple classifiers can be used to identify vehicle faults. The classifier learns the characteristic patterns corresponding to different fault types based on the training data, and then classifies the input features to determine whether the engine has a fault and the possible fault type.

[0071] S210: Identify the fault type of the vehicle based on the multiple classification results.

[0072] In practical applications, the fault category probabilities output by different classifiers can be averaged to obtain the final fused probability distribution, and the final fault diagnosis result can be determined based on this probability distribution. For example, if the probability that the neural network classifier determines that the engine fault is type A is 0.5, and the probability that the support vector machine classifier determines that it is type A is 0.6, then the fusion probability is (0.5+0.6) / 2=0.55. According to the set threshold (such as 0.5), if 0.55>0.5, then the final diagnosis is that the engine has fault type A.

[0073] By obtaining multi-source fault feature data of the vehicle and the weights corresponding to the multi-source fault feature data; determining a first fusion feature sequence based on the multi-source fault feature data and the weights corresponding to the multi-source fault feature data; determining a second fusion feature sequence within a preset time length, the second fusion feature sequence being a feature matrix constructed based on the first fusion feature sequence; inputting the second fusion feature sequence into multiple classifiers respectively, and obtaining multiple classification results accordingly; identifying the fault type of the vehicle based on the multiple classification results. This application can more comprehensively and accurately reflect the fault status of the vehicle by fusing multi-source fault data and making full use of the complementarity of different sensor data, avoiding the incomplete diagnosis caused by a single sensor.

[0074] In one embodiment, obtaining multi-source fault feature data of a vehicle includes:

[0075] Collect multi-source raw data of vehicles;

[0076] Preprocessing various multi-source raw data to obtain processed multi-source data;

[0077] Feature extraction is performed on the processed multi-source data to obtain multi-source fault feature data including time domain features and frequency domain features.

[0078] The preprocessing of multi-source raw data can include operations such as data cleaning, denoising, and normalization to improve the quality and reliability of the data.

[0079] In practical applications, when extracting features from processed multi-source data, we can first use time domain feature extraction to preliminarily determine whether the vehicle has a fault and the type of fault, and then use frequency domain feature extraction to obtain the amplitude distribution at different frequencies to determine whether the vehicle has a fault at a specific frequency.

[0080] Taking engine failure as an example, feature extraction of multi-source data is explained. For example, the mean, variance, root mean square value and other time domain characteristics of the engine's vibration signal are found by calculation, and its changing trend is observed. If the mean of the vibration signal gradually deviates from the normal range within a certain period of time, the variance and root mean square value increase significantly, and the vibration waveform shows the above-mentioned periodic and harmonic characteristics, it can be preliminarily determined that the engine has an unbalanced fault. Possible causes include crankshaft imbalance, fan blade damage or improper installation, flywheel imbalance, etc.; then the frequency spectrum of the vibration signal is obtained by combining fast Fourier transform analysis. If characteristic amplitude peaks and energy concentration phenomena appear, it can be further confirmed that the engine has an unbalanced fault.

[0081] In one embodiment, obtaining multi-source fault feature data of a vehicle further includes:

[0082] Based on multi-source feature data including time domain features and frequency domain features, a generative adversarial network model is used to generate sample data with the same features as the multi-source fault feature data;

[0083] The sample data is used to train the generative adversarial network model, and the trained generative adversarial network model is used to generate multi-source fault feature data having the same features as the multi-source fault feature data.

[0084] Since there is less fault feature data in practice, this embodiment uses generative adversarial networks (GAN) to generate more multi-source fault data.

[0085] GAN generates realistic data samples through adversarial training between two neural networks (generator and discriminator). The task of the generator is to generate realistic data samples from random noise. The goal of the generator is to generate data samples that can deceive the discriminator into mistaking them for real data. The task of the discriminator is to distinguish between real data and fake data generated by the generator. The goal of the discriminator is to maximize its ability to correctly classify real data and fake data.

[0086] During the training process, multi-source feature data containing time domain features and frequency domain features are input into the GAN model for training. For example, for vibration feature vectors, the generator attempts to generate vectors similar to the real vibration fault features, and the discriminator continuously learns to distinguish between real and generated vibration features. Similarly, similar training is performed on other feature vectors such as temperature and sound. After multiple rounds of training, the generator is able to learn the intrinsic feature distribution of different modal data, thereby generating more representative feature vectors. For example, for vibration data, the generator may generate feature vectors containing more obvious fault feature patterns, which can better reflect the vibration characteristics of the engine under different fault conditions.

[0087] In one embodiment, a plurality of multi-source raw data are preprocessed to obtain processed multi-source data, including:

[0088] Determine the mean and standard deviation of data from multiple sources;

[0089] Determine the normalized multi-source data based on the mean and standard deviation;

[0090] The normalized multi-source data is used as the processed multi-source data.

[0091] In actual use, the Z-score standardization method can be used to normalize the data with different characteristics to the same scale. The normalization is explained by taking the engine speed as an example.

[0092] First, the mean value μ of the engine speed characteristic is obtained by the above statistical method 转速 , the standard deviation of the engine speed characteristic σ 转速 ; Secondly, perform Z-score normalization: for each value x in the engine speed column i,转速 , using the formula Calculate the normalized rotation speed data.

[0093] In one embodiment, a plurality of multi-source raw data are preprocessed to obtain processed multi-source data, including:

[0094] Determine the mean and standard deviation of data from multiple sources;

[0095] Based on the mean and standard deviation, determine whether the multi-source data is abnormal data;

[0096] If the multi-source data is abnormal data, the average value of the adjacent data of the multi-source data is used as the processed multi-source data.

[0097] Assume that the dataset of multi-source data is: X = {x1, x2, ..., x n},

[0098] First calculate the mean Standard Deviation

[0099] Secondly, set a threshold and detect outliers. Usually, a threshold can be set, such as k times the standard deviation, for example: k is 3. For each data point x in the data set i , if |x i -μ|>kσ, it is considered an outlier. For example, for data collected by a temperature sensor, if its mean is 27°C and its standard deviation is 3°C, then any data point greater than 36°C or less than 18°C ​​may be considered an outlier.

[0100] If the data point x i is judged as an outlier if x i-1 and x i+1 is its adjacent normal data point, then x i-1 and x i+1 The average value of x i The interpolation result is

[0101] In one embodiment, a plurality of multi-source raw data are preprocessed to obtain processed multi-source data, including:

[0102] Logarithmic transformation of multi-source data.

[0103] Since the amplitude range of the actual measured data signal is very large, the logarithmic transformation can compress the larger numerical range into an interval that is easier to process and visualize, highlighting the details of smaller signal changes while reducing the impact of large signal changes on the overall analysis.

[0104] In one embodiment, determining a second fusion feature sequence within a preset time length includes:

[0105] Get the sampling frequency within the preset time length;

[0106] According to the preset time length and sampling frequency, determine the number of data within the preset time length;

[0107] Based on the dimension of the first fused feature sequence and the number of data within a preset time length, a second fused feature sequence is constructed.

[0108] In practical applications, assuming that the preset duration is t2-t1, that is, considering the data from time t1 to time t2, assuming the data sampling frequency f, calculate the number of data in the preset duration N = (t2-t1) * f, and arrange the first fused feature sequence in chronological order to form a feature matrix. If the feature vector dimension of the first fused feature sequence is D, then the dimension of the constructed feature matrix is ​​N*D. Taking simple splicing fusion as an example, assuming that there are N time points in the time range [t1, t2], the dimension of the fused feature vector obtained by simple splicing is D, and the feature matrix is ​​constructed through the following pseudo code:

[0109] feature_matrix = []

[0110] for t in range(N):

[0111] fused_vector=fusion_function(t)

[0112] feature_matrix.append(fused_vector)

[0113] feature_matrix=np.array(feature_matrix)

[0114] Among them, fusion_function is a function that performs the fusion operation and returns the fused feature vector, which is the second fused feature sequence.

[0115] In practical applications, the second fused feature sequence can be further extracted. For example, the feature dimension can be reduced by using methods such as principal component analysis to extract the main feature components while retaining as much useful information as possible.

[0116] In one embodiment, the classification result includes the fault category of the vehicle and the probability of the fault category; based on the multiple classification results, identifying the fault type of the vehicle includes:

[0117] Based on the fault category probabilities, determining the fusion probabilities of the fault categories;

[0118] If the fusion probability is higher than a preset threshold, the fault type is determined to be the fault type of the vehicle.

[0119] In practical applications, the fault category probabilities output by different classifiers can be averaged to obtain the fusion probability of the fault category, and the final fault diagnosis result can be determined based on the fusion probability of the fault category. When the fusion probability is higher than the preset threshold, the fault type can be determined to be the fault type of the vehicle. For example, if the probability that the neural network classifier determines that the engine fault is type A is 0.5, and the probability that the support vector machine classifier determines that it is type A is 0.6, then the fusion probability is (0.5+0.6) / 2=0.55. According to the set threshold (such as 0.5), if 0.55>0.5, the final diagnosis is that the engine has fault type A.

[0120] Exemplary Devices

[0121] Accordingly, the embodiment of the present application also provides a device, Figure 3 This is a structural block diagram of a vehicle fault identification device provided in an embodiment of the present application. Figure 3 As shown, the apparatus may include:

[0122] An acquisition unit 301 is used to acquire multi-source fault characteristic data of a vehicle and weights corresponding to the multi-source fault characteristic data; the multi-source fault characteristic data includes fault characteristic data corresponding to sensors, on-board diagnostic systems, and vehicle communication systems;

[0123] A first determining unit 303 is used to determine a first fusion feature sequence based on multi-source fault feature data and weights corresponding to the multi-source fault feature data;

[0124] The second determining unit 305 is used to determine a second fusion feature sequence within a preset time length, where the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence;

[0125] The classification unit 307 is used to input the second fusion feature sequence into multiple classifiers respectively to obtain multiple classification results;

[0126] The identification unit 309 is used to identify the fault type of the vehicle based on multiple classification results.

[0127] The vehicle fault identification device provided in this embodiment belongs to the same application concept as the vehicle fault identification method provided in the above embodiments of this application, and can execute the vehicle fault identification method provided in any of the above embodiments of this application, and has the corresponding functional modules and beneficial effects of executing the vehicle fault identification method. For technical details not fully described in this embodiment, please refer to the specific processing content of the vehicle fault identification method provided in the above embodiments of this application, and will not be repeated here.

[0128] The functions implemented by the above first determination unit 303, the second determination unit 305, the classification unit 307 and the identification unit 309 may be implemented by the same or different processors respectively, which is not limited in the embodiment of the present application.

[0129] It should be understood that the first determination unit 303, the second determination unit 305, the classification unit 307 and the identification unit 309 in the above device can be implemented in the form of a processor calling software. For example, the device includes a processor, the processor is connected to a memory, and instructions are stored in the memory. The processor calls the instructions stored in the memory to implement any of the above methods or realize the functions of each unit of the device, wherein the processor can be a general-purpose processor, such as a CPU or a microprocessor, etc., and the memory can be a memory in the device or a memory outside the device. Alternatively, the unit in the device can be implemented in the form of a hardware circuit, and the functions of some or all of the units can be realized by designing the hardware circuit. The hardware circuit can be understood as one or more processors; for example, in one implementation, the hardware circuit is an ASIC, and the functions of some or all of the above units are realized by designing the logical relationship of the components in the circuit; for another example, in another implementation, the hardware circuit can be implemented by PLD. Taking FPGA as an example, it can include a large number of logic gate circuits, and the connection relationship between the logic gate circuits is configured through the configuration file, so as to realize the functions of some or all of the above units. All units of the above device may be implemented entirely in the form of a processor calling software, or entirely in the form of a hardware circuit, or partially in the form of a processor calling software and the rest in the form of a hardware circuit.

[0130] In an embodiment of the present application, a processor is a circuit with the ability to process signals. In one implementation, the processor may be a circuit with the ability to read and run instructions, such as a CPU, a microprocessor, a GPU, or a DSP; in another implementation, the processor may implement certain functions through the logical relationship of a hardware circuit, and the logical relationship of the hardware circuit is fixed or reconfigurable, such as a hardware circuit implemented by an ASIC or PLD, such as an FPGA. In a reconfigurable hardware circuit, the process of the processor loading a configuration document to implement the hardware circuit configuration can be understood as the process of the processor loading instructions to implement the functions of some or all of the above units. In addition, it can also be a hardware circuit designed for artificial intelligence, which can be understood as an ASIC, such as an NPU, TPU, DPU, etc.

[0131] It can be seen that each unit in the above device can be one or more processors (or processing circuits) configured to implement the above method, such as: CPU, GPU, NPU, TPU, DPU, microprocessor, DSP, ASIC, FPGA, or a combination of at least two of these processor forms.

[0132] In addition, all or part of the units in the above device can be integrated together, or can be implemented independently. In one implementation, these units are integrated together and implemented in the form of a SOC. The SOC may include at least one processor for implementing any of the above methods or implementing the functions of each unit of the device. The type of the at least one processor may be different, for example, including a CPU and an FPGA, a CPU and an artificial intelligence processor, a CPU and a GPU, etc.

[0133] Exemplary Electronic Devices

[0134] Another embodiment of the present application also provides an electronic device, see Figure 4 As shown, the device includes:

[0135] Memory 400 and processor 410;

[0136] The memory 400 is connected to the processor 410 and is used to store programs;

[0137] The processor 410 is used to implement the vehicle fault identification method disclosed in any of the above embodiments by running the program stored in the memory 400.

[0138] Specifically, the electronic device may further include: a bus, a communication interface 420 , an input device 430 and an output device 440 .

[0139] The processor 410, the memory 400, the communication interface 420, the input device 430 and the output device 440 are connected to each other via a bus.

[0140] A bus may include a pathway that transfers information between components of a computer system.

[0141] Processor 410 may be a general purpose processor, such as a general purpose central processing unit (CPU), a microprocessor, etc., or an application-specific integrated circuit (ASIC), or one or more integrated circuits for controlling the execution of the program of the scheme of the present invention. It may also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0142] The processor 410 may include a main processor, and may also include a baseband chip, a modem, and the like.

[0143] The memory 400 stores a program for executing the technical solution of the present invention, and may also store an operating system and other key services. Specifically, the program may include a program code, and the program code includes a computer operation instruction. More specifically, the memory 400 may include a read-only memory (ROM), other types of static storage devices that can store static information and instructions, a random access memory (RAM), other types of dynamic storage devices that can store information and instructions, a disk storage, a flash, and the like.

[0144] The input device 430 may include a device for receiving data and information input by a user, such as a keyboard, a mouse, a camera, a scanner, a light pen, a voice input device, a touch screen, a pedometer, or a gravity sensor.

[0145] Output device 440 may include a device that allows information to be output to a user, such as a display screen, a printer, a speaker, etc.

[0146] The communication interface 420 may include any transceiver or the like to communicate with other devices or communication networks, such as Ethernet, a radio access network (RAN), a wireless local area network (WLAN), etc.

[0147] The processor 410 executes the program stored in the memory 400 and calls other devices, which can be used to implement each step of vehicle fault identification provided in any of the above embodiments of the present application.

[0148] An embodiment of the present application also provides a vehicle, which includes the above-mentioned electronic device.

[0149] An embodiment of the present application also proposes a chip, which includes a processor and a data interface. The processor reads and runs a program stored in a memory through the data interface to execute the vehicle fault identification method introduced in any of the above embodiments. The specific processing process and its beneficial effects can be found in the introduction to the embodiment of the above-mentioned vehicle fault identification method.

[0150] Exemplary computer program products and storage media

[0151] In addition to the above-mentioned methods and devices, an embodiment of the present application may also be a computer program product, which includes computer program instructions, which, when executed by a processor, enable the processor to execute the steps of the vehicle fault identification method according to various embodiments of the present application described in any of the above embodiments of this specification.

[0152] The computer program product may be written in any combination of one or more programming languages ​​to write program codes for performing the operations of the embodiments of the present application, including object-oriented programming languages, such as Java, C++, etc., and conventional procedural programming languages, such as "C" language or similar programming languages. The program code may be executed entirely on the user computing device, partially on the user device, as an independent software package, partially on the user computing device and partially on a remote computing device, or entirely on a remote computing device or server.

[0153] In addition, the embodiment of the present application may also be a storage medium on which a computer program is stored. The computer program is executed by a processor to execute the steps of the vehicle fault identification method according to various embodiments of the present application described in any of the above embodiments of this specification, and specifically the following steps may be implemented:

[0154] S202: Acquire multi-source fault feature data of the vehicle and weights corresponding to the multi-source fault feature data.

[0155] S204: Determine a first fusion feature sequence based on multi-source fault feature data and weights corresponding to the multi-source fault feature data.

[0156] S206: Determine a second fusion feature sequence within a preset time length, where the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence.

[0157] S208: Input the second fused feature sequence into a plurality of classifiers respectively to obtain a plurality of classification results of vehicle fault types.

[0158] S210: Identify the fault type of the vehicle based on the multiple classification results.

[0159] For the aforementioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the order of the actions described, because according to the present application, some steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0160] It should be noted that each embodiment in this specification is described in a progressive manner, and each embodiment focuses on the differences from other embodiments, and the same or similar parts between the embodiments can be referred to each other. For the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0161] The steps in the methods of each embodiment of the present application can be adjusted in order, combined and deleted according to actual needs, and the technical features recorded in each embodiment can be replaced or combined.

[0162] The modules and sub-modules in the devices and terminals of the various embodiments of the present application can be combined, divided and deleted according to actual needs.

[0163] In the several embodiments provided in the present application, it should be understood that the disclosed terminals, devices and methods can be implemented in other ways. For example, the terminal embodiments described above are only schematic, for example, the division of modules or submodules is only a logical function division, and there may be other division methods in actual implementation, for example, multiple submodules or modules can be combined or integrated into another module, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or modules, which can be electrical, mechanical or other forms.

[0164] The modules or submodules described as separate components may or may not be physically separated, and the components of the modules or submodules may or may not be physical modules or submodules, that is, they may be located in one place, or they may be distributed on multiple network modules or submodules. Some or all of the modules or submodules may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0165] In addition, each functional module or submodule in each embodiment of the present application may be integrated into one processing module, or each module or submodule may exist physically separately, or two or more modules or submodules may be integrated into one module. The above-mentioned integrated modules or submodules may be implemented in the form of hardware or in the form of software functional modules or submodules.

[0166] Professionals may further appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of the two. In order to clearly illustrate the interchangeability of hardware and software, the composition and steps of each example have been generally described in the above description according to function. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professionals and technicians may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0167] The steps of the method or algorithm described in conjunction with the embodiments disclosed herein may be implemented directly by hardware, software units executed by a processor, or a combination of the two. The software units may be placed in a random access memory (RAM), a memory, a read-only memory (ROM), an electrically programmable ROM, an electrically erasable programmable ROM, a register, a hard disk, a removable disk, a CD-ROM, or any other form of storage medium known in the art.

[0168] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0169] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A vehicle fault identification method, characterized in that: include: Obtaining multi-source fault feature data of a vehicle and weights corresponding to the multi-source fault feature data; The multi-source fault characteristic data includes fault characteristic data corresponding to sensors, on-board diagnostic systems, and vehicle communication systems; Determining a first fusion feature sequence based on the multi-source fault feature data and weights corresponding to the multi-source fault feature data; Determine a second fusion feature sequence within a preset time length, where the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence; Inputting the second fused feature sequence into a plurality of classifiers respectively to obtain a plurality of classification results of vehicle fault types; Based on the plurality of classification results, a fault type of the vehicle is identified.

2. The vehicle fault identification method according to claim 1, characterized in that: The obtaining of multi-source fault feature data of the vehicle includes: Collecting multi-source raw data of the vehicle; Preprocessing the plurality of multi-source original data to obtain processed multi-source data; Feature extraction is performed on the processed multi-source data to obtain multi-source fault feature data including time domain features and frequency domain features.

3. The vehicle fault identification method according to claim 2, characterized in that: The acquiring of multi-source fault feature data of the vehicle further includes: Based on the multi-source feature data including time domain features and frequency domain features, using a generative adversarial network model to generate sample data having the same features as the multi-source fault feature data; The generative adversarial network model is trained using the sample data, and the trained generative adversarial network model is used to generate multi-source fault feature data having the same features as the multi-source fault feature data.

4. The vehicle fault identification method according to claim 2, characterized in that: The preprocessing of the plurality of multi-source original data to obtain processed multi-source data includes: Determining the mean and standard deviation of the multi-source data; Based on the mean and the standard deviation, determine the normalized multi-source data; The normalized multi-source data is used as processed multi-source data.

5. The vehicle fault identification method according to claim 2, characterized in that: The preprocessing of the plurality of multi-source original data to obtain processed multi-source data includes: Determining the mean and standard deviation of the multi-source data; Based on the mean and the standard deviation, determining whether the multi-source data is abnormal data; If the multi-source data is abnormal data, the average value of adjacent data of the multi-source data is used as the processed multi-source data.

6. The vehicle fault identification method according to claim 2, characterized in that: The preprocessing of the plurality of multi-source original data to obtain processed multi-source data includes: The multi-source data are logarithmically transformed.

7. The vehicle fault identification method according to claim 1, characterized in that: The determining of the second fusion feature sequence within the preset time length includes: Get the sampling frequency within the preset time length; Determining the number of data within the preset time length according to the preset time length and the sampling frequency; The second fused feature sequence is constructed based on the dimension of the first fused feature sequence and the number of data within the preset time length.

8. The vehicle fault identification method according to claim 1, characterized in that: The classification result includes the fault category of the vehicle and the probability of the fault category; The step of identifying the fault type of the vehicle based on the plurality of classification results comprises: Based on the fault category probabilities, determining fusion probabilities of the fault categories; If the fusion probability is higher than a preset threshold, the fault type is determined to be the fault type of the vehicle.

9. A vehicle fault identification device, characterized in that: include: An acquisition unit, used to acquire multi-source fault feature data of a vehicle and weights corresponding to the multi-source fault feature data; The multi-source fault characteristic data includes fault characteristic data corresponding to sensors, on-board diagnostic systems, and vehicle communication systems; A first determining unit, configured to determine a first fusion feature sequence based on the multi-source fault feature data and weights corresponding to the multi-source fault feature data; A second determining unit is used to determine a second fusion feature sequence within a preset time length, where the second fusion feature sequence is a feature matrix constructed based on the first fusion feature sequence; A classification unit, used for inputting the second fusion feature sequence into a plurality of classifiers respectively, and obtaining a plurality of classification results accordingly; An identification unit is used to identify the fault type of the vehicle based on the multiple classification results.

10. An electronic device, characterized in that: including memory and processor; The memory is connected to the processor and is used to store programs; The processor is used to implement the vehicle fault identification method as described in any one of claims 1 to 8 by running the program in the memory.

11. A vehicle, characterized in that: A vehicle comprises the electronic device according to claim 10.

12. A chip, characterized in that: It comprises a processor and a data interface, wherein the processor reads and runs a program stored in a memory through the data interface to execute the vehicle fault identification method as claimed in any one of claims 1 to 8.

13. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the vehicle fault identification method according to any one of claims 1 to 8 is implemented.

Images