Vehicle insulation fault detection method and device and computer equipment
By drawing the vehicle operation data into a graph and inputting it into a neural network model, the problem of difficulty in judging the cause of vehicle insulation failure is solved, and fast and accurate fault diagnosis is achieved.
Patent Information
- Application Number
- CN202411050644.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-31
- Publication Date
- 2024-11-29
AI Technical Summary
The prior art cannot effectively determine the cause of vehicle insulation failure, resulting in diagnosis difficulties and potential safety hazards.
By obtaining the vehicle's operating data, drawing it into a data graph and inputting a pre-trained neural network model, the neural network model is used to quickly extract the change trend of data to determine the type of insulation failure, and then determining the cause of insulation failure.
It realizes the rapid and accurate judgment of the cause of vehicle insulation failure, improves the accuracy and efficiency of detection, and solves the problems of diagnosis difficulties in traditional methods.
Smart Images

Figure CN119044686A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle insulation fault detection method, device and computer equipment. Background Art
[0002] Vehicle insulation fault detection refers to the detection of the vehicle's electrical system to determine whether there is an insulation fault. Insulation fault refers to a short circuit or grounding between wires or components in the vehicle's electrical system, which causes abnormal current flow or electrical system failure. Through insulation fault detection, potential safety hazards can be discovered and eliminated in a timely manner to ensure the normal operation of the vehicle and the safety of passengers. In traditional insulation fault detection methods, insulation problems are caused by a variety of reasons, among which it is difficult to clearly diagnose and evaluate whether it is a vehicle insulation fault or a battery pack insulation fault.
[0003] To address the above-mentioned problems, no effective solution has been proposed yet. Summary of the invention
[0004] The embodiments of the present invention provide a vehicle insulation fault detection method, device and computer equipment to at least solve the technical problem in the related art that it is impossible to determine the cause of the insulation fault when determining that the insulation fault occurs.
[0005] According to one aspect of an embodiment of the present invention, a vehicle insulation fault detection method is provided, comprising: obtaining operating data of a vehicle to be tested; plotting the operating data into a data graph to be tested, wherein the data graph to be tested is used to characterize the change trend of the operating data; inputting the data graph to be tested into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training the original neural network model through training samples, and the training samples include a sample data graph of a sample vehicle, and a sample insulation fault type of the sample vehicle. In this embodiment, by converting the data into a data graph and using a model to process the data graph to be tested, the change trend of the data can be quickly extracted, and then the insulation fault type corresponding to the data can be obtained relatively quickly and accurately, and the cause of the insulation fault can be determined.
[0006] Optionally, when the operation data includes multiple types, the operation data is plotted as a test data graph, including: plotting respective timing graphs of the multiple operation data according to the moments corresponding to the multiple operation data; and splicing respective timing graphs of multiple groups of operation data to obtain the test data graph. In this optional embodiment, the use of the timing graph can more accurately represent the change trend of the data, helping the model to quickly and accurately obtain the insulation fault type corresponding to the data.
[0007] Optionally, the splicing order of the timing diagram in the sample data diagram matches the splicing order of the timing diagram in the test data diagram. In this optional embodiment, the model can learn the change trends of various data. When the change trend diagrams of various data are spliced in a certain order, it helps the model to quickly discover the relationship between the change trend of each data and the insulation fault type.
[0008] Optionally, the training samples are obtained by: obtaining sample operation data of a sample vehicle and a sample insulation fault type of the sample vehicle; plotting the sample operation data as a sample data graph; and establishing a corresponding relationship between the sample data graph and the sample insulation fault type based on the sample vehicle to obtain the training samples. In this optional embodiment, converting the sample operation data into a sample data graph can enable the model to learn the relationship between the change trend of the data and the fault type, so that the model can quickly and accurately obtain the insulation fault type corresponding to the data during the application process.
[0009] Optionally, the neural network model is trained in the following manner: obtaining an original neural network model that has been pre-trained; locking the parameters of a predetermined layer in the original neural network model; using training samples to train the original neural network model after locking the parameters, and adjusting the unlocked parameters to obtain the neural network model. In this optional embodiment, a pre-trained model can be used as the original neural network model. Such a model has stronger capabilities and higher accuracy, and can quickly and accurately obtain the insulation fault type corresponding to the data.
[0010] Optionally, the original neural network model after locking the parameters is trained using training samples, and the unlocked parameters are adjusted to obtain a neural network model, including: replacing the last layer of the original neural network model with a fully connected layer to obtain a model to be trained, wherein the predetermined layer does not include the last layer; the model to be trained is trained using training samples, and the unlocked parameters in the model to be trained are adjusted to obtain a neural network model. In this optional embodiment, the parameters of the predetermined layer of the pre-trained model can be locked, and the last layer can be replaced with a fully connected layer. The parameters of the fully connected layer can be modified during training, so that the pre-trained model can better adapt to the implementation scenario of vehicle insulation fault detection while maintaining good performance, so as to improve the accuracy of insulation fault type detection.
[0011] According to another aspect of an embodiment of the present invention, a vehicle insulation fault detection device is also provided, including: an acquisition module, used to acquire operating data of a vehicle to be tested; a drawing module, used to draw the operating data into a data graph to be tested, wherein the data graph to be tested is used to characterize the changing trend of the operating data; a detection module, used to input the data graph to be tested into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training an original neural network model through training samples, and the training samples include a sample data graph of a sample vehicle, and a sample insulation fault type of the sample vehicle.
[0012] According to another aspect of an embodiment of the present invention, a non-volatile storage medium is provided, the non-volatile storage medium including a stored program, wherein when the program is running, the device where the non-volatile storage medium is located is controlled to execute any one of the above-mentioned vehicle insulation fault detection methods.
[0013] According to another aspect of the embodiments of the present invention, a computer device is provided. The computer device includes a processor, and the processor is used to run a program. When the program is run, any one of the above-mentioned vehicle insulation fault detection methods is executed.
[0014] According to yet another aspect of an embodiment of the present invention, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, any one of the above-mentioned vehicle insulation fault detection methods is implemented.
[0015] In an embodiment of the present invention, operating data of a vehicle to be tested is obtained; the operating data is plotted as a data graph to be tested, wherein the data graph to be tested is used to characterize the changing trend of the operating data; the data graph to be tested is input into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training an original neural network model through training samples, and the training samples include a sample data graph of a sample vehicle, and a sample insulation fault type of the sample vehicle, thereby achieving the purpose of using a model to process the data graph to be tested and allowing the model to quickly extract the changing trend of the data, thereby achieving the technical effect of quickly and accurately obtaining the insulation fault type corresponding to the data, and determining the cause of the insulation fault, thereby solving the technical problem in the related art that the cause of the insulation fault cannot be determined when the insulation fault occurs. BRIEF DESCRIPTION OF THE DRAWINGS
[0016] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:
[0017] Figure 1A hardware structure block diagram of a computer terminal for implementing a vehicle insulation fault detection method is shown;
[0018] Figure 2 is a flow chart of a vehicle insulation fault detection method provided according to an embodiment of the present invention;
[0019] Figure 3 is a graph of data to be tested provided according to an optional embodiment of the present invention;
[0020] Figure 4 4 is a structural block diagram of a vehicle insulation fault detection device provided according to an embodiment of the present invention. DETAILED DESCRIPTION
[0021] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.
[0022] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.
[0023] According to an embodiment of the present invention, a method embodiment for detecting vehicle insulation faults is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.
[0024] The method embodiment provided in the first embodiment of the present application can be executed in a mobile terminal, a computer terminal or a similar computing device. Figure 1 FIG. 1 shows a hardware structure block diagram of a computer terminal for implementing a vehicle insulation fault detection method. Figure 1As shown, the computer terminal 10 may include one or more (102a, 102b, ..., 102n are used to illustrate) processors (the processor may include but is not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. It can be understood by those skilled in the art that Figure 1 The structure shown is only for illustration and does not limit the structure of the above electronic device. Figure 1 More or fewer components as shown, or with Figure 1 Different configurations shown.
[0025] It should be noted that the one or more processors and / or other data processing circuits described above may generally be referred to herein as "data processing circuits". The data processing circuits may be embodied in whole or in part as software, hardware, firmware, or any other combination thereof. In addition, the data processing circuit may be a single independent processing module, or may be incorporated in whole or in part into any of the other components in the computer terminal 10. As described in the embodiments of the present application, the data processing circuit acts as a processor control (e.g., selection of a variable resistor terminal path connected to an interface).
[0026] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the vehicle insulation fault detection method in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, that is, the vehicle insulation fault detection method of the above-mentioned application is realized. The memory 104 may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 104 may further include a memory remotely arranged relative to the processor, and these remote memories may be connected to the computer terminal 10 via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0027] The display may be, for example, a touch screen liquid crystal display (LCD) that enables a user to interact with a user interface of the computer terminal 10 .
[0028] Figure 2 FIG. 1 is a flow chart of a vehicle insulation fault detection method according to an embodiment of the present invention. Figure 2 As shown, the method comprises the following steps:
[0029] Step S202, obtaining the operating data of the vehicle to be tested.
[0030] In this step, the vehicle to be tested can be monitored and data collected to obtain various data generated during operation, such as battery voltage, battery temperature, remaining battery power, insulation value between the live part and the insulating part, and total mileage of the vehicle. These data can be collected in real time by sensors or other monitoring equipment installed on the vehicle. The operating status of the vehicle to be tested is not limited here, and it can be a running vehicle or a stopped vehicle.
[0031] Step S206: plotting the operating data into a test data graph, wherein the test data graph is used to represent a change trend of the operating data.
[0032] In this step, the acquired operation data can be plotted into charts through data processing and visualization tools. These charts can reflect the changing trends and patterns of the operation data, facilitating subsequent analysis and identification.
[0033] Step S208, inputting the data graph to be tested into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training the original neural network model through training samples, and the training samples include a sample data graph of a sample vehicle and a sample insulation fault type of the sample vehicle.
[0034] In this step, the drawn test data graph can be used as input and processed and analyzed by a pre-trained neural network model. The neural network model is an artificial intelligence algorithm that learns the complex relationships and rules between data through a large amount of training data, so that the test data can be accurately identified and classified. After processing the test data graph, the neural network model will output the corresponding insulation fault type, which indicates the cause of the fault of the vehicle under test, for example, whether it is a vehicle insulation fault or a battery pack insulation fault.
[0035] In practical applications, a certain number of training samples need to be prepared first, that is, the sample data graphs of known sample vehicles and their corresponding insulation fault types. These training samples are input into the original neural network model for training, so that the neural network model can learn the changing trend of the data, gradually optimize and improve its own recognition ability, and then determine its corresponding insulation fault type.
[0036] Through the above steps, the purpose of using the model to process the data graph to be tested and enabling the model to quickly extract the changing trend of the data can be achieved, thereby achieving the technical effect of quickly and accurately obtaining the fault type corresponding to the data, thereby solving the technical problem in the related technology that it is impossible to determine the cause of the insulation fault when the insulation fault occurs.
[0037] As an optional embodiment, when the operation data includes multiple types, the operation data is plotted as a test data graph, including: plotting respective time series graphs of the multiple operation data according to the time points corresponding to the multiple operation data; and splicing the respective time series graphs of the multiple groups of operation data to obtain the test data graph. In this optional embodiment, the use of the time series graph can more accurately represent the change trend of the data, helping the model to quickly and accurately obtain the fault type corresponding to the data.
[0038] Optionally, in order to further improve the accuracy of the judgment, a variety of operating data can be comprehensively considered for judgment. At this time, a variety of different operating data can be processed, and these data may involve different parameters. In order to better analyze these data, these operating data can be plotted into a test data graph, so that the model can more conveniently obtain the change trend of various data, and comprehensively judge the insulation fault type of the vehicle based on the respective operating trends of the various operating data.
[0039] First, you can draw the time series diagrams of various operating data according to the time corresponding to each operating data. This makes the changes of each data at different time points more intuitive. Secondly, you can splice the time series diagrams of multiple groups of operating data together to get the data diagram to be tested. You can analyze the association between different data to better analyze the characteristics and trends of the data. This helps the model quickly and accurately determine the fault type corresponding to the data. Figure 3 is a data diagram to be tested provided according to an optional embodiment of the present invention, such as Figure 3 As shown, the test data diagram is formed by splicing the respective timing diagrams of 6 types of operating data. It should be noted that the horizontal axis of the test data diagram represents time, and multiple timing diagrams can share the same horizontal axis.
[0040] As an optional embodiment, the splicing order of the timing diagram in the sample data diagram matches the splicing order of the timing diagram in the test data diagram. In this optional embodiment, the model can learn the change trends of various data. When the change trend diagrams of various data are spliced in a certain order, it helps the model to quickly discover the relationship between the change trend of each data and the insulation fault type.
[0041] Optionally, the splicing order of the timing diagrams in the sample data diagram matches the splicing order of the timing diagrams in the data diagram to be tested. This means that the arrangement order of the change trend diagrams of the various data displayed in the sample data diagram is consistent with the arrangement order of the timing diagrams in the data diagram to be tested. When the training model learns the change trend of each data, splicing these change trend diagrams together in a certain order helps the model quickly discover the relationship between the change trend of each data and the fault type. This is because by combining the timing diagrams in a specific order in the data diagram to be tested, the model can better understand the correlation and mutual influence between the data. Therefore, when the model is actually applied, the same arrangement order is also used to sort the timing diagrams of the various data, so that the model can more accurately identify the possible insulation fault types.
[0042] As an optional embodiment, the training samples are obtained in the following manner: obtaining sample operation data of a sample vehicle and a sample insulation fault type of the sample vehicle; plotting the sample operation data as a sample data graph; and establishing a corresponding relationship between the sample data graph and the sample insulation fault type based on the sample vehicle to obtain the training samples. In this optional embodiment, converting the sample operation data into a sample data graph can enable the model to learn the relationship between the change trend of the data and the fault type, so that the model can quickly and accurately obtain the insulation fault type corresponding to the data during the application process.
[0043] Optionally, the training samples are obtained as follows: First, sample operation data of some sample vehicles can be obtained, which include the values of various parameters of the vehicle at different time points. Secondly, the sample insulation fault types of these sample vehicles, that is, the insulation fault categories that have been determined for the vehicles, can be obtained. Next, these sample operation data can be converted into sample data graphs, that is, the data can be plotted into visual images. Doing so allows the model and engineers to see the changing trends of the data more clearly, which helps the model learn the characteristics and laws of the data. Then, based on these sample vehicles, a correspondence between the sample data graph and the sample insulation fault type can be established to obtain training samples, that is, each sample data graph is matched with the corresponding insulation fault type to form a training sample set for training the model.
[0044] The method provided in this embodiment can help better utilize sample data to train the model, so that the model can better understand the relationship between data features and fault types, thereby improving the performance of the model in fault diagnosis and prediction.
[0045] As an optional embodiment, the neural network model is trained in the following manner: obtaining an original neural network model that has been pre-trained; locking the parameters of a predetermined layer in the original neural network model; using training samples to train the original neural network model after locking the parameters, and adjusting the unlocked parameters to obtain the neural network model. In this optional embodiment, a pre-trained model can be used as the original neural network model. Such a model has stronger capabilities and higher accuracy, and can quickly and accurately obtain the insulation fault type corresponding to the data.
[0046] Optionally, the training method of the neural network model is as follows: First, an original neural network model that has been pre-trained can be obtained. This original neural network model can be a model that has been trained on a large-scale data set and performs well. Next, the parameters of the predetermined layers in the original neural network model can be locked, that is, the parameters of these layers are fixed and not adjusted. In this way, the features and knowledge learned by the original model in these layers can be retained, thereby ensuring the accuracy of the original neural network model. Then, the original neural network model with locked parameters can be trained using training samples, and the unlocked parameters can be adjusted to obtain a new neural network model. Based on the pre-trained model, this new model uses specific training samples and specific recognition tasks to fine-tune the parameters of the new neural network model, so that the new neural network model can better adapt to the relevant data of vehicle insulation fault detection and perform insulation fault type judgment.
[0047] As an optional embodiment, the original neural network model after locking the parameters is trained using training samples, and the unlocked parameters are adjusted to obtain a neural network model, including: replacing the last layer of the original neural network model with a fully connected layer to obtain a model to be trained, wherein the predetermined layer does not include the last layer; the model to be trained is trained using training samples, and the unlocked parameters in the model to be trained are adjusted to obtain a neural network model. In this optional embodiment, the parameters of the predetermined layer of the pre-trained model can be locked, and the last layer can be replaced with a fully connected layer. The parameters of the fully connected layer can be modified during training, so that the pre-trained model can better adapt to the implementation scenario of vehicle insulation fault detection while maintaining good performance, so as to improve the accuracy of insulation fault type detection.
[0048] Optionally, during the training of the neural network model, the last layer of the original neural network model is replaced with a fully connected layer to obtain a model to be trained. In this process, the predetermined layer does not include the last layer, that is, only the last layer needs to be trained. Then, the training sample can be used to train the model to be trained, and the unlocked parameters in the training model can be adjusted to obtain a new neural network model. During the training process, the model will judge the insulation fault type corresponding to the input sample data based on its own knowledge, and then adjust the parameters of the last fully connected layer based on the difference between the input label and its own judgment result, until the optimal parameters are found, so that the model can better adapt to the specific scenario of vehicle insulation fault detection.
[0049] In this embodiment, the parameters of the predetermined layer of the pre-trained model are locked, and the last layer is replaced by a fully connected layer, so that the pre-trained model can better adapt to the implementation scenario of vehicle insulation fault detection while maintaining good performance. By adjusting the parameters of the fully connected layer, the model learns the features and knowledge related to fault type detection, thereby improving the accuracy of fault type detection. Therefore, the method provided by this optional embodiment can effectively improve the adaptability and accuracy of the model in a specific field, so as to be better applied to the practical problem of vehicle insulation fault detection.
[0050] As a specific embodiment, the vehicle insulation fault detection method may include four parts: data processing and slicing, data visualization and result labeling, model training and evaluation, and practical application.
[0051] Among them, data processing and slicing refers to the collection of data and preprocessing of data. Specifically, the earliest time point of the abnormally low insulation value of the vehicle can be extracted from the big data platform. Then, 6000 frames of data of the vehicle with abnormal insulation can be taken from the day in units of days. The data types that need to be extracted may include the vehicle identification code, the actual time when the collected data occurs, the insulation value between the live part and the insulating part of the vehicle, the remaining capacity value of the vehicle battery, the current value of the vehicle battery, the voltage array of the vehicle battery, the temperature array of the vehicle battery, and the vehicle mileage.
[0052] Data visualization and result labeling means that training samples can be generated based on the collected data. Specifically, the data can be sorted in the time dimension. Then, a time series picture is drawn, and the time series pictures are arranged in the order of voltage, temperature, remaining capacity value, insulation, and mileage to generate a complete picture. Then, according to the vehicle maintenance results, the pictures can be labeled as vehicle insulation faults or battery pack insulation fault types.
[0053] The above two parts can be applied to multiple vehicles with insulation failures, collect multiple pictures and corresponding multiple labels, and then generate training samples.
[0054] Model training and evaluation means that images and corresponding results can be used as training samples and input into the model for training. First, the obtained images can be uniformly resized and standardized. Then the resized images and insulation fault detection results are divided into training sets and test sets at a ratio of 7 to 3. Then, the pre-trained ResNet18 model can be used, in which all layers except the last layer need to be frozen and the last layer is replaced by a fully connected layer. Finally, the accuracy of the test set prediction results can be used as the evaluation criterion for model training.
[0055] Among them, ResNet18 is a deep residual neural network model, which belongs to the ResNet (Residual Network) series. ResNet is a deep learning model architecture proposed by Microsoft Research, which aims to solve the problems of gradient vanishing and gradient explosion that occur in deep neural networks as the number of layers increases, making it possible to train deeper neural networks. ResNet18 is a relatively small model in the ResNet series, with 18 layers (including convolutional layers, pooling layers, fully connected layers, etc.), which has been deeply trained and optimized. ResNet18 adopts the idea of residual learning, that is, by introducing residual blocks (Residual Blocks), the network can learn residual mapping, so that it is easier to train deep networks. ResNet18 is widely used in the field of computer vision, especially in tasks such as image classification, object detection and image segmentation, and has achieved good results. Due to its relatively small size and efficient performance, ResNet18 is often used as a benchmark model or lightweight model, and has high practicality and scalability in practical applications.
[0056] The practical application means that after obtaining the trained model, vehicle data with abnormal insulation values can be obtained from the big data platform in real time, and pictures can be generated for model prediction scores to obtain the fault results of vehicle insulation problems.
[0057] It should be noted that, for the above-mentioned method embodiments, for the sake of simplicity, they are all described as a series of action combinations, but those skilled in the art should know that the present invention is not limited by the described action sequence, because according to the present invention, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should also know that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present invention.
[0058] Through the description of the above implementation methods, those skilled in the art can clearly understand that the vehicle insulation fault detection method according to the above embodiment can be implemented by means of software plus a necessary general hardware platform, and of course can also be implemented by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for enabling a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.
[0059] According to an embodiment of the present invention, a vehicle insulation fault detection device for implementing the above vehicle insulation fault detection method is also provided. Figure 4 is a structural block diagram of a vehicle insulation fault detection device provided according to an embodiment of the present invention, such as Figure 4 As shown, the vehicle insulation fault detection device includes: an acquisition module 41, a drawing module 42 and a detection module 43. The vehicle insulation fault detection device is described below.
[0060] The acquisition module 41 is used to acquire the operating data of the vehicle to be tested.
[0061] The drawing module 42 is connected to the acquisition module 41 and is used to draw the operation data into a test data graph, wherein the test data graph is used to represent the change trend of the operation data.
[0062] The detection module 43 is connected to the drawing module 42, and is used to input the data graph to be tested into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training the original neural network model through training samples, and the training samples include the sample data graph of the sample vehicle and the sample insulation fault type of the sample vehicle.
[0063] It should be noted that the acquisition module 41, the drawing module 42 and the detection module 43 correspond to steps S202 to S206 in the embodiment, and the examples and application scenarios implemented by the multiple modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above embodiment. It should be noted that the above modules, as part of the device, can be run in the computer terminal 10 provided in the embodiment.
[0064] An embodiment of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one network device among multiple network devices of a computer network. The computer device includes a memory and a processor.
[0065] Among them, the memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the vehicle insulation fault detection method and device in the embodiment of the present invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, that is, realizing the above-mentioned vehicle insulation fault detection method. The memory may include a high-speed random access memory, and may also include a non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include a memory remotely arranged relative to the processor, and these remote memories can be connected to the computer terminal via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.
[0066] The processor can call the information and application programs stored in the memory through the transmission device to perform the following steps: obtain the operating data of the vehicle to be tested; plot the operating data into a data graph to be tested, wherein the data graph to be tested is used to characterize the changing trend of the operating data; input the data graph to be tested into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training the original neural network model through training samples, and the training samples include a sample data graph of a sample vehicle and a sample insulation fault type of the sample vehicle.
[0067] Optionally, the processor may also execute the program code of the following steps: when the operating data includes multiple types, the operating data are plotted as a data graph to be tested, including: plotting respective timing graphs of the multiple types of operating data according to the moments corresponding to the multiple types of operating data respectively; and splicing the respective timing graphs of multiple groups of operating data to obtain the data graph to be tested.
[0068] Optionally, the processor may further execute program code of the following steps: the splicing order of the timing diagrams in the sample data diagram matches the splicing order of the timing diagrams in the data diagram to be tested.
[0069] Optionally, the processor may also execute program code of the following steps: the training sample is obtained by: acquiring sample operation data of a sample vehicle and a sample insulation fault type of the sample vehicle; drawing the sample operation data into a sample data graph; and based on the sample vehicle, establishing a correspondence between the sample data graph and the sample insulation fault type to obtain a training sample.
[0070] Optionally, the processor may also execute program code of the following steps: the neural network model is trained in the following manner: obtaining an original neural network model that has been pre-trained; locking the parameters of a predetermined layer in the original neural network model; training the original neural network model with locked parameters using training samples, and adjusting the unlocked parameters to obtain a neural network model.
[0071] Optionally, the processor may also execute the program code of the following steps: using training samples to train the original neural network model after locking the parameters, and adjusting the unlocked parameters to obtain the neural network model, including: replacing the last layer of the original neural network model with a fully connected layer to obtain a model to be trained, wherein the predetermined layer does not include the last layer; using training samples to train the model to be trained, and adjusting the unlocked parameters in the model to be trained to obtain the neural network model.
[0072] The processor can also execute the program code of the following steps: Using the embodiment of the present invention, a solution for detecting vehicle insulation faults is provided. By acquiring the operating data of the vehicle to be tested; drawing the operating data into a test data graph, wherein the test data graph is used to characterize the change trend of the operating data; inputting the test data graph into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training the original neural network model through training samples, and the training samples include the sample data graph of the sample vehicle, and the sample insulation fault type of the sample vehicle, so as to achieve the purpose of using the model to process the test data graph and make the model quickly extract the change trend of the data, thereby achieving the technical effect of obtaining the fault type corresponding to the data relatively quickly and accurately, thereby solving the technical problem in the related technology that the cause of the insulation fault cannot be determined when the insulation fault occurs.
[0073] A person of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing the hardware related to the terminal device through a program, and the program can be stored in a non-volatile storage medium, and the storage medium may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.
[0074] The embodiment of the present invention further provides a non-volatile storage medium. Optionally, in this embodiment, the non-volatile storage medium can be used to store the program code executed by the vehicle insulation fault detection method provided by the above embodiment.
[0075] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a computer terminal group in a computer network, or in any mobile terminal in a mobile terminal group.
[0076] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: obtaining operating data of the vehicle to be tested; plotting the operating data as a data graph to be tested, wherein the data graph to be tested is used to characterize a changing trend of the operating data; inputting the data graph to be tested into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training an original neural network model using training samples, and the training samples include a sample data graph of a sample vehicle, and a sample insulation fault type of the sample vehicle.
[0077] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: when the operating data includes multiple types, the operating data is drawn as a data graph to be tested, including: drawing respective timing graphs of the multiple types of operating data according to the moments corresponding to the multiple types of operating data respectively; splicing the respective timing graphs of multiple groups of operating data to obtain the data graph to be tested.
[0078] Optionally, in this embodiment, the non-volatile storage medium is configured to store program codes for executing the following steps: the splicing order of the timing diagrams in the sample data diagram matches the splicing order of the timing diagrams in the data diagram to be tested.
[0079] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: the training sample is obtained in the following manner: obtaining sample operation data of a sample vehicle and a sample insulation fault type of the sample vehicle; plotting the sample operation data as a sample data graph; based on the sample vehicle, establishing a correspondence between the sample data graph and the sample insulation fault type to obtain a training sample.
[0080] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: the neural network model is trained in the following manner: obtaining an original neural network model that has been pre-trained; locking the parameters of a predetermined layer in the original neural network model; using training samples to train the original neural network model after locking the parameters, and adjusting the unlocked parameters to obtain a neural network model.
[0081] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for executing the following steps: using training samples to train the original neural network model after locking the parameters, and adjusting the unlocked parameters to obtain the neural network model, including: replacing the last layer of the original neural network model with a fully connected layer to obtain a model to be trained, wherein the predetermined layer does not include the last layer; using training samples to train the model to be trained, adjusting the unlocked parameters in the model to be trained, and obtaining the neural network model.
[0082] An embodiment of the present invention further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the vehicle insulation fault detection method in each embodiment of the present application.
[0083] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.
[0084] In the above embodiments of the present invention, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.
[0085] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of the units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, 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 through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.
[0086] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.
[0087] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.
[0088] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk and other media that can store program codes.
[0089] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.
Claims
1. A vehicle insulation fault detection method, characterized in that: include: Obtaining the operating data of the vehicle to be tested; Plotting the operating data into a test data graph, wherein the test data graph is used to represent a change trend of the operating data; The data graph to be tested is input into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training an original neural network model through training samples, and the training samples include a sample data graph of a sample vehicle and a sample insulation fault type of the sample vehicle.
2. The method according to claim 1, characterized in that In the case where the operating data includes multiple types, drawing the operating data into a test data graph includes: Draw respective timing diagrams of the various operating data according to the times corresponding to the various operating data; The respective timing diagrams of the plurality of sets of operation data are spliced together to obtain the data diagram to be tested.
3. The method according to claim 2, characterized in that The splicing order of the timing diagrams in the sample data diagram matches the splicing order of the timing diagrams in the data diagram to be tested.
4. The method according to claim 1, characterized in that: The training samples are obtained in the following way: Acquiring sample operation data of the sample vehicle and sample insulation fault types of the sample vehicle; plotting the sample operation data as the sample data graph; Based on the sample vehicle, a corresponding relationship between the sample data graph and the sample insulation fault type is established to obtain the training sample.
5. The method according to any one of claims 1 to 4, characterized in that: The neural network model is trained in the following way: Get the original pre-trained neural network model; Locking the parameters of a predetermined layer in the original neural network model; The training samples are used to train the original neural network model after locking the parameters, and the unlocked parameters are adjusted to obtain the neural network model.
6. The method according to claim 5, characterized in that The method of using the training sample to train the original neural network model after locking the parameters and adjusting the unlocked parameters to obtain the neural network model includes: Replacing the last layer of the original neural network model with a fully connected layer to obtain a model to be trained, wherein the predetermined layer does not include the last layer; The training sample is used to train the model to be trained, and unlocked parameters in the model to be trained are adjusted to obtain the neural network model.
7. A vehicle insulation fault detection device, characterized in that: include: An acquisition module, used to acquire the operating data of the vehicle to be tested; A drawing module, used for drawing the operation data into a test data graph, wherein the test data graph is used to represent the change trend of the operation data; A detection module is used to input the data graph to be tested into a pre-trained neural network model, and the neural network model outputs the insulation fault type of the vehicle to be tested, wherein the neural network model is obtained by training an original neural network model through training samples, and the training samples include a sample data graph of a sample vehicle and a sample insulation fault type of the sample vehicle.
8. A non-volatile storage medium, characterized in that: The non-volatile storage medium includes a stored program, wherein when the program is executed, the device where the non-volatile storage medium is located is controlled to execute the vehicle insulation fault detection method according to any one of claims 1 to 6.
9. A computer device, characterized in that: include: Memory and processor, The memory stores a computer program; The processor is used to execute the computer program stored in the memory, and when the computer program is run, the processor executes the vehicle insulation fault detection method according to any one of claims 1 to 6.
10. A computer program product comprising computer instructions, characterized in that: The computer instructions are executed by a processor to implement the vehicle insulation fault detection method according to any one of claims 1 to 6.
