Fault identification method and device, electronic equipment and storage medium
By updating the parameters of the vehicle identification model to adapt to dynamic changes, the accuracy and reliability issues of traditional vehicle identification algorithms are solved, and more efficient fault identification is achieved.
Patent Information
- Application Number
- CN202510715786.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-30
- Publication Date
- 2025-09-19
AI Technical Summary
Traditional vehicle identification de-jitter algorithms are unable to update model parameters in real time, resulting in low accuracy and reliability of fault identification and an increased probability of misjudgment.
By acquiring historical fault data, the model parameters of the preset recognition model are updated to obtain the target recognition model, and the target signal data is input into the model for prediction processing of the fault recognition parameters to determine whether there is an abnormality in the signal data.
It achieves real-time adaptation to dynamic changes in vehicle operation, improves the accuracy and reliability of fault identification, and reduces the probability of misjudgment.
Smart Images
Figure CN120671034A_ABST
Abstract
Description
Technical Field
[0001] The present disclosure relates to the field of automobile safety technology, and in particular to a fault identification method, device, electronic device, and storage medium. Background Art
[0002] With the rapid development of automotive technology, the data collected by sensors in automobiles provides rich information for vehicle fault identification. How to accurately identify fault characteristics through sensor data has also become a key point in ensuring driving safety.
[0003] In related technologies, the signals output by sensors are often processed through models trained based on traditional vehicle identification debounce algorithms (time-based debounce algorithms or number-based debounce algorithms). However, in related technologies, traditional vehicle identification debounce algorithms cannot update model parameters in real time based on new signal data, resulting in the model being unable to adapt to dynamic changes in vehicle operation in real time, and the accuracy and reliability of fault identification are low, which in turn increases the probability of misjudgment. Summary of the Invention
[0004] The present disclosure provides a fault identification method, device, electronic device, and storage medium to at least address the problems in related technologies such as the inability of conventional vehicle identification de-jitter algorithms to update model parameters in real time based on new signal data, resulting in the model's inability to adapt to dynamic changes in vehicle operation, low fault identification accuracy and reliability, and an increased probability of misjudgment. The technical solutions of the present disclosure are as follows:
[0005] According to a first aspect of an embodiment of the present disclosure, a fault identification method is provided, including:
[0006] In response to a fault identification instruction carrying target signal data, historical fault data and a preset identification model are acquired; the historical fault data is fault data within a preset time period before the fault identification instruction is triggered;
[0007] Based on the historical fault data, updating the model parameters of the preset recognition model to obtain a target recognition model;
[0008] Inputting the target signal data into the target recognition model to perform prediction processing on the fault recognition parameter to obtain a first fault recognition parameter; the first fault recognition parameter is used to determine whether the target signal data has an abnormality;
[0009] Based on the first fault identification parameter, fault identification is performed on the target signal data to obtain a target identification result.
[0010] In an optional embodiment, the historical fault data includes historical signal data and historical fault identification parameters, and updating the model parameters of the preset identification model based on the historical fault data to obtain the target identification model includes:
[0011] Inputting the historical signal data into the signal feature extraction module in the preset recognition model to extract signal features to obtain historical signal features;
[0012] Based on the historical signal features and the historical fault identification parameters, the weights of the prediction modules in the preset identification model are updated to obtain a target identification model.
[0013] In an optional embodiment, the method further includes:
[0014] In the case where the historical fault data is not obtained, the target signal data is input into the preset recognition model to perform prediction processing on the fault recognition parameter to obtain a second fault recognition parameter;
[0015] Based on the second fault identification parameter, fault identification is performed on the target signal data to obtain a target identification result.
[0016] In an optional embodiment, when the first fault identification parameter is a time fault identification parameter, performing fault identification on the target signal data based on the first fault identification parameter to obtain a target identification result includes:
[0017] Obtaining a first preset signal range; the first preset signal range is a range in which the signal corresponding to the target signal data does not exhibit abnormalities;
[0018] Based on the first preset signal range, determining a target duration for which the target signal data is outside the first preset signal range;
[0019] A target identification result is obtained based on the target duration and the time fault identification parameter.
[0020] In an optional embodiment, when the first fault identification parameter is a number fault identification parameter, performing fault identification on the target signal data based on the first fault identification parameter to obtain a target identification result includes:
[0021] Obtaining a second preset signal range; the second preset signal range is a range in which the signal corresponding to the target signal data does not exhibit an abnormality;
[0022] Based on the second preset signal range, determining a target fault number of times that the target signal data is outside the second preset signal range;
[0023] A target identification result is obtained based on the target number of faults and the number of fault identification parameters.
[0024] In an optional embodiment, before inputting the target signal data into the target recognition model to obtain the first fault recognition parameter, the method further includes:
[0025] Obtaining a third preset signal range; the third preset signal range is a range in which the signal corresponding to the target signal data does not exhibit an abnormality;
[0026] When the target signal data exceeds the third preset signal range, the target signal data is deleted.
[0027] In an optional embodiment, the method further includes:
[0028] The historical fault data is updated based on the first fault identification parameter and the target signal data.
[0029] According to a second aspect of an embodiment of the present disclosure, there is provided a fault identification device, comprising:
[0030] An acquisition module, configured to acquire historical fault data and a preset recognition model in response to a fault recognition instruction carrying target signal data; the historical fault data is fault data within a preset time period before the fault recognition instruction is triggered;
[0031] A target recognition model acquisition module is used to update the model parameters of the preset recognition model based on the historical fault data to obtain a target recognition model;
[0032] a first fault identification parameter acquisition module, configured to input the target signal data into the target identification model to perform fault identification parameter prediction processing to obtain a first fault identification parameter; the first fault identification parameter is used to determine whether the target signal data has an abnormality;
[0033] The first target recognition result acquisition module is used to perform fault recognition on the target signal data based on the first fault recognition parameter to obtain a target recognition result.
[0034] In an optional embodiment, the historical fault data includes historical signal data and historical fault identification parameters, and the target recognition model acquisition module includes:
[0035] A historical signal feature acquisition unit, configured to input the historical signal data into a signal feature extraction module in the preset recognition model to extract signal features and obtain historical signal features;
[0036] The target recognition model acquisition unit is used to update the weight of the prediction module in the preset recognition model based on the historical signal characteristics and the historical fault recognition parameters to obtain the target recognition model.
[0037] In an optional embodiment, the device further comprises:
[0038] a second fault identification parameter acquisition module, configured to input the target signal data into the preset identification model to perform fault identification parameter prediction processing to obtain a second fault identification parameter when the historical fault data is not acquired;
[0039] The second target recognition result acquisition module is used to perform fault recognition on the target signal data based on the second fault recognition parameter to obtain a target recognition result.
[0040] In an optional embodiment, when the first fault identification parameter is a time fault identification parameter, the first target identification result acquisition module includes:
[0041] A first preset signal range acquisition unit is configured to acquire a first preset signal range; the first preset signal range is a range in which the signal corresponding to the target signal data does not exhibit an abnormality;
[0042] a target duration determining unit, configured to determine, based on the first preset signal range, a target duration for which the target signal data is outside the first preset signal range;
[0043] The target recognition result acquisition unit is used to obtain a target recognition result based on the target duration and the time fault recognition parameter.
[0044] In an optional embodiment, when the first fault identification parameter is a number fault identification parameter, the first target identification result acquisition module includes:
[0045] A second preset signal range acquisition unit is configured to acquire a second preset signal range; the second preset signal range is a range in which the signal corresponding to the target signal data does not exhibit an abnormality;
[0046] a target fault number determining unit, configured to determine, based on the second preset signal range, a target fault number when the target signal data is not within the second preset signal range;
[0047] The third target recognition result acquisition unit is configured to obtain a target recognition result based on the target number of faults and the number of fault recognition parameters.
[0048] In an optional embodiment, before inputting the target signal data into the target recognition model to obtain the first fault recognition parameter, the apparatus further includes:
[0049] A third preset signal range acquisition module is configured to acquire a third preset signal range; the third preset signal range is a range in which the signal corresponding to the target signal data does not exhibit any abnormality;
[0050] The target signal data deleting module is configured to delete the target signal data if the target signal data exceeds the third preset signal range.
[0051] In an optional embodiment, the device further comprises:
[0052] A historical fault data updating module is configured to update the historical fault data based on the first fault identification parameter and the target signal data.
[0053] According to a third aspect of an embodiment of the present disclosure, an electronic device is provided, comprising: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement a method as described in any one of the first aspects above.
[0054] According to a fourth aspect of an embodiment of the present disclosure, a computer-readable storage medium is provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute any method described in the first aspect of the embodiment of the present disclosure.
[0055] The technical solutions provided by the embodiments of the present disclosure bring at least the following beneficial effects:
[0056] In response to a fault identification instruction carrying target signal data, historical fault data and a preset identification model are obtained; the historical fault data is the fault data within a preset time period before the fault identification instruction is triggered; based on the historical fault data, the model parameters of the preset identification model are updated to obtain a target identification model; the target signal data is input into the target identification model for predictive processing of the fault identification data to obtain a first fault identification parameter for determining whether there is an abnormality in the target signal data; based on the first fault identification parameter, fault identification is performed on the target signal data to obtain a target identification result, which can adapt to dynamic changes in vehicle operation in real time, improve the accuracy and reliability of fault identification, and thereby reduce the probability of misjudgment.
[0057] It is to be understood that the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the disclosure. BRIEF DESCRIPTION OF THE DRAWINGS
[0058] The accompanying drawings herein are incorporated into and constitute a part of the specification, illustrate embodiments consistent with the present disclosure, and together with the description are used to explain the principles of the present disclosure, and do not constitute an improper limitation of the present disclosure.
[0059] Figure 1 is a schematic diagram showing an application environment according to an exemplary embodiment;
[0060] Figure 2 is a flow chart showing a fault identification method according to an exemplary embodiment;
[0061] Figure 3 is a block diagram of a fault identification device according to an exemplary embodiment;
[0062] Figure 4 is a block diagram of an electronic device for fault identification according to an exemplary embodiment;
[0063] Figure 5 The figure is a block diagram of an electronic device for a fault identification method according to an exemplary embodiment. DETAILED DESCRIPTION
[0064] In order to enable ordinary persons in the art to better understand the technical solutions of the present disclosure, the technical solutions in the embodiments of the present disclosure will be clearly and completely described below with reference to the accompanying drawings.
[0065] It should be noted that the terms "first," "second," and the like in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish between similar and different contents, and are not necessarily used to describe a specific order or precedence. It should be understood that the numbers used in this manner are interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present disclosure. Instead, they are merely examples of apparatus and methods consistent with certain aspects of the present disclosure as detailed in the appended claims.
[0066] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for display, data for analysis, etc.) involved in this disclosure are all information and data authorized by the user or fully authorized by all parties.
[0067] See also Figure 1 , Figure 1 is a schematic diagram showing an application environment according to an exemplary embodiment. Figure 1 As shown, the application environment may include a terminal 100 and a server 200 .
[0068] In an optional embodiment, the terminal 100 can be used to provide users with services such as fault identification. Specifically, the terminal 100 may include, but is not limited to, electronic devices such as smartphones, desktop computers, tablet computers, laptops, smart speakers, digital assistants, augmented reality (AR) / virtual reality (VR) devices, and smart wearable devices. It may also be software running on these electronic devices, such as applications. Optionally, the operating system running on the electronic device may include, but is not limited to, Android, iOS, Linux, Windows, etc.
[0069] In an optional embodiment, the server 200 can provide background services for the terminal 100 and perform fault identification processing. Optionally, the server 200 can update the model parameters of the preset recognition model to obtain a target recognition model. Accordingly, fault identification can be performed in combination with the target recognition model. Specifically, the server 200 can be an independent physical server, or a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), and big data and artificial intelligence platforms.
[0070] In addition, it should be noted that Figure 1 What is shown is only one application environment provided by the present disclosure. In actual application, other application environments may also be included.
[0071] In the embodiments of this specification, the terminal 100 and the server 200 may be directly or indirectly connected via wired or wireless communication, which is not limited in this disclosure.
[0072] Figure 2 FIG. 1 is a flow chart showing a fault identification method according to an exemplary embodiment. Figure 2 As shown, the fault identification method is used for a server and includes the following steps.
[0073] In step S201 , in response to a fault identification instruction carrying target signal data, historical fault data and a preset identification model are acquired.
[0074] In a specific embodiment, the target signal data may be signal data for fault identification. Specifically, the target signal data may be at least one sensor data, and the at least one sensor data may be data corresponding to at least one sensor, for example, the temperature of the engine coolant collected by the temperature sensor, the wheel speed measured by the speed sensor, and the oxygen content in the engine exhaust monitored by the oxygen sensor.
[0075] In a specific embodiment, the historical fault data is the fault data within a preset time period before the fault identification instruction is triggered. Specifically, the historical fault data may include historical fault signal data and corresponding historical fault identification parameters. The historical fault signal data may be the signal data corresponding to the fault location within the preset time period before the fault identification instruction is triggered. The historical fault identification parameters may be the fault identification parameters corresponding to the fault location within the preset time period before the fault identification instruction is triggered. Exemplarily, the fault identification parameters may include a time threshold and a number threshold.
[0076] In a specific embodiment, taking the target signal data as the temperature of the engine coolant collected by the temperature sensor as an example, the historical fault signal data can be the temperature of the engine coolant at the fault location within a preset time period before the fault identification instruction is triggered, and the historical fault identification parameters can be the fault identification parameters corresponding to the temperature of the engine coolant at the fault location within the preset time period before the fault identification instruction is triggered. Specifically, the fault identification parameters can include a time threshold and a number threshold corresponding to the temperature of the engine coolant at the fault location within the preset time period before the fault identification instruction is triggered.
[0077] In a specific embodiment, taking the target signal data as the wheel speed measured by the speed sensor as an example, the historical fault signal data may be the wheel speed at the fault location within a preset time period before the fault identification instruction is triggered, and the historical fault identification parameters may be the fault identification parameters corresponding to the wheel speed at the fault location within the preset time period before the fault identification instruction is triggered. Specifically, the fault identification parameters may include a time threshold and a number threshold corresponding to the wheel speed at the fault location within the preset time period before the fault identification instruction is triggered.
[0078] In a specific embodiment, taking the target signal data as the oxygen content in the engine exhaust monitored by the oxygen sensor as an example, the historical fault signal data may be the oxygen content at the fault location within a preset time period before the fault identification instruction is triggered, and the historical fault identification parameters may be the fault identification parameters corresponding to the oxygen content within the preset time period before the fault identification instruction is triggered. Specifically, the fault identification parameters may include a time threshold and a number threshold corresponding to the oxygen content at the fault location within the preset time period before the fault identification instruction is triggered.
[0079] In a specific embodiment, the preset recognition model can be a pre-set recognition model. Specifically, the preset recognition model can be obtained by training preset fault data through an extreme learning machine algorithm (ELM). The preset fault data may include at least one fault signal data and respective corresponding fault recognition parameters.
[0080] In step S203, based on the historical fault data, the model parameters of the preset recognition model are updated to obtain a target recognition model.
[0081] In a specific embodiment, the target recognition model can be used to perform fault recognition on target signal data. Specifically, the target recognition model can be obtained by updating model parameters of a preset recognition model based on historical fault parameters.
[0082] In an optional embodiment, the historical fault data includes historical signal data and historical fault identification parameters. Based on the historical fault data, updating the model parameters of the preset identification model to obtain the target identification model may include:
[0083] Inputting historical signal data into the signal feature extraction module in the preset recognition model to extract signal features and obtain historical signal features;
[0084] Based on historical signal features and historical fault recognition parameters, the weights of the prediction modules in the preset recognition model are updated to obtain the target recognition model.
[0085] In a specific embodiment, the signal feature extraction module may be a module for performing signal feature extraction. For example, the signal feature extraction module may be a hidden layer. Accordingly, the activation function and the number of nodes of the signal feature extraction module may be determined in combination with actual application requirements.
[0086] In a specific embodiment, the historical signal feature may be a signal feature corresponding to historical signal data. Specifically, when the signal feature extraction module is a hidden layer, the historical signal feature may be a feature value of the historical signal data extracted by the hidden layer.
[0087] In a specific embodiment, the prediction module can be used to output the prediction result of the preset recognition model. Specifically, the prediction module can be an output layer.
[0088] In a specific embodiment, the target recognition model can be obtained by updating the weights of the prediction module in the preset recognition model. Specifically, the weights of the prediction module in the preset recognition model can be updated based on historical signal characteristics and historical fault recognition parameters.
[0089] In a specific embodiment, taking the signal feature extraction module as the hidden layer and the preset module as the output layer as an example, the historical signal data is input into the hidden layer for calculation, and the output of the hidden layer is used as the historical signal feature. Based on the historical signal feature and the historical fault identification parameters, the weight of the output layer is updated, and the updated preset recognition model is used as the target recognition model.
[0090] In the above embodiment, by combining historical fault identification parameters to update the weights of the prediction module, the model can better learn the mapping relationship between signal features and faults in historical data. The model can automatically adjust itself according to new data, so that when faced with new signal data, it can more accurately identify whether the fault exists.
[0091] In step S205 , the target signal data is input into the target recognition model to perform prediction processing on the fault recognition parameters to obtain the first fault recognition parameters.
[0092] In a specific embodiment, the first fault identification parameter can be used to determine whether there is an abnormality in the target signal data. Specifically, the first fault identification parameter may include a time fault identification parameter and a number fault identification parameter. The time fault identification parameter may be a time threshold, and the number fault identification parameter may be a number threshold.
[0093] In an optional embodiment, before inputting the target signal data into the target recognition model to obtain the first fault recognition parameter, the method may further include:
[0094] Obtaining a third preset signal range;
[0095] When the target signal data exceeds the third preset signal range, the target signal data is deleted.
[0096] In a specific embodiment, the third preset signal range can be a range in which the signal corresponding to the target signal data does not show any abnormality. Specifically, taking the target signal data as the temperature of the engine coolant corresponding to the temperature sensor as an example, the third preset signal range can be a range in which the temperature of the engine coolant does not show any abnormality.
[0097] In the above embodiment, before the target signal data is input into the target recognition model to obtain the first fault recognition parameter, data preprocessing is performed to delete erroneous data that exceeds the third preset signal range. This can avoid abnormal value interference and unstable model output, ensuring that the system can continuously and accurately perform fault identification.
[0098] In step S207 , fault identification is performed on the target signal data based on the first fault identification parameter to obtain a target identification result.
[0099] In a specific embodiment, the target recognition result may be a fault recognition result of a signal corresponding to the target signal data.
[0100] In an optional embodiment, when the first target fault identification parameter is a time fault identification parameter, performing fault identification on the target signal data based on the first target fault identification parameter to obtain a target identification result may include:
[0101] Obtaining a first preset signal range;
[0102] Based on the first preset signal range, determining a target duration for which the target signal data is outside the first preset signal range;
[0103] Based on the target duration and time fault identification parameters, the target identification result is obtained.
[0104] In a specific embodiment, the first preset signal range may be a range in which the target signal data corresponds to a signal in which no abnormality occurs, the target duration may be a duration in which the target signal data is not within the first preset signal range, and the time fault identification parameter may be a time threshold.
[0105] In a specific embodiment, taking the target signal data as the temperature of the engine coolant corresponding to the temperature sensor, the first preset signal range as the temperature range in which the engine coolant temperature does not show abnormalities, and the fault identification parameter as the time threshold as an example, the target identification result can be obtained based on the target duration and time threshold when the engine coolant temperature is not within the first preset signal range. When the target duration exceeds the time threshold, the target identification result is determined to be that the signal corresponding to the target signal data is abnormal. When the target duration does not exceed the time threshold, the target identification result is determined to be that the signal corresponding to the target signal data is normal.
[0106] In a specific embodiment, taking the target signal data as the wheel speed measured by the speed sensor, the first preset signal range as the speed range in which the wheel speed does not show abnormalities, and the fault identification parameter as the time threshold as an example, the target identification result can be obtained based on the target duration and time threshold when the wheel speed is not within the first preset signal range. When the target duration exceeds the time threshold, the target identification result is determined to be that the signal corresponding to the target signal data is abnormal. When the target duration does not exceed the time threshold, the target identification result is determined to be that the signal corresponding to the target signal data is normal.
[0107] In a specific embodiment, taking the target signal data as the oxygen content in the engine exhaust monitored by the oxygen sensor, the first preset signal range as the speed range in which the oxygen content is not abnormal, and the fault identification parameter as the time threshold as an example, the target identification result can be obtained based on the target duration and time threshold when the oxygen content is not within the first preset signal range. When the target duration exceeds the time threshold, the target identification result is determined to be that the signal corresponding to the target signal data is abnormal. When the target duration does not exceed the time threshold, the target identification result is determined to be that the signal corresponding to the target signal data is normal.
[0108] In the above embodiment, when the first target fault identification parameter is a time fault identification parameter, a target identification result is obtained based on the target duration and time fault identification parameter when the target signal data is not within the first preset signal range. It can accurately determine whether it is a transient error caused by occasional interference or a continuous abnormality caused by a real component failure, thereby avoiding misjudgment and missed judgment.
[0109] In an optional embodiment, when the first fault identification parameter is a number fault identification parameter, performing fault identification on the target signal data based on the first fault identification parameter to obtain a target identification result may include:
[0110] Obtaining a second preset signal range;
[0111] Based on the second preset signal range, determining a target fault number where the target signal data is outside the second preset signal range;
[0112] Based on the target fault number and the fault identification parameter, a target identification result is obtained.
[0113] In a specific embodiment, the second preset signal range can be the range in which the target signal data corresponds to a signal in which no abnormality occurs, the target fault number can be the target fault number in which the target signal data is not within the second preset signal range, and the number fault identification parameter can be the number threshold.
[0114] In a specific embodiment, taking the target signal data as the temperature of the engine coolant corresponding to the temperature sensor, the second preset signal range as the content range in which the temperature of the engine coolant is not abnormal, and the fault identification parameter as the number threshold as an example, the target identification result can be obtained based on the target fault number and the number threshold when the temperature of the engine coolant is not within the second preset signal range. When the target continuous number exceeds the number threshold, the target identification result is determined to be that the signal corresponding to the target signal data is abnormal. When the target continuous number does not exceed the number threshold, the target identification result is determined to be that the signal corresponding to the target signal data is normal.
[0115] In a specific embodiment, taking the target signal data as the wheel speed measured by the speed sensor, the second preset signal range as the content range in which the wheel speed does not show abnormalities, and the fault identification parameter as the number threshold as an example, the target identification result can be obtained based on the target fault number and the number threshold when the wheel speed is not within the second preset signal range. When the target continuous number exceeds the number threshold, the target identification result is determined to be that the signal corresponding to the target signal data is abnormal. When the target continuous number does not exceed the number threshold, the target identification result is determined to be that the signal corresponding to the target signal data is normal.
[0116] In a specific embodiment, taking the target signal data as the oxygen content in the engine exhaust monitored by the oxygen sensor, the second preset signal range as the content range in which the oxygen content is not abnormal, and the fault identification parameter as the number threshold as an example, the target identification result can be obtained based on the target fault number and the number threshold in which the oxygen content is not within the second preset signal range. When the target continuous number exceeds the number threshold, the target identification result is determined to be that the signal corresponding to the target signal data is abnormal. When the target continuous number does not exceed the number threshold, the target identification result is determined to be that the signal corresponding to the target signal data is normal.
[0117] In the above embodiment, when the second fault identification parameter is the number fault identification parameter, the target identification result is obtained based on the target continuous number of times the target signal data is not within the second preset signal range and the number fault identification parameter, which can effectively distinguish between occasional abnormalities and continuous faults and avoid misjudgment and missed judgment.
[0118] In an optional embodiment, the above method may further include:
[0119] In the case where no historical fault data is obtained, the target signal data is input into a preset recognition model to perform prediction processing on the fault recognition parameters to obtain a second fault recognition parameter;
[0120] Based on the second fault identification parameter, fault identification is performed on the target signal data to obtain a target identification result.
[0121] In a specific embodiment, the second fault identification parameter can be used to perform fault identification on the target signal data. Specifically, the second fault identification parameter can be obtained by inputting the target signal data into a preset identification model to perform predictive processing on the fault identification parameter. For example, taking the target signal data as the temperature of the engine coolant corresponding to the temperature sensor as an example, the temperature of the engine coolant is input into the preset identification model to perform predictive processing on the fault identification parameter to obtain the second fault identification parameter. Based on the second fault identification parameter, the temperature of the engine coolant is fault identified to obtain a target identification result.
[0122] In the above embodiment, when historical fault data is not obtained, the target signal data is directly input into the preset recognition model for prediction processing of the fault recognition parameters, and the target signal data is fault identified based on the second fault recognition parameter. In the absence of historical data, preliminary fault judgment information can be provided to avoid further deterioration of the fault.
[0123] In an optional embodiment, the above method may further include:
[0124] The historical fault data is updated based on the first fault identification parameter and the target signal data.
[0125] In a specific embodiment, the target signal data and the first fault identification signal may be used as fault identification parameters corresponding to the target signal data and stored in the historical fault data.
[0126] In the above embodiment, the historical fault data is updated based on the target signal data and the first fault identification parameter generated by the current fault identification. By continuously updating the historical fault data, the trend of fault development can be observed more clearly, thereby more accurately identifying the fault.
[0127] It can be seen from the technical solutions provided in the above embodiments of this specification that this specification obtains historical fault data and a preset recognition model in response to a fault recognition instruction carrying target signal data; the historical fault data is the fault data within a preset time period before the fault recognition instruction is triggered; based on the historical fault data, the model parameters of the preset recognition model are updated to obtain a target recognition model; the target signal data is input into the target recognition model for predictive processing of the fault recognition data to obtain a first fault recognition parameter for determining whether there is an abnormality in the target signal data; based on the first fault recognition parameter, the target signal data is subjected to fault recognition to obtain a target recognition result, which can adapt to dynamic changes in vehicle operation in real time, improve the accuracy and reliability of fault recognition, and thereby reduce the probability of misjudgment.
[0128] Figure 3 FIG. 1 is a block diagram of a fault identification device according to an exemplary embodiment. Figure 3 , the device comprises:
[0129] An acquisition module 310 is configured to acquire historical fault data and a preset recognition model in response to a fault recognition instruction carrying target signal data; the historical fault data is fault data within a preset time period before the fault recognition instruction is triggered;
[0130] The target recognition model acquisition module 330 is used to update the model parameters of the preset recognition model based on the historical fault data to obtain the target recognition model;
[0131] The first fault identification parameter acquisition module 350 is used to input the target signal data into the target identification model to perform fault identification parameter prediction processing to obtain the first fault identification parameter; the first fault identification parameter is used to determine whether there is an abnormality in the target signal data;
[0132] The first target recognition result acquisition module 370 is configured to perform fault recognition on the target signal data based on the first fault recognition parameter to obtain a target recognition result.
[0133] In an optional embodiment, the historical fault data includes historical signal data and historical fault identification parameters, and the target recognition model acquisition module 330 includes:
[0134] A historical signal feature acquisition unit is used to input historical signal data into a signal feature extraction module in a preset recognition model to extract signal features and obtain historical signal features;
[0135] The target recognition model acquisition unit is used to update the weight of the prediction module in the preset recognition model based on historical signal characteristics and historical fault recognition parameters to obtain the target recognition model.
[0136] In an optional embodiment, the above device further includes:
[0137] A second fault identification parameter acquisition module is used to input the target signal data into a preset identification model to perform fault identification parameter prediction processing to obtain a second fault identification parameter when no historical fault data is obtained;
[0138] The second target recognition result acquisition module is used to perform fault recognition on the target signal data based on the second fault recognition parameter to obtain a target recognition result.
[0139] In an optional embodiment, when the first fault identification parameter is a time fault identification parameter, the first target identification result acquisition module 370 includes:
[0140] A first preset signal range acquisition unit is configured to acquire a first preset signal range; the first preset signal range is a range in which the target signal data corresponds to a signal in which no abnormality occurs;
[0141] a target duration determining unit, configured to determine, based on the first preset signal range, a target duration for which the target signal data is not within the first preset signal range;
[0142] The target recognition result acquisition unit is used to obtain the target recognition result based on the target duration and the time fault recognition parameter.
[0143] In an optional embodiment, when the first fault identification parameter is a number fault identification parameter, the first target identification result acquisition module 370 includes:
[0144] A second preset signal range acquisition unit is configured to acquire a second preset signal range; the second preset signal range is a range in which the target signal data corresponds to a signal in which no abnormality occurs;
[0145] a target fault number determining unit, configured to determine, based on the second preset signal range, a target fault number when the target signal data is not within the second preset signal range;
[0146] The third target recognition result acquisition unit is configured to obtain a target recognition result based on the target fault number and the fault number recognition parameter.
[0147] In an optional embodiment, before inputting the target signal data into the target recognition model to obtain the first fault recognition parameter, the apparatus further includes:
[0148] A third preset signal range acquisition module is configured to acquire a third preset signal range; the third preset signal range is a range in which the target signal data corresponds to a signal in which no abnormality occurs;
[0149] The target signal data deletion module is used to delete the target signal data when the target signal data exceeds a third preset signal range.
[0150] In an optional embodiment, the above device further includes:
[0151] The historical fault data updating module is used to update the historical fault data based on the first fault identification parameter and the target signal data.
[0152] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.
[0153] Figure 4 is a block diagram of an electronic device for fault identification according to an exemplary embodiment. The electronic device may be a terminal, and its internal structure diagram may be as shown in FIG. Figure 4As shown. The electronic device includes a processor, a memory, a network interface, a display screen and an input device connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a fault identification method is implemented. The display screen of the electronic device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the electronic device can be a touch layer covering the display screen, or a button, trackball or touchpad provided on the housing of the electronic device, or an external keyboard, touchpad or mouse, etc.
[0154] Figure 5 is a block diagram of an electronic device for fault identification according to an exemplary embodiment. The electronic device may be a server, and its internal structure diagram may be as shown in FIG. Figure 4 As shown. The electronic device includes a processor, a memory, and a network interface connected via a system bus. The processor of the electronic device is used to provide computing and control capabilities. The memory of the electronic device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The network interface of the electronic device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a fault identification method is implemented.
[0155] Those skilled in the art will understand that Figure 4 or Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the scheme of the present disclosure, and does not constitute a limitation on the electronic device to which the scheme of the present disclosure is applied. The specific electronic device may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.
[0156] In an exemplary embodiment, an electronic device is further provided, including: a processor; and a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the fault identification method in the embodiment of the present disclosure.
[0157] In an exemplary embodiment, a computer-readable storage medium is further provided. When instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the fault identification method in the embodiment of the present disclosure.
[0158] Other embodiments of the present disclosure will readily occur to those skilled in the art after considering the specification and practicing the invention disclosed herein. This application is intended to cover any variations, uses, or adaptations of the present disclosure that follow the general principles of the present disclosure and include common knowledge or customary techniques in the art not disclosed herein. The description and examples are to be considered as exemplary only, with the true scope and spirit of the present disclosure being indicated by the following claims.
[0159] It should be understood that the present disclosure is not limited to the exact structures that have been described above and shown in the drawings, and that various modifications and changes can be made without departing from the scope thereof. The scope of the present disclosure is limited only by the appended claims.
Claims
1. A fault identification method, characterized in that: include: Responding to a fault identification instruction carrying target signal data, acquiring historical fault data and a preset identification model; The historical fault data is the fault data within a preset time period before the fault identification instruction is triggered; Based on the historical fault data, updating the model parameters of the preset recognition model to obtain a target recognition model; Inputting the target signal data into the target recognition model to perform prediction processing on the fault recognition parameter to obtain the first fault recognition parameter; The first fault identification parameter is used to determine whether there is an abnormality in the target signal data; Based on the first fault identification parameter, fault identification is performed on the target signal data to obtain a target identification result.
2. The fault identification method according to claim 1, characterized in that: The historical fault data includes historical signal data and historical fault identification parameters. The updating of the model parameters of the preset identification model based on the historical fault data to obtain the target identification model includes: Inputting the historical signal data into the signal feature extraction module in the preset recognition model to extract signal features to obtain historical signal features; Based on the historical signal features and the historical fault identification parameters, the weights of the prediction modules in the preset identification model are updated to obtain a target identification model.
3. The fault identification method according to claim 1, characterized in that: The method further comprises: In the case where the historical fault data is not obtained, the target signal data is input into the preset recognition model to perform prediction processing on the fault recognition parameter to obtain a second fault recognition parameter; Based on the second fault identification parameter, fault identification is performed on the target signal data to obtain a target identification result.
4. The fault identification method according to claim 1, characterized in that: In a case where the first fault identification parameter is a time fault identification parameter, performing fault identification on the target signal data based on the first fault identification parameter to obtain a target identification result includes: Obtaining a first preset signal range; the first preset signal range is a range in which the signal corresponding to the target signal data does not exhibit abnormalities; Based on the first preset signal range, determining a target duration for which the target signal data is outside the first preset signal range; A target identification result is obtained based on the target duration and the time fault identification parameter.
5. The fault identification method according to claim 1, characterized in that: In a case where the first fault identification parameter is a number fault identification parameter, performing fault identification on the target signal data based on the first fault identification parameter to obtain a target identification result includes: Obtaining a second preset signal range; the second preset signal range is a range in which the signal corresponding to the target signal data does not exhibit an abnormality; Based on the second preset signal range, determining a target fault number of times that the target signal data is outside the second preset signal range; A target identification result is obtained based on the target number of faults and the number of fault identification parameters.
6. The fault identification method according to claim 1, characterized in that: Before inputting the target signal data into the target recognition model to obtain the first fault recognition parameter, the method further includes: Obtaining a third preset signal range; the third preset signal range is a range in which the signal corresponding to the target signal data does not exhibit an abnormality; When the target signal data exceeds the third preset signal range, the target signal data is deleted.
7. The fault identification method according to any one of claims 1 to 6, characterized in that: The method further comprises: The historical fault data is updated based on the first fault identification parameter and the target signal data.
8. A fault identification device, characterized in that: include: an acquisition module, configured to acquire historical fault data and a preset recognition model in response to a fault recognition instruction carrying target signal data; The historical fault data is the fault data within a preset time period before the fault identification instruction is triggered; A target recognition model acquisition module is used to update the model parameters of the preset recognition model based on the historical fault data to obtain a target recognition model; a first fault identification parameter acquisition module, configured to input the target signal data into the target identification model to perform fault identification parameter prediction processing to obtain a first fault identification parameter; The first fault identification parameter is used to determine whether there is an abnormality in the target signal data; The first target recognition result acquisition module is used to perform fault recognition on the target signal data based on the first fault recognition parameter to obtain a target recognition result.
9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the fault identification method according to any one of claims 1 to 7.
10. A computer-readable storage medium, characterized in that When the instructions in the storage medium are executed by a processor of an electronic device, the electronic device is enabled to execute the fault identification method according to any one of claims 1 to 7.