A vehicle fault diagnosis method and system

Abstract

This invention provides a vehicle fault diagnosis method and system. The method includes: during normal vehicle operation, collecting vehicle driving parameters in real time through preset sensors and generating a corresponding driving dataset based on the driving parameters; when a fault signal is detected in real time, parsing the fault signal to extract the fault parameters contained in the fault signal in real time; inputting both the driving dataset and the fault parameters into a preset edge server, and training a fault diagnosis model corresponding to the vehicle using the preset edge server based on the driving dataset and the fault parameters; detecting the fault code corresponding to the fault signal in real time, and identifying the fault type corresponding to the vehicle based on the fault code using the fault diagnosis model. This invention can identify vehicle fault types in a timely and effective manner, thereby improving diagnostic efficiency.

Description

Technical Field

[0001] This invention relates to the field of automotive technology, and in particular to a vehicle fault diagnosis method and system. Background Technology

[0002] In the process of diagnosing automotive faults, most existing technologies rely on instrument-based diagnostic methods. Specifically, this involves using existing computers and sensors to diagnose automotive faults. However, this method is entirely dependent on existing diagnostic equipment, which is susceptible to environmental factors and operator error during the diagnostic process, thus reducing the efficiency of automotive fault diagnosis. Summary of the Invention

[0003] Based on this, the purpose of the present invention is to provide a vehicle fault diagnosis method and system to solve the problem that the fault diagnosis methods of the prior art are easily affected by the environment and the operation of the personnel, which reduces the efficiency of vehicle fault diagnosis.

[0004] The first aspect of the present invention proposes:

[0005] A vehicle fault diagnosis method, wherein the method includes:

[0006] During normal vehicle operation, the vehicle's driving parameters are collected in real time by preset sensors, and a corresponding driving dataset is generated based on the driving parameters.

[0007] When a fault signal is detected in the vehicle in real time, the fault signal is analyzed and processed to extract the fault parameters contained in the fault signal in real time.

[0008] The driving dataset and the fault parameters are both input into a preset edge server, and a fault diagnosis model corresponding to the vehicle is trained by the preset edge server based on the driving dataset and the fault parameters.

[0009] The fault code corresponding to the fault signal is detected in real time, and the fault diagnosis model identifies the fault type corresponding to the vehicle based on the fault code.

[0010] The beneficial effects of this invention are: by collecting driving parameters of the vehicle in normal condition and fault parameters in fault condition in real time, the current working status of the vehicle can be obtained in all aspects. Based on this, the required fault diagnosis model can be further trained by a preset edge server. Furthermore, the fault diagnosis model can be used to identify the fault type of the current vehicle in a timely and effective manner, thereby improving the diagnostic efficiency.

[0011] Furthermore, the step of training a fault diagnosis model corresponding to the vehicle using a preset edge server based on the driving dataset and the fault parameters includes:

[0012] When the driving dataset and the fault parameters are obtained respectively, a first weight is added to the driving dataset and a second weight is added to the fault parameters, and the sum of the first weight and the second weight is 1.

[0013] According to the first weight, the corresponding first data subset is extracted in real time from the driving dataset, and according to the second weight, the corresponding second data subset is extracted in real time from the fault parameters;

[0014] A fault diagnosis model corresponding to the vehicle is trained based on the first data subset and the second data subset.

[0015] Furthermore, the step of training a fault diagnosis model corresponding to the vehicle based on the first data subset and the second data subset includes:

[0016] When the first data subset and the second data subset are obtained respectively, the first data subset and the second data subset are fused to generate the corresponding target dataset;

[0017] The target dataset is divided into corresponding training and test sets, and the training and test sets are input into the preset edge server to train a fault diagnosis model corresponding to the vehicle.

[0018] Furthermore, the step of inputting the training set and the test set into the preset edge server to train a fault diagnosis model corresponding to the vehicle includes:

[0019] When the training set and the test set are obtained respectively, the corresponding initial convolutional neural network is retrieved from the preset edge server.

[0020] The training set is converted into a corresponding feature sequence by a preset DTW algorithm, and the initial convolutional neural network is trained using the feature sequence to generate a corresponding intermediate convolutional neural network.

[0021] The intermediate convolutional neural network is tested using the test set to generate the corresponding fault diagnosis model.

[0022] Furthermore, the step of training the initial convolutional neural network using the feature sequence to generate a corresponding intermediate convolutional neural network includes:

[0023] When the feature sequence is acquired in real time, several feature values ​​contained in the feature sequence are extracted in real time, and each feature value is unique.

[0024] The network distribution map corresponding to the initial convolutional neural network is detected in real time, and several network nodes contained in the network distribution map are detected in real time.

[0025] The intermediate convolutional neural network is trained based on several of the aforementioned feature values ​​and several of the aforementioned network nodes.

[0026] Furthermore, the step of training the intermediate convolutional neural network based on the plurality of feature values ​​and the plurality of network node correspondences includes:

[0027] For each of the aforementioned feature values, a corresponding first identifier is added sequentially, and for each of the aforementioned network nodes, a corresponding second identifier is added sequentially.

[0028] The mapping relationship between the first identifier and the second identifier is constructed one by one, and the initial network parameters contained in each network node are detected in real time.

[0029] Based on the mapping relationship, each of the initial network parameters is sequentially replaced with each of the feature values ​​to train the intermediate convolutional neural network accordingly.

[0030] Furthermore, the step of identifying the fault type corresponding to the vehicle based on the fault code using the fault diagnosis model includes:

[0031] When the fault code is acquired in real time, the fault sequence corresponding to the fault code is detected in real time.

[0032] The fault values ​​contained in the fault sequence are detected in real time, and the fault values ​​are input into the internal part of the fault diagnosis model to identify the fault type corresponding to the vehicle.

[0033] The second aspect of the present invention proposes:

[0034] A vehicle fault diagnosis system, wherein the system includes:

[0035] The data acquisition module is used to collect the vehicle's driving parameters in real time through preset sensors during normal vehicle operation, and generate a corresponding driving dataset based on the driving parameters.

[0036] The parsing module is used to parse the fault signal when a fault signal is detected in the vehicle in real time, so as to extract the fault parameters contained in the fault signal in real time.

[0037] The training module is used to input the driving dataset and the fault parameters into a preset edge server, and train a fault diagnosis model corresponding to the vehicle based on the driving dataset and the fault parameters through the preset edge server.

[0038] The execution module is used to detect the fault code corresponding to the fault signal in real time, and to identify the fault type corresponding to the vehicle based on the fault code through the fault diagnosis model.

[0039] Furthermore, the training module is specifically used for:

[0040] When the driving dataset and the fault parameters are obtained respectively, a first weight is added to the driving dataset and a second weight is added to the fault parameters, and the sum of the first weight and the second weight is 1.

[0041] According to the first weight, the corresponding first data subset is extracted in real time from the driving dataset, and according to the second weight, the corresponding second data subset is extracted in real time from the fault parameters;

[0042] A fault diagnosis model corresponding to the vehicle is trained based on the first data subset and the second data subset.

[0043] Furthermore, the training module is specifically used for:

[0044] When the first data subset and the second data subset are obtained respectively, the first data subset and the second data subset are fused to generate the corresponding target dataset;

[0045] The target dataset is divided into corresponding training and test sets, and the training and test sets are input into the preset edge server to train a fault diagnosis model corresponding to the vehicle.

[0046] Furthermore, the training module is specifically used for:

[0047] When the training set and the test set are obtained respectively, the corresponding initial convolutional neural network is retrieved from the preset edge server.

[0048] The training set is converted into a corresponding feature sequence by a preset DTW algorithm, and the initial convolutional neural network is trained using the feature sequence to generate a corresponding intermediate convolutional neural network.

[0049] The intermediate convolutional neural network is tested using the test set to generate the corresponding fault diagnosis model.

[0050] Furthermore, the training module is specifically used for:

[0051] When the feature sequence is acquired in real time, several feature values ​​contained in the feature sequence are extracted in real time, and each feature value is unique.

[0052] The network distribution map corresponding to the initial convolutional neural network is detected in real time, and several network nodes contained in the network distribution map are detected in real time.

[0053] The intermediate convolutional neural network is trained based on several of the aforementioned feature values ​​and several of the aforementioned network nodes.

[0054] Furthermore, the training module is specifically used for:

[0055] For each of the aforementioned feature values, a corresponding first identifier is added sequentially, and for each of the aforementioned network nodes, a corresponding second identifier is added sequentially.

[0056] The mapping relationship between the first identifier and the second identifier is constructed one by one, and the initial network parameters contained in each network node are detected in real time.

[0057] Based on the mapping relationship, each of the initial network parameters is sequentially replaced with each of the feature values ​​to train the intermediate convolutional neural network accordingly.

[0058] Furthermore, the execution module is specifically used for:

[0059] When the fault code is acquired in real time, the fault sequence corresponding to the fault code is detected in real time.

[0060] The fault values ​​contained in the fault sequence are detected in real time, and the fault values ​​are input into the internal part of the fault diagnosis model to identify the fault type corresponding to the vehicle.

[0061] The third aspect of the present invention proposes:

[0062] A computer includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor, when executing the computer program, implements the vehicle fault diagnosis method as described above.

[0063] The fourth aspect of the present invention proposes:

[0064] A readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the vehicle fault diagnosis method as described above.

[0065] Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0066] Figure 1 A flowchart of a vehicle fault diagnosis method provided in the first embodiment of the present invention;

[0067] Figure 2 This is a structural block diagram of a vehicle fault diagnosis system provided in the third embodiment of the present invention.

[0068] The following detailed description, in conjunction with the accompanying drawings, will further illustrate the present invention. Detailed Implementation

[0069] To facilitate understanding of the present invention, a more complete description will be given below with reference to the accompanying drawings. Several embodiments of the invention are illustrated in the drawings. However, the invention can be implemented in many different forms and is not limited to the embodiments described herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete.

[0070] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there may be an intervening component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there may be an intervening component. The terms "vertical," "horizontal," "left," "right," and similar expressions used in this document are for illustrative purposes only.

[0071] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains. The terminology used herein in the description of the invention is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. The term "and / or" as used herein includes any and all combinations of one or more of the associated listed items.

[0072] Please see Figure 1 The image shows a vehicle fault diagnosis method provided in the first embodiment of the present invention. The vehicle fault diagnosis method provided in this embodiment can identify the fault type of the current vehicle in a timely and effective manner through the constructed fault diagnosis model, thereby improving the diagnosis efficiency.

[0073] Specifically, this embodiment provides:

[0074] A vehicle fault diagnosis method specifically includes the following steps:

[0075] Step S10: During normal vehicle operation, the vehicle's driving parameters are collected in real time by preset sensors, and a corresponding driving dataset is generated based on the driving parameters.

[0076] Step S20: When a fault signal is detected in the vehicle in real time, the fault signal is parsed and processed to extract the fault parameters contained in the fault signal in real time.

[0077] Step S30: Input the driving dataset and the fault parameters into a preset edge server, and train a fault diagnosis model corresponding to the vehicle based on the driving dataset and the fault parameters through the preset edge server.

[0078] Step S40: Real-time detection of the fault code corresponding to the fault signal, and identification of the fault type corresponding to the vehicle based on the fault code using the fault diagnosis model.

[0079] Specifically, in this embodiment, it should first be noted that in order to diagnose vehicle faults in a timely and effective manner, it is necessary to obtain the vehicle's operating status in real time and accurately. Specifically, this means obtaining information when the vehicle is in a normal state and information when it is in an abnormal state. Furthermore, it should be pointed out that this vehicle fault diagnosis method is based on a real-time vehicle controller installed inside the vehicle. In practical applications, when the vehicle is detected to be in normal operating condition, various sensors pre-installed inside the vehicle will collect the current vehicle's driving parameters in real time. Preferably, the vehicle's speed, torque, and throttle opening are collected in real time. Simultaneously, a corresponding driving dataset can be generated based on these driving parameters.

[0080] Furthermore, when the vehicle controller detects a vehicle fault in real time and acquires the corresponding fault signal, it should be noted that since this fault signal contains certain fault information, it can be further analyzed to extract the corresponding fault parameters. Going further, to facilitate subsequent model training, the current driving dataset and fault parameters are immediately input into a pre-set edge server. Simultaneously, this edge server trains a fault diagnosis model corresponding to the current vehicle in real time based on the current driving dataset and fault parameters. Building upon this, by further detecting the fault code contained in the current fault signal in real time, the fault diagnosis model can ultimately identify the fault type of the current vehicle based on the fault code and provide a corresponding solution, thus improving diagnostic efficiency.

[0081] Second Embodiment

[0082] Furthermore, the step of training a fault diagnosis model corresponding to the vehicle using a preset edge server based on the driving dataset and the fault parameters includes:

[0083] When the driving dataset and the fault parameters are obtained respectively, a first weight is added to the driving dataset and a second weight is added to the fault parameters, and the sum of the first weight and the second weight is 1.

[0084] According to the first weight, the corresponding first data subset is extracted in real time from the driving dataset, and according to the second weight, the corresponding second data subset is extracted in real time from the fault parameters;

[0085] A fault diagnosis model corresponding to the vehicle is trained based on the first data subset and the second data subset.

[0086] Furthermore, the step of training a fault diagnosis model corresponding to the vehicle based on the first data subset and the second data subset includes:

[0087] When the first data subset and the second data subset are obtained respectively, the first data subset and the second data subset are fused to generate the corresponding target dataset;

[0088] The target dataset is divided into corresponding training and test sets, and the training and test sets are input into the preset edge server to train a fault diagnosis model corresponding to the vehicle.

[0089] Furthermore, the step of inputting the training set and the test set into the preset edge server to train a fault diagnosis model corresponding to the vehicle includes:

[0090] When the training set and the test set are obtained respectively, the corresponding initial convolutional neural network is retrieved from the preset edge server.

[0091] The training set is converted into a corresponding feature sequence by a preset DTW algorithm, and the initial convolutional neural network is trained using the feature sequence to generate a corresponding intermediate convolutional neural network.

[0092] The intermediate convolutional neural network is tested using the test set to generate the corresponding fault diagnosis model.

[0093] Furthermore, the step of training the initial convolutional neural network using the feature sequence to generate a corresponding intermediate convolutional neural network includes:

[0094] When the feature sequence is acquired in real time, several feature values ​​contained in the feature sequence are extracted in real time, and each feature value is unique.

[0095] The network distribution map corresponding to the initial convolutional neural network is detected in real time, and several network nodes contained in the network distribution map are detected in real time.

[0096] The intermediate convolutional neural network is trained based on several of the aforementioned feature values ​​and several of the aforementioned network nodes.

[0097] Furthermore, the step of training the intermediate convolutional neural network based on the plurality of feature values ​​and the plurality of network node correspondences includes:

[0098] For each of the aforementioned feature values, a corresponding first identifier is added sequentially, and for each of the aforementioned network nodes, a corresponding second identifier is added sequentially.

[0099] The mapping relationship between the first identifier and the second identifier is constructed one by one, and the initial network parameters contained in each network node are detected in real time.

[0100] Based on the mapping relationship, each of the initial network parameters is sequentially replaced with each of the feature values ​​to train the intermediate convolutional neural network accordingly.

[0101] Furthermore, the step of identifying the fault type corresponding to the vehicle based on the fault code using the fault diagnosis model includes:

[0102] When the fault code is acquired in real time, the fault sequence corresponding to the fault code is detected in real time.

[0103] The fault values ​​contained in the fault sequence are detected in real time, and the fault values ​​are input into the internal part of the fault diagnosis model to identify the fault type corresponding to the vehicle.

[0104] Furthermore, in this embodiment, it should be noted that after obtaining the required driving dataset and fault parameters in real time through the above steps, in order to improve the comprehensiveness of subsequent training, it is necessary to first obtain the corresponding training set. Based on this, it is necessary to first select effective data from the current driving dataset and fault parameters respectively. Preferably, the present invention adds a first weight to the current driving dataset and a second weight to the current fault parameters. Preferably, the sum of the two weights is 1, and the value of the first weight is greater than the value of the second weight. Further, a first data subset is extracted from the driving dataset according to the current first weight, and a second data subset is extracted from the fault parameters according to the current second weight. Further, the current first data subset and second data subset are immediately fused to obtain the required target dataset, and the current target dataset can be further divided into corresponding training and test sets. At the same time, the current training and test sets only need to be immediately input into the initial convolutional neural network inside the preset edge server to perform subsequent training.

[0105] Furthermore, before training begins, the DTW (Data Transformation) algorithm needs to be invoked. The DTW algorithm immediately transforms the training set into a feature sequence for training. To facilitate simple and rapid training, several feature values ​​from the current feature sequence need to be extracted in real-time. Simultaneously, the network distribution map corresponding to the initial convolutional neural network and its corresponding network nodes are detected. It's important to note that each feature value and each network node is unique. To facilitate subsequent identification and training, a first identifier is added to each feature value, and a second identifier is added to each network node, establishing a mapping between them. Based on this, by replacing each initial network parameter with each feature value according to the mapping, the required intermediate convolutional neural network can be generated. Finally, testing this intermediate convolutional neural network yields the desired fault diagnosis model. Furthermore, in the actual diagnostic process, it is only necessary to extract the fault sequence contained in the current fault code in real time, and further extract the required fault value from the current fault sequence. Then, the current fault diagnosis model can finally complete the identification of the current vehicle fault based on the current fault value, thereby improving the efficiency of fault diagnosis.

[0106] Please see Figure 2 The third embodiment of the present invention provides:

[0107] A vehicle fault diagnosis system, wherein the system includes:

[0108] The data acquisition module is used to collect the vehicle's driving parameters in real time through preset sensors during normal vehicle operation, and generate a corresponding driving dataset based on the driving parameters.

[0109] The parsing module is used to parse the fault signal when a fault signal is detected in the vehicle in real time, so as to extract the fault parameters contained in the fault signal in real time.

[0110] The training module is used to input the driving dataset and the fault parameters into a preset edge server, and train a fault diagnosis model corresponding to the vehicle based on the driving dataset and the fault parameters through the preset edge server.

[0111] The execution module is used to detect the fault code corresponding to the fault signal in real time, and to identify the fault type corresponding to the vehicle based on the fault code through the fault diagnosis model.

[0112] Furthermore, the training module is specifically used for:

[0113] When the driving dataset and the fault parameters are obtained respectively, a first weight is added to the driving dataset and a second weight is added to the fault parameters, and the sum of the first weight and the second weight is 1.

[0114] According to the first weight, the corresponding first data subset is extracted in real time from the driving dataset, and according to the second weight, the corresponding second data subset is extracted in real time from the fault parameters;

[0115] A fault diagnosis model corresponding to the vehicle is trained based on the first data subset and the second data subset.

[0116] Furthermore, the training module is specifically used for:

[0117] When the first data subset and the second data subset are obtained respectively, the first data subset and the second data subset are fused to generate the corresponding target dataset;

[0118] The target dataset is divided into corresponding training and test sets, and the training and test sets are input into the preset edge server to train a fault diagnosis model corresponding to the vehicle.

[0119] Furthermore, the training module is specifically used for:

[0120] When the training set and the test set are obtained respectively, the corresponding initial convolutional neural network is retrieved from the preset edge server.

[0121] The training set is converted into a corresponding feature sequence by a preset DTW algorithm, and the initial convolutional neural network is trained using the feature sequence to generate a corresponding intermediate convolutional neural network.

[0122] The intermediate convolutional neural network is tested using the test set to generate the corresponding fault diagnosis model.

[0123] Furthermore, the training module is specifically used for:

[0124] When the feature sequence is acquired in real time, several feature values ​​contained in the feature sequence are extracted in real time, and each feature value is unique.

[0125] The network distribution map corresponding to the initial convolutional neural network is detected in real time, and several network nodes contained in the network distribution map are detected in real time.

[0126] The intermediate convolutional neural network is trained based on several of the aforementioned feature values ​​and several of the aforementioned network nodes.

[0127] Furthermore, the training module is specifically used for:

[0128] For each of the aforementioned feature values, a corresponding first identifier is added sequentially, and for each of the aforementioned network nodes, a corresponding second identifier is added sequentially.

[0129] The mapping relationship between the first identifier and the second identifier is constructed one by one, and the initial network parameters contained in each network node are detected in real time.

[0130] Based on the mapping relationship, each of the initial network parameters is sequentially replaced with each of the feature values ​​to train the intermediate convolutional neural network accordingly.

[0131] Furthermore, the execution module is specifically used for:

[0132] When the fault code is acquired in real time, the fault sequence corresponding to the fault code is detected in real time.

[0133] The fault values ​​contained in the fault sequence are detected in real time, and the fault values ​​are input into the internal part of the fault diagnosis model to identify the fault type corresponding to the vehicle.

[0134] The fourth embodiment of the present invention provides a computer, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the vehicle fault diagnosis method as described above.

[0135] The fifth embodiment of the present invention provides a readable storage medium having a computer program stored thereon, wherein the program, when executed by a processor, implements the vehicle fault diagnosis method as described above.

[0136] In summary, the vehicle fault diagnosis method and system provided by the above embodiments of the present invention can identify the fault type of a vehicle in a timely and effective manner through the fault diagnosis model constructed in real time, thereby significantly improving the vehicle diagnosis efficiency.

[0137] It should be noted that the above modules can be functional modules or program modules, and can be implemented through software or hardware. For modules implemented through hardware, the above modules can reside in the same processor; or the above modules can be located in different processors in any combination.

[0138] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-included system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0139] More specific examples of computer-readable media (a non-exhaustive list) include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0140] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0141] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0142] The embodiments described above are merely illustrative of several implementations of the present invention, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these modifications and improvements all fall within the scope of protection of the present invention. Therefore, the scope of protection of this patent should be determined by the appended claims.

Claims

1. A vehicle fault diagnosis method, characterized in that, The method includes: During normal vehicle operation, the vehicle's driving parameters are collected in real time by preset sensors, and a corresponding driving dataset is generated based on the driving parameters. When a fault signal is detected in the vehicle in real time, the fault signal is analyzed and processed to extract the fault parameters contained in the fault signal in real time. The driving dataset and the fault parameters are both input into a preset edge server, and a fault diagnosis model corresponding to the vehicle is trained by the preset edge server based on the driving dataset and the fault parameters. The fault code corresponding to the fault signal is detected in real time, and the fault diagnosis model identifies the fault type corresponding to the vehicle based on the fault code. The step of training a fault diagnosis model corresponding to the vehicle using a preset edge server based on the driving dataset and the fault parameters includes: When the driving dataset and the fault parameters are obtained respectively, a first weight is added to the driving dataset and a second weight is added to the fault parameters, and the sum of the first weight and the second weight is 1. According to the first weight, the corresponding first data subset is extracted in real time from the driving dataset, and according to the second weight, the corresponding second data subset is extracted in real time from the fault parameters; A fault diagnosis model corresponding to the vehicle is trained based on the first data subset and the second data subset.

2. The vehicle fault diagnosis method according to claim 1, characterized in that: The step of training a fault diagnosis model corresponding to the vehicle based on the first data subset and the second data subset includes: When the first data subset and the second data subset are obtained respectively, the first data subset and the second data subset are fused to generate the corresponding target dataset; The target dataset is divided into corresponding training and test sets, and the training and test sets are input into the preset edge server to train a fault diagnosis model corresponding to the vehicle.

3. The vehicle fault diagnosis method according to claim 2, characterized in that: The step of inputting the training set and the test set into the preset edge server to train a fault diagnosis model corresponding to the vehicle includes: When the training set and the test set are obtained respectively, the corresponding initial convolutional neural network is retrieved from the preset edge server. The training set is converted into a corresponding feature sequence by a preset DTW algorithm, and the initial convolutional neural network is trained using the feature sequence to generate a corresponding intermediate convolutional neural network. The intermediate convolutional neural network is tested using the test set to generate the corresponding fault diagnosis model.

4. The vehicle fault diagnosis method according to claim 3, characterized in that: The step of training the initial convolutional neural network using the feature sequence to generate the corresponding intermediate convolutional neural network includes: When the feature sequence is acquired in real time, several feature values ​​contained in the feature sequence are extracted in real time, and each feature value is unique. The network distribution map corresponding to the initial convolutional neural network is detected in real time, and several network nodes contained in the network distribution map are detected in real time. The intermediate convolutional neural network is trained based on several of the aforementioned feature values ​​and several of the aforementioned network nodes.

5. The vehicle fault diagnosis method according to claim 4, characterized in that: The step of training the intermediate convolutional neural network based on the plurality of feature values ​​and the plurality of network node correspondences includes: For each of the aforementioned feature values, a corresponding first identifier is added sequentially, and for each of the aforementioned network nodes, a corresponding second identifier is added sequentially. The mapping relationship between the first identifier and the second identifier is constructed one by one, and the initial network parameters contained in each network node are detected in real time. Based on the mapping relationship, each of the initial network parameters is sequentially replaced with each of the feature values ​​to train the intermediate convolutional neural network accordingly.

6. The vehicle fault diagnosis method according to claim 5, characterized in that: The step of identifying the fault type corresponding to the vehicle based on the fault code using the fault diagnosis model includes: When the fault code is acquired in real time, the fault sequence corresponding to the fault code is detected in real time. The fault values ​​contained in the fault sequence are detected in real time, and the fault values ​​are input into the internal part of the fault diagnosis model to identify the fault type corresponding to the vehicle.

7. A vehicle fault diagnosis system, characterized in that, The system for implementing the vehicle fault diagnosis method as described in any one of claims 1 to 6 includes: The data acquisition module is used to collect the vehicle's driving parameters in real time through preset sensors during normal vehicle operation, and generate a corresponding driving dataset based on the driving parameters. The parsing module is used to parse the fault signal when a fault signal is detected in the vehicle in real time, so as to extract the fault parameters contained in the fault signal in real time. The training module is used to input the driving dataset and the fault parameters into a preset edge server, and train a fault diagnosis model corresponding to the vehicle based on the driving dataset and the fault parameters through the preset edge server. The execution module is used to detect the fault code corresponding to the fault signal in real time, and to identify the fault type corresponding to the vehicle based on the fault code through the fault diagnosis model.

8. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the vehicle fault diagnosis method as described in any one of claims 1 to 6.

9. A readable storage medium having a computer program stored thereon, characterized in that, When executed by the processor, the program implements the vehicle fault diagnosis method as described in any one of claims 1 to 6.

Images