Fault detection method, device and system, electronic equipment and storage medium
By using vehicle big data to establish and cycle training fault diagnosis models in new energy vehicles, the problem of inaccurate diagnosis results in cooling circuit fault detection is solved, and the accurate diagnosis of coolant deficiency faults is achieved, and the fault detection rate is improved.
Patent Information
- Application Number
- CN202411883265.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-12-19
- Publication Date
- 2025-04-11
AI Technical Summary
The existing new energy vehicle cooling circuit fault detection methods have the problem of inaccurate diagnosis results, especially when there is insufficient coolant. The bubbles formed by air in the circuit may cause the water pump to be misdiagnosed as dry rotation, resulting in inaccurate monitoring.
By using vehicle big data to establish a fault diagnosis model, accumulate effective data as the vehicle runs, and train the fault diagnosis model through cycles to improve the accuracy of the diagnostic results. This method does not require increasing the number of sensors, and uses data interaction and model training between cloud processors and vehicle processors to achieve accurate diagnosis of coolant deficiency failures.
It improves the diagnostic accuracy of the cooling liquid deficiency fault, reduces the risk of fault detection rate, solves the problem of inaccurate diagnosis results in the existing methods, and reduces the fault calibration work required in the vehicle R&D stage.
Smart Images
Figure CN119810949A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of new energy vehicle technology, and more specifically, to a fault detection method, device, system, electronic device and storage medium. Background Art
[0002] The cooling circuit of the temperature control system of new energy vehicles usually adopts a water cooling solution, and the heat transfer medium of the vehicle is coolant. If the vehicle cooling circuit pipeline is damaged, it will lead to insufficient coolant, which may cause the vehicle temperature control system to fail. The coolant monitoring method usually uses whether the water pump in the cooling circuit runs dry to detect whether it runs dry for a period of time (time T), then it is judged that the cooling circuit coolant is insufficient.
[0003] Since there may be a small amount of air in the cooling circuit, the air moves in the circuit to form bubbles. When the bubbles pass through the water pump, the water pump may be diagnosed as dry-running. If you need to eliminate the misdiagnosis of the fault caused by this situation, you need to extend the monitoring time T. However, setting the time T too long will reduce the fault detection rate, resulting in inaccurate monitoring of insufficient coolant. Summary of the invention
[0004] The purpose of the embodiments of the present application is to provide a fault detection method, device, system, electronic device and storage medium, which utilizes vehicle big data to establish a fault diagnosis model, accumulates effective data as the vehicle runs, and improves the accuracy of the diagnosis results by cyclically training the fault diagnosis model, thereby solving the problem of inaccurate diagnosis results of existing methods.
[0005] The present application embodiment provides a fault diagnosis method, which is applied to a vehicle-side processor, and the method includes:
[0006] Extracting features from the vehicle data to obtain first feature data;
[0007] Inputting the characteristic data into a fault diagnosis model for detection, wherein the fault diagnosis model is obtained by training a machine learning model using vehicle big data and user feedback fault data by a cloud processor;
[0008] If the detection result is a coolant shortage fault, the detection result is sent to the human-computer interaction terminal to obtain the actual vehicle detection result fed back by the user;
[0009] The actual vehicle detection result is sent to a cloud server to perform cyclic training on the fault diagnosis model.
[0010] In the above implementation process, vehicle big data is used to establish a fault diagnosis model to diagnose the coolant shortage fault, without increasing the number of sensors; and as the vehicle runs, effective data is gradually accumulated. By continuously training the fault diagnosis model in a cycle, the accuracy of the detection results can be improved, solving the problem of inaccurate diagnosis results of existing methods.
[0011] The present application also provides a fault diagnosis method, which is applied to a cloud server, and the method includes:
[0012] Get vehicle-side data;
[0013] Processing the vehicle-side data to obtain model input data;
[0014] Using the model input data to train the machine learning model to obtain a fault diagnosis model;
[0015] The fault diagnosis model is sent to the vehicle-side processor to perform coolant shortage fault diagnosis, and the actual vehicle test results fed back by the user are obtained, so as to use the actual vehicle test results to perform cyclic training on the fault diagnosis model.
[0016] In the above implementation process, the cloud server continuously obtains the actual vehicle detection results fed back by users to perform model training, thereby improving the accuracy of the model detection results and solving the problem of inaccurate diagnosis results of existing methods.
[0017] Among them, obtaining vehicle-side data includes:
[0018] Obtain vehicle big data and user feedback fault data, wherein the vehicle big data includes vehicle operation data, and the user feedback fault data is user feedback data on whether the vehicle actually has a coolant shortage fault.
[0019] In the above implementation process, the correlation between vehicle big data and user feedback fault data is used to determine whether a coolant shortage fault occurs, without the need to use sensors, thereby reducing costs.
[0020] The processing of the vehicle-side data to obtain model input data includes:
[0021] Acquire all data segments when the water pump state in the vehicle operation data is continuous dry running;
[0022] Extracting statistical features from the data segments to obtain second feature data;
[0023] Converting the user feedback fault data into fault label data;
[0024] The second characteristic data and the fault label data are matched by occurrence time to obtain characteristic data with a fault label, and used as model input data.
[0025] In the above implementation process, the correlation between the second characteristic data and the fault label data within the preset time period can be obtained through matching, so that the fault diagnosis is performed using the correlation.
[0026] The step of extracting statistical features from the data segments to obtain second feature data includes:
[0027] Performing statistical feature extraction on the data segment to obtain primary feature data;
[0028] Perform secondary statistical feature extraction on the primary feature data within a preset time period to obtain secondary feature data.
[0029] In the above implementation process, statistical feature extraction is performed on the data segments to obtain primary feature data and secondary feature data, and feature extraction is performed twice to accurately obtain data features.
[0030] The present application also provides a fault diagnosis device, which is applied to a vehicle-side processor, and the device includes:
[0031] A feature extraction module, used to extract features from vehicle data to obtain first feature data;
[0032] A fault detection module, used for inputting the first feature data into a fault diagnosis model for detection, wherein the fault diagnosis model is obtained by training a machine learning model using vehicle big data and user feedback fault data by a cloud processor;
[0033] A real vehicle result acquisition module is used to send the test result to the human-computer interaction terminal if the test result is a coolant shortage fault, so as to obtain the real vehicle test result fed back by the user;
[0034] The result sending module is used to send the actual vehicle detection result to the cloud server to perform cyclic training on the fault diagnosis model.
[0035] In the above implementation process, vehicle big data is used to establish a fault diagnosis model to diagnose the coolant shortage fault, without increasing the number of sensors; and as the vehicle runs, effective data is gradually accumulated. By continuously training the fault diagnosis model in a cycle, the accuracy of the detection results can be improved, solving the problem of inaccurate diagnosis results of existing methods.
[0036] The present application also provides a fault diagnosis device, which is applied to a cloud server, and the device includes:
[0037] A vehicle-side data acquisition module is used to acquire vehicle-side data;
[0038] A data processing module, used to process the vehicle-side data to obtain model input data;
[0039] A model training module, used to train the machine learning model using the model input data to obtain a fault diagnosis model;
[0040] The model sending module is used to send the fault diagnosis model to the vehicle-side processor to diagnose the coolant shortage fault and obtain the actual vehicle detection results fed back by the user, so as to use the actual vehicle detection results to perform cyclic training on the fault diagnosis model.
[0041] In the above implementation process, the cloud server continuously obtains the actual vehicle detection results fed back by users to perform model training, thereby improving the accuracy of the model detection results and solving the problem of inaccurate diagnosis results of existing methods.
[0042] The present application also provides a fault detection system, which includes a vehicle-side processor and a cloud server:
[0043] The vehicle-side processor uses the fault diagnosis model to perform coolant shortage fault detection on the vehicle data, and sends the detection result to the user to obtain the actual vehicle detection result fed back by the user, and sends the actual vehicle detection result to the cloud server;
[0044] The cloud server uses the vehicle-side data to train the decision tree model to obtain a fault diagnosis model, and sends the fault diagnosis model to the vehicle-side processor, receives the actual vehicle detection results returned by the vehicle-side processor, and uses the actual vehicle detection results to perform cyclic training on the fault diagnosis model.
[0045] In the above implementation process, fault diagnosis is performed on the vehicle-side processor and model training is performed on the cloud server, which can achieve rapid response and rationally utilize the storage space of the cloud server. The vehicle big data is used to establish a fault diagnosis model to diagnose the coolant shortage fault without increasing the number of sensors. Moreover, as the vehicle runs, effective data gradually accumulates. By continuously training the fault diagnosis model in a cycle, the accuracy of the detection results can be improved, solving the problem of inaccurate diagnosis results of existing methods.
[0046] An embodiment of the present application further provides an electronic device, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the above-mentioned fault diagnosis method.
[0047] An embodiment of the present application further provides a readable storage medium, wherein the readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the above-mentioned fault diagnosis method is executed. BRIEF DESCRIPTION OF THE DRAWINGS
[0048] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments of the present application will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present application and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.
[0049] Figure 1 A flowchart of a fault diagnosis method provided in an embodiment of the present application;
[0050] Figure 2 A flowchart of another fault diagnosis method provided in an embodiment of the present application;
[0051] Figure 3 A flow chart of a method for diagnosing insufficient coolant faults based on vehicle big data provided in an embodiment of the present application;
[0052] Figure 4 A flowchart for processing vehicle-side data provided in an embodiment of the present application;
[0053] Figure 5 A flow chart of feature extraction of data segments provided in an embodiment of the present application;
[0054] Figure 6 A structural block diagram of a fault diagnosis device provided in an embodiment of the present application;
[0055] Figure 7 A structural block diagram of another fault diagnosis device provided in an embodiment of the present application.
[0056] icon:
[0057] 100-feature extraction module; 200-fault detection module; 300-real vehicle result acquisition module; 400-result sending module; 500-vehicle-side data acquisition module; 600-data processing module; 700-model training module; 800-model sending module. DETAILED DESCRIPTION
[0058] The technical solutions in the embodiments of the present application will be described below in conjunction with the drawings in the embodiments of the present application.
[0059] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. At the same time, in the description of this application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0060] Please see Figure 1 , Figure 1 A flowchart of a fault diagnosis method provided in an embodiment of the present application. The method is applied to a vehicle-side processor and specifically includes the following steps:
[0061] Step S100: extracting features from vehicle data to obtain first feature data;
[0062] Step S200: inputting the first feature data into a fault diagnosis model for detection, wherein the fault diagnosis model is obtained by training a machine learning model using vehicle big data and user feedback fault data by a cloud processor;
[0063] Step S300: If the detection result is a coolant shortage fault, the detection result is sent to the human-computer interaction terminal to obtain the actual vehicle detection result fed back by the user;
[0064] Step S400: Send the actual vehicle detection result to a cloud server to perform cyclic training on the fault diagnosis model.
[0065] like Figure 2 FIG. 1 is a flowchart of another fault diagnosis method provided by an embodiment of the present application. The present application also provides a fault diagnosis method, which is applied to a cloud server and specifically includes the following steps:
[0066] Step S500: Acquire vehicle-side data;
[0067] Step S600: Processing the vehicle-side data to obtain model input data;
[0068] Step S700: training the machine learning model using the model input data to obtain a fault diagnosis model;
[0069] Step S800: Send the fault diagnosis model to the vehicle-side processor to perform coolant shortage fault diagnosis, and obtain the actual vehicle test results fed back by the user, so as to use the actual vehicle test results to perform cyclic training on the fault diagnosis model.
[0070] like Figure 3The figure shows a flow chart of a method for diagnosing a coolant shortage fault based on vehicle big data. This application obtains a fault diagnosis model by training a machine learning model based on vehicle operation data and feedback from vehicle users through an interactive terminal on whether the vehicle is actually short of coolant (fault label data). The fault diagnosis model is transmitted back to the vehicle-side processor, which uses the model to diagnose the fault of insufficient coolant. When a fault is determined to have occurred, the vehicle user is reminded through the human-computer interaction terminal and the user is requested to feedback the actual fault condition of the vehicle. The fault diagnosis model is then iterated in sequence based on the actual vehicle fault data fed back by the user, and the diagnostic accuracy is continuously improved as the data accumulates.
[0071] First, collect and upload vehicle-side data. Specifically, step S500 may include:
[0072] Obtain vehicle big data and user feedback fault data, wherein the vehicle big data includes vehicle operation data, and the user feedback fault data is user feedback data on whether the vehicle actually has a coolant shortage fault.
[0073] Among them, the vehicle operation data includes various sensor data collected and processed by the on-board ECU (Electronic Control Unit), request and feedback information data between ECUs, including vehicle speed, motor temperature, motor controller temperature, power battery temperature, air conditioning cooler coolant temperature, vehicle high-voltage status, low-voltage battery voltage, water pump requested speed, water pump actual speed, water pump status (whether dry running) and other related signals.
[0074] The user feedback fault data refers to the data provided by the user through the human-computer interaction terminal to indicate whether the vehicle actually has a coolant shortage fault, and the human-computer interaction terminal is such as a touch screen.
[0075] Secondly, the vehicle operation characteristic data (second characteristic data) is extracted, and the user feedback fault data is converted into fault label data.
[0076] Specifically, Figure 4 As shown in FIG. 1 , it is a flow chart of processing vehicle-side data, and step S600 specifically includes the following steps:
[0077] Step S610: Acquire all data segments when the water pump state in the vehicle operation data is continuous dry running;
[0078] Step S620: extracting statistical features from the data segment to obtain second feature data;
[0079] Specifically, Figure 5 As shown, this is the feature extraction flow chart of the data segment:
[0080] Step S621: extracting statistical features from the data segment to obtain primary feature data;
[0081] Step S622: Perform secondary statistical feature extraction on the primary feature data within a preset time period to obtain secondary feature data.
[0082] Data segments when the water pump status is continuously dry are selected from the vehicle operation data of multiple vehicles, and statistical features (such as mean, maximum, change value, etc.) are extracted for each data segment. Secondary statistical features (such as number of times, mean, maximum, change value, etc.) are extracted for the primary feature data that occurred recently (such as within a month or within the last 3000km of vehicle travel). The primary feature data and secondary feature data are stored in the vehicle operation feature database as the second feature data.
[0083] When matching with the fault label data later, both the primary feature data and the secondary feature data need to be matched with the fault label data, and the purpose of performing secondary statistical feature extraction on the primary feature data is to ensure the accuracy of the matching result.
[0084] Step S630: converting the user feedback fault data into fault label data;
[0085] The coolant shortage fault / normal data fed back by the user through the human-computer interaction terminal, that is, the user-feedback fault data, is converted into fault label data.
[0086] Step S640: Match the second characteristic data and the fault label data by occurrence time to obtain characteristic data with a fault label and use it as model input data.
[0087] Match the second characteristic data and fault label data within a certain period of time to determine the correlation between the two. For example, the vehicle has a coolant shortage fault at a certain moment, but due to delay, the second characteristic data may have shown abnormalities in the previous period, such as the previous month. Therefore, the second characteristic data of the previous month can be matched with the fault label data to determine the correlation between the two, and the fault diagnosis can be performed based on this correlation. In view of this, this method can also be used for the diagnosis and identification of other vehicle faults that require multiple factors or long-term observation.
[0088] Thirdly, the vehicle operation feature data is matched with the fault label data, and the machine learning model is trained. The machine learning model can be a decision tree model or an artificial neural network model, which is not limited here.
[0089] Finally, the trained model is used as a fault diagnosis model after being evaluated for abnormalities, and the fault diagnosis model is sent back to the vehicle-side processor.
[0090] Placing the fault diagnosis process on the vehicle-side processor ensures faster response and rapid acquisition of diagnostic results without occupying cloud resources.
[0091] After the fault occurs, the user can be reminded through the human-computer interaction terminal, and the user can be requested to feedback the actual vehicle inspection results (whether the coolant shortage fault has actually occurred), and the actual vehicle inspection results will be sent to the vehicle data collection and upload device.
[0092] The vehicle coolant shortage fault diagnosis method in the present application establishes a fault diagnosis model using vehicle big data without increasing the number of sensors. As the vehicle runs and effective data is accumulated, the diagnostic accuracy of the coolant shortage fault diagnosis model can be gradually enhanced, solving the problem of inaccurate diagnostic results of existing methods. At the same time, this method also reduces the fault calibration workload required in the vehicle research and development stage.
[0093] The present application also provides a fault diagnosis device, which is applied to a vehicle-side processor, such as Figure 6 The figure is a structural block diagram of a fault diagnosis device, which includes but is not limited to:
[0094] The feature extraction module 100 is used to extract features from the vehicle data to obtain first feature data;
[0095] A fault detection module 200 is used to input the characteristic data into a fault diagnosis model for detection. The fault diagnosis model is obtained by training a machine learning model using vehicle big data and user feedback fault data by a cloud processor;
[0096] The real vehicle result acquisition module 300 is used to send the detection result to the human-computer interaction terminal to obtain the real vehicle detection result fed back by the user if the detection result is a coolant shortage fault;
[0097] The result sending module 400 is used to send the actual vehicle detection result to the cloud server to perform cyclic training on the fault diagnosis model.
[0098] The specific implementation process of the device has been specifically described in the above method and will not be repeated here.
[0099] The present application also provides a fault diagnosis device, which is applied to a cloud server, such as Figure 7 FIG. 1 is a block diagram of another fault diagnosis device, which includes but is not limited to:
[0100] The vehicle-side data acquisition module 500 is used to acquire vehicle-side data;
[0101] The data processing module 600 is used to process the vehicle-side data to obtain model input data;
[0102] A model training module 700 is used to train the machine learning model using the model input data to obtain a fault diagnosis model;
[0103] The model sending module 800 is used to send the fault diagnosis model to the vehicle-side processor to perform coolant shortage fault diagnosis and obtain the actual vehicle test results fed back by the user, so as to use the actual vehicle test results to perform cyclic training on the fault diagnosis model.
[0104] The specific implementation process of the device has been specifically described in the above method and will not be repeated here.
[0105] The present application also provides a fault detection system, which includes a vehicle-side processor and a cloud server:
[0106] The vehicle-side processor uses the fault diagnosis model to perform coolant shortage fault detection on the vehicle data, and sends the detection result to the user to obtain the actual vehicle detection result fed back by the user, and sends the actual vehicle detection result to the cloud server;
[0107] The cloud server uses the vehicle-side data to train the decision tree model to obtain a fault diagnosis model, and sends the fault diagnosis model to the vehicle-side processor, receives the actual vehicle detection results returned by the vehicle-side processor, and uses the actual vehicle detection results to perform cyclic training on the fault diagnosis model.
[0108] The specific implementation process of the system has been specifically described in the above method and will not be repeated here.
[0109] An embodiment of the present application further provides an electronic device, which includes a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the above-mentioned fault diagnosis method.
[0110] An embodiment of the present application further provides a readable storage medium, wherein the readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the above-mentioned fault diagnosis method is executed.
[0111] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can also be implemented in other ways. The device embodiments described above are merely schematic. For example, the flowcharts and block diagrams in the accompanying drawings show the possible architecture, functions and operations of the devices, methods and computer program products according to multiple embodiments of the present application. In this regard, each box in the flowchart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from the order marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flowchart, and the combination of boxes in the block diagram and / or flowchart can be implemented with a dedicated hardware-based system that performs a specified function or action, or can be implemented with a combination of dedicated hardware and computer instructions.
[0112] In addition, the functional modules in the various embodiments of the present application may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
[0113] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium, including several instructions to enable a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0114] The above description is only an embodiment of the present application and is not intended to limit the scope of protection of the present application. For those skilled in the art, the present application may have various changes and variations. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the scope of protection of the present application. It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings.
[0115] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.
[0116] 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 existence of other identical elements in the process, method, article or device including the elements.
Claims
1. A fault diagnosis method, characterized in that: Applied to a vehicle-side processor, the method includes: Extracting features from the vehicle data to obtain first feature data; Inputting the first feature data into a fault diagnosis model for detection, wherein the fault diagnosis model is obtained by training a machine learning model using vehicle big data and user feedback fault data by a cloud processor; If the detection result is a coolant shortage fault, the detection result is sent to the human-computer interaction terminal to obtain the actual vehicle detection result fed back by the user; The actual vehicle detection result is sent to a cloud server to perform cyclic training on the fault diagnosis model.
2. A fault diagnosis method, characterized in that: Applied to a cloud server, the method includes: Get vehicle-side data; Processing the vehicle-side data to obtain model input data; Using the model input data to train the machine learning model to obtain a fault diagnosis model; The fault diagnosis model is sent to the vehicle-side processor to perform coolant shortage fault diagnosis, and the actual vehicle test results fed back by the user are obtained, so as to use the actual vehicle test results to perform cyclic training on the fault diagnosis model.
3. The fault diagnosis method according to claim 2, characterized in that: The obtaining of vehicle-side data includes: Obtain vehicle big data and user feedback fault data, wherein the vehicle big data includes vehicle operation data, and the user feedback fault data is user feedback data on whether the vehicle actually has a coolant shortage fault.
4. The fault diagnosis method according to claim 3, characterized in that: The processing of the vehicle-side data to obtain model input data includes: Acquire all data segments when the water pump state in the vehicle operation data is continuous dry running; Extracting statistical features from the data segments to obtain second feature data; Converting the user feedback fault data into fault label data; The second characteristic data and the fault label data are matched by occurrence time to obtain characteristic data with a fault label, and used as model input data.
5. The fault diagnosis method according to claim 4, characterized in that: The step of extracting statistical features from the data segments to obtain second feature data includes: Performing statistical feature extraction on the data segment to obtain primary feature data; Perform secondary statistical feature extraction on the primary feature data within a preset time period to obtain secondary feature data.
6. A fault diagnosis device, characterized in that: Applied to a vehicle-side processor, the device comprises: A feature extraction module, used to extract features from vehicle data to obtain first feature data; A fault detection module, used for inputting the first feature data into a fault diagnosis model for detection, wherein the fault diagnosis model is obtained by training a machine learning model using vehicle big data and user feedback fault data by a cloud processor; A real vehicle result acquisition module is used to send the test result to the human-computer interaction terminal if the test result is a coolant shortage fault, so as to obtain the real vehicle test result fed back by the user; The result sending module is used to send the actual vehicle detection result to the cloud server to perform cyclic training on the fault diagnosis model.
7. A fault diagnosis device, characterized in that: Applied to a cloud server, the device comprises: A vehicle-side data acquisition module is used to acquire vehicle-side data; A data processing module, used to process the vehicle-side data to obtain model input data; A model training module, used to train the machine learning model using the model input data to obtain a fault diagnosis model; The model sending module is used to send the fault diagnosis model to the vehicle-side processor to diagnose the coolant shortage fault and obtain the actual vehicle detection results fed back by the user, so as to use the actual vehicle detection results to perform cyclic training on the fault diagnosis model.
8. A fault detection system, characterized in that: The system comprises the vehicle-side processor according to claim 1 and the cloud server according to any one of claims 2 to 5: The vehicle-side processor uses the fault diagnosis model to perform coolant shortage fault detection on the vehicle data, and sends the detection result to the user to obtain the actual vehicle detection result fed back by the user, and sends the actual vehicle detection result to the cloud server; The cloud server uses the vehicle-side data to train the decision tree model to obtain a fault diagnosis model, and sends the fault diagnosis model to the vehicle-side processor, receives the actual vehicle detection results returned by the vehicle-side processor, and uses the actual vehicle detection results to perform cyclic training on the fault diagnosis model.
9. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to perform the fault diagnosis method according to any one of claims 1 to 5.
10. A readable storage medium, characterized in that: The readable storage medium stores computer program instructions, and when the computer program instructions are read and executed by a processor, the fault diagnosis method according to any one of claims 1 to 5 is executed.
Citation Information
Cited By
Software bug handling device and method for automobiles
KR102944960B1