Vehicle abnormity identification method and device, equipment and storage medium

Abstract

The invention discloses a vehicle abnormity identification method and device, equipment and a storage medium, and belongs to the field of vehicle engineering. The method comprises the following steps: acquiring vehicle data, wherein the vehicle data comprises periodically acquired indication information of timestamps, insulation resistance and vehicle states; according to the abnormal interval of the insulation resistance, abnormal data fragments are screened from the vehicle data; the insulation resistance in the abnormal data segment is located in the abnormal interval; determining a risk level of the vehicle according to the abnormal data fragment; the risk level is associated with the occurrence frequency of the abnormal data fragment; and according to the vehicle state and the risk level, generating warning information of vehicle insulation abnormity. The method can quickly and accurately diagnose the insulation fault of the vehicle.

Description

Technical Field

[0001] The present application relates to the field of vehicle engineering, and in particular to a method, device, equipment and storage medium for identifying vehicle anomalies. Background Art

[0002] The high-voltage powertrain of electric vehicles, including components such as battery packs, motor controllers, and high-voltage wiring harnesses, involves high voltage and high current. Therefore, the quality of electrical insulation performance is directly related to the safety and reliability of electric vehicles.

[0003] Insulation resistance is a key indicator of the insulation condition of an electrical system. Changes in its value can indicate potential insulation faults. Insulation abnormalities can lead to powertrain failures, battery degradation, and vehicle malfunction. In severe cases, they can even cause safety incidents such as electric shock and fire, posing a serious threat to personal and property safety.

[0004] Therefore, how to quickly and accurately diagnose and troubleshoot insulation faults in electric vehicles has become an important issue that needs to be urgently addressed in the current field of electric vehicle technology. Summary of the Invention

[0005] This application provides a method, device, equipment, and storage medium for identifying vehicle anomalies, which can ensure driving safety. The technical solution is as follows:

[0006] According to one aspect of the present application, a method for identifying vehicle abnormalities is provided, the method comprising:

[0007] Acquiring vehicle data, the vehicle data including periodically collected information such as a timestamp, insulation resistance, and vehicle status;

[0008] According to the abnormal range of the insulation resistance, an abnormal data segment is obtained by screening the vehicle data; the insulation resistance in the abnormal data segment is within the abnormal range;

[0009] Determining a risk level of the vehicle based on the abnormal data segment; the risk level is associated with the frequency of occurrence of the abnormal data segment;

[0010] An alarm message of vehicle insulation abnormality is generated according to the vehicle state and the risk level.

[0011] According to another aspect of the present application, a vehicle abnormality identification device is provided, the device comprising:

[0012] An acquisition module is used to acquire vehicle data, wherein the vehicle data includes periodically collected information such as a timestamp, insulation resistance, and vehicle status;

[0013] a screening module, configured to screen the vehicle data to obtain an abnormal data segment based on the abnormal interval of the insulation resistance; wherein the insulation resistance in the abnormal data segment is within the abnormal interval;

[0014] a determination module, configured to determine a risk level of the vehicle based on the abnormal data segment; the risk level is associated with the frequency of occurrence of the abnormal data segment;

[0015] An alarm module is used to generate alarm information of vehicle insulation abnormality according to the vehicle state and the risk level.

[0016] According to another aspect of the present application, a computer device is provided, comprising a processor and a memory, wherein the memory stores at least one instruction, at least one program, a code set, or an instruction set, and the at least one instruction, the at least one program, the code set, or the instruction set is loaded and executed by the processor to implement the vehicle abnormality identification method as described above.

[0017] According to another aspect of the present application, a computer-readable storage medium is provided, in which at least one instruction, at least one program, a code set or an instruction set is stored. The at least one instruction, the at least one program, the code set or the instruction set is loaded and executed by a processor to implement the method for identifying vehicle abnormalities as described above.

[0018] According to another aspect of the present application, a computer program product or computer program is provided, comprising computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the vehicle anomaly identification method provided in various optional implementations of the above aspects.

[0019] The beneficial effects of the technical solution provided by this application include at least:

[0020] By using the vehicle data uploaded to the cloud by the vehicle, abnormal data segments with insulation resistance within the abnormal range are obtained, the risk level is determined based on the vehicle status of the abnormal data segment, and an alarm is issued for insulation abnormalities based on the risk level. This method requires a reduced number of vehicle data fields, has loose data quality requirements, and the algorithm logic is simple and clear, which greatly reduces the computing power required for insulation abnormality identification and is conducive to large-scale deployment and application. The algorithm has been successfully deployed and verified on many vehicle models with a high accuracy rate (over 80%). With the help of this algorithm, it is possible to achieve long-term and effective tracking of low-risk vehicles, take rapid preventive measures for medium-risk vehicles, and immediately activate emergency response mechanisms for high-risk vehicles, reducing vehicle failure rates and optimizing the user's driving experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0022] Figure 1 It is a structural diagram of a vehicle abnormality identification system provided by an exemplary embodiment of the present application;

[0023] Figure 2 is a flow chart of a method for identifying vehicle abnormalities provided by an exemplary embodiment of the present application;

[0024] Figure 3 is a flow chart of a method for identifying vehicle abnormalities provided by an exemplary embodiment of the present application;

[0025] Figure 4 is a flow chart of a method for identifying vehicle abnormalities provided by an exemplary embodiment of the present application;

[0026] Figure 5 This is a schematic structural diagram of a vehicle abnormality identification device provided by an exemplary embodiment of the present application;

[0027] Figure 6 It is a structural diagram of a computer device provided by an exemplary embodiment of the present application.

[0028] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application. DETAILED DESCRIPTION

[0029] In order to make the objectives, technical solutions and advantages of this application clearer, the implementation methods of this application will be further described in detail below with reference to the accompanying drawings.

[0030] Figure 1 A schematic diagram of a vehicle abnormality identification system provided by an exemplary embodiment of the present application is shown. The system includes a controller 101 and a server 102 .

[0031] The controller 101 is disposed in the vehicle and is used to collect and report vehicle data to the server 102 .

[0032] The controller 101 may include a first memory and a first processor. The first memory stores a vehicle data collection and reporting program; the vehicle data collection and reporting program is called and executed by the first processor to implement the vehicle anomaly identification method provided in this application. The first memory may include, but is not limited to, the following: Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), and Electrically Erasable Programmable Read-Only Memory (EEPROM).

[0033] The server 102 is used to identify abnormal data segments in vehicle data; determine the risk level of the vehicle based on the vehicle status and the abnormal data segments; and generate alarm information of vehicle insulation abnormality corresponding to the risk level; and synchronize the alarm information to the vehicle controller 101 so that the controller 101 broadcasts the alarm information and / or executes the intervention strategy.

[0034] The server 102 may include a second memory and a second processor. The second memory stores a vehicle abnormality identification program; the vehicle abnormality identification program is called and executed by the second processor to implement the vehicle abnormality identification method provided in the present application. The second memory may include, but is not limited to, the following: Random Access Memory (RAM), Read Only Memory (ROM), Programmable Read-Only Memory (PROM), Erasable Programmable Read-Only Memory (EPROM), and Electrically Erasable Programmable Read-Only Memory (EEPROM).

[0035] Figure 2 This is a flow chart of a method for identifying vehicle anomalies provided by an exemplary embodiment of the present application. Figure 1 The vehicle abnormality identification system shown, for example, the method is executed by the server 102. The method includes the following steps.

[0036] Step 210: Acquire vehicle data, which includes periodically collected information such as timestamp, insulation resistance, and vehicle status.

[0037] For example, the vehicle status indication information may include: total current, total mileage. The vehicle status indication information may also include at least one of the following information: total voltage, SOC (State of Charge, percentage of remaining battery power), charging state, engine state, operating mode, DC-DC state.

[0038] Timestamps are used to record the specific time when vehicle data was generated. They can be used for data synchronization, analysis, and fault tracing. Timestamps can be in the following formats: YYYY-MM-DD or HH:MM:SS.sss; or in Unix timestamps (e.g., 1656789000).

[0039] The total voltage is the total DC voltage output by the power battery pack.

[0040] Total current is the total current flowing through the battery pack, with positive values ​​indicating discharge and negative values ​​indicating charge.

[0041] SOC is the percentage of remaining battery power (0% to 100%), which is used to indicate the current available power.

[0042] Exemplarily, the charging status may include at least one of the following: uncharged, slow charging (eg, AC charging), fast charging (eg, DC charging), and charging completed.

[0043] Exemplarily, the engine status is used to indicate whether the engine is running and the running status. For example, the engine status may include at least one of the following: shut down, idling, working, and failure.

[0044] The operating mode indicates the current operating mode of the vehicle's powertrain. For example, the operating mode includes at least one of the following: pure electric mode, hybrid mode, fuel mode, and energy recovery mode.

[0045] The DC-DC state is the state of the DC converter used by the high-voltage battery to supply power to the low-voltage system. The DC-DC state can include at least one of the following: off, operating, or faulty.

[0046] Insulation resistance is the insulation performance between the high-voltage system and the vehicle body. The higher the high-voltage resistance value, the safer it is. If the insulation resistance value is too low, it will trigger an insulation fault.

[0047] The total mileage is the total number of kilometers traveled by the vehicle, which is stored in the vehicle's T-Box or instrument panel.

[0048] Exemplarily, one timestamp corresponds to one frame of vehicle data, and one frame of vehicle data may include at least one of the following data: timestamp, insulation resistance, total current, total mileage, total voltage, SOC (State of Charge, percentage of remaining battery power), charging status, engine status, operating mode, and DC-DC status.

[0049] In an optional embodiment, the vehicle status indication information can not only indicate the vehicle status but also assist in analyzing the cause of the insulation anomaly. For example, after determining the risk level and vehicle status, the vehicle status indication information, vehicle status, and risk level are input into an analysis model to determine the cause of the insulation anomaly, and an alarm is generated based on the cause of the insulation anomaly.

[0050] Step 220: Filtering the vehicle data to obtain an abnormal data segment based on the abnormal range of the insulation resistance; the insulation resistance in the abnormal data segment is within the abnormal range.

[0051] Step 230: Determine the risk level of the vehicle based on the abnormal data segments; the risk level is associated with the frequency of occurrence of the abnormal data segments.

[0052] Step 240: Generate vehicle insulation abnormality warning information based on the vehicle status and risk level.

[0053] In summary, the method provided in the embodiment of the present application utilizes the vehicle data uploaded to the cloud by the vehicle to obtain abnormal data segments in which the insulation resistance is within the abnormal range, determines the risk level based on the vehicle status of the abnormal data segment, and issues an alarm for insulation abnormalities based on the risk level. The number of vehicle data fields required by this method is streamlined, the data quality requirements are relaxed, the algorithm logic is simple and clear, which greatly reduces the computing power requirements for insulation abnormality identification and is conducive to large-scale deployment and application. The algorithm has been successfully deployed and verified on many vehicle models with a high accuracy rate (over 80%). With the help of this algorithm, it is possible to achieve long-term and effective tracking of low-risk vehicles, take rapid preventive measures for medium-risk vehicles, and immediately initiate an emergency response mechanism for high-risk vehicles, thereby reducing vehicle failure rates and optimizing the user's driving experience.

[0054] Figure 3 This is a flow chart of a method for identifying vehicle anomalies provided by an exemplary embodiment of the present application. Figure 1 The vehicle abnormality identification system shown, for example, the method is executed by the server 102. Figure 2 In the illustrated embodiment, step 220 includes step 221 , step 230 includes step 231 , and step 240 includes step 241 .

[0055] Step 210: Acquire vehicle data, which includes periodically collected information such as timestamp, insulation resistance, and vehicle status.

[0056] Step 221: When the insulation resistance in x consecutive frames of vehicle data is all within the abnormal range, mark the x consecutive frames of vehicle data as abnormal data segments, where x is a positive integer.

[0057] Exemplarily, the abnormal interval is determined based on the minimum and maximum insulation resistance values. When the insulation resistance falls within the abnormal interval, it indicates an insulation resistance abnormality. If the insulation resistance in multiple consecutive frames of vehicle data is abnormal, the multiple consecutive frames of vehicle data are marked as abnormal data segments.

[0058] Step 231: Obtain risk level intervals corresponding to at least two risk levels; slide on the abnormal data segment to obtain the maximum insulation resistance in the window according to the sliding window and sliding step; determine the risk level corresponding to the sliding window according to the risk level interval to which the maximum insulation resistance value belongs.

[0059] Exemplarily, multiple risk level intervals corresponding to multiple risk levels constitute an abnormal interval. For example, the low risk level interval is from the first insulation resistance value to the maximum insulation resistance value [IR1, IR_max]; the medium risk level interval is from the second insulation resistance value to the first insulation resistance value [IR2, IR1]; and the high risk level interval is from the minimum insulation resistance value to the second insulation resistance value [IR_min, IR2]. The second insulation resistance value is lower than the first insulation resistance value.

[0060] Step 241: Calculate the average vehicle speed of the abnormal data segment based on the total mileage and timestamp; calculate the average current of the abnormal data segment based on the total current and timestamp; determine the vehicle status based on the average vehicle speed and average current; identify the abnormal situation corresponding to the risk level based on the vehicle status, and generate alarm information corresponding to the abnormal situation.

[0061] Exemplarily, a first total mileage of a first timestamp and a second total mileage of a second timestamp are obtained, the mileage difference between the second total mileage and the first total mileage is calculated, the time difference between the second timestamp and the first timestamp is calculated, and the average speed is obtained by dividing the mileage difference by the time difference.

[0062] Exemplarily, the total current corresponding to each time stamp in the abnormal data segment is obtained, and the average value of all the total currents is calculated to obtain the average current.

[0063] Exemplarily, when the average vehicle speed is higher than a first vehicle speed threshold, the vehicle state is determined to be driving;

[0064] When the average vehicle speed is not higher than the first vehicle speed threshold and the average current is less than the first current threshold, the vehicle state is determined to be charging; when the average vehicle speed is not higher than the first vehicle speed threshold, the average current is not less than the first current threshold and less than the second current threshold, the vehicle state is determined to be stationary; when the average vehicle speed is not higher than the first vehicle speed threshold and the average current is not less than the second current threshold, the vehicle state is determined to be driving.

[0065] The first current threshold is a negative value. If the average current is less than the first current threshold, it indicates that the battery pack is charging and the charging current is relatively high. The second current threshold is a positive value. If the average current is greater than the first current threshold but less than the second current threshold, it indicates that the vehicle is stationary. If the average current is greater than the second current threshold, it indicates that the battery pack is discharging and the discharge current is relatively high, indicating that the vehicle is in motion.

[0066] Exemplarily, the risk levels include low risk, medium risk and high risk; when the duration of low risk is not greater than the first duration threshold, and the duration of medium risk is not greater than the second duration threshold, no alarm information is generated and vehicle data is continuously monitored; when the duration of low risk is less than the first duration threshold, or the duration of medium risk is less than the second duration threshold, historical vehicle data within the historical target duration is obtained, the historical vehicle data is analyzed according to the vehicle status, and an alarm information is generated; in the case of high risk, the cause of the insulation abnormality is determined according to the vehicle status, and an alarm information is generated.

[0067] For example, the server obtains the vehicle data of the vehicle in the past week and analyzes the vehicle data of the vehicle in the past week. When the number of low-risk tags in the vehicle data of a day is higher than the threshold, the day is marked as low-risk. When 7 consecutive days are marked as low-risk, it is determined that the duration of the low-risk occurrence is greater than the first duration threshold. Similarly, the day on which the number of medium-risk tags in a day is higher than the threshold is marked as medium-risk. When 3 consecutive days are marked as medium-risk, it is determined that the duration of the medium-risk occurrence is greater than the second duration threshold. If a high-risk tag appears, an alarm message is immediately generated, and intervention measures are implemented to deal with insulation abnormalities.

[0068] Exemplarily, a linear regression fit is performed on the insulation resistance in historical vehicle data to obtain a fitting curve; the slope of the fitting curve is calculated to obtain the attenuation coefficient of the insulation resistance; when the attenuation coefficient is greater than a first threshold, an alarm message is generated, and the alarm message is used to remind the vehicle that there is an insulation abnormality; the first threshold is determined according to the vehicle status; when the attenuation coefficient is not greater than the first threshold, no alarm message is generated, and the vehicle data is continuously monitored.

[0069] For example, the historical vehicle data may include historical vehicle data for a predetermined period of time, for example, the historical vehicle data includes vehicle data reported by the vehicle in the past month. A linear fit is performed on the insulation resistance values ​​in the vehicle data for the month to obtain a fitting curve for the insulation resistance, and the slope of the fitting curve is calculated to obtain the attenuation coefficient.

[0070] The insulation resistance attenuation coefficient (also known as the insulation degradation rate or insulation aging coefficient) is the rate of change of insulation resistance over time, reflecting the decline in insulation performance. The insulation resistance attenuation coefficient is a key indicator of the rate of insulation material degradation. Exceeding the specified value (e.g., >5-10% / h) directly indicates a potential leakage risk.

[0071] In summary, the method provided in the embodiment of the present application utilizes the vehicle data uploaded to the cloud by the vehicle to obtain abnormal data segments in which the insulation resistance is within the abnormal range, determines the risk level based on the vehicle status of the abnormal data segment, and issues an alarm for insulation abnormalities based on the risk level. The number of vehicle data fields required by this method is streamlined, the data quality requirements are relaxed, the algorithm logic is simple and clear, which greatly reduces the computing power requirements for insulation abnormality identification and is conducive to large-scale deployment and application. The algorithm has been successfully deployed and verified on many vehicle models with a high accuracy rate (over 80%). With the help of this algorithm, it is possible to achieve long-term and effective tracking of low-risk vehicles, take rapid preventive measures for medium-risk vehicles, and immediately initiate an emergency response mechanism for high-risk vehicles, thereby reducing vehicle failure rates and optimizing the user's driving experience.

[0072] Figure 4 This is a flow chart of a method for identifying vehicle anomalies provided by an exemplary embodiment of the present application. Figure 1 The vehicle abnormality identification system shown, for example, the method is executed by the server 102. The method includes the following steps.

[0073] Step 301 (data screening): The running electric vehicle uploads the national standard GBT / 32960 data to the car company's cloud server through the T-box gateway. The fields mainly include timestamp, total voltage, total current, SOC (State of Charge, percentage of remaining battery power), charging status, engine status, operating mode, DC-DC status, insulation resistance, total mileage, etc. The insulation abnormality data fragment is screened based on the "insulation resistance" IR: [IR_min, IR_max] and the number of consecutive frames (cnt1) and recorded as data 1.

[0074] Where IR_max is the maximum insulation resistance threshold, IR_min is the minimum insulation resistance threshold, and cnt1 is the minimum threshold for the number of consecutive frames.

[0075] Step 302 (Operating Condition Identification): Calculate the average current (avg_c) and average vehicle speed (avg_v) for each data segment in Data 1. First, determine whether avg_v is greater than the speed threshold (v1). If so, mark the segment as "driving." Otherwise, proceed to the next determination condition: determine whether avg_c is less than the first current threshold (c1). If so, mark the segment as "charging." Otherwise, proceed to the final determination condition: determine whether avg_c is less than the second current threshold (c2). If so, mark the segment as "stationary." Otherwise, mark it as "driving." This data is recorded as Data 2.

[0076] Among them, avg_v is the average speed; avg_c is the average current; v1 is the minimum speed threshold in the driving state; c1 is the maximum current threshold in the charging state; c2 is the maximum current threshold in the static state.

[0077] Step 303 (risk grading): Calculate the maximum insulation resistance (IR_max_window) of the data sliding window for a specific number of consecutive frames (cnt_window) in each data segment in data 2, and use this value as the risk grading judgment value for this window. A total of three risk intervals are set: low risk [IR1, IR_max], medium risk [IR2, IR1], and high risk [IR_min, IR2].

[0078] Where cnt_window is the size of the sliding window data frames; IR1 is the minimum threshold of low-risk insulation resistance; and IR2 is the minimum threshold of medium-risk insulation resistance.

[0079] Step 304: For high-risk vehicles, direct intervention is required; for low- and medium-risk vehicles, a comprehensive judgment should be made based on the alarm frequency (number of days) and the insulation attenuation trend: if the low-risk frequency is less than or equal to 7 days and the medium-risk frequency is less than or equal to 3 days, keep tracking; otherwise, it is necessary to pull the vehicle's driving data for the past month and use linear regression, moving average and other methods to calculate the insulation resistance attenuation coefficient α. If α>α1, direct intervention is required for this vehicle, otherwise keep tracking.

[0080] In summary, the method provided in the embodiment of the present application utilizes the driving data uploaded to the cloud by the vehicle end to obtain the changing characteristics of the vehicle speed and current within a specific insulation resistance range, identifies and matches the working conditions when the vehicle insulation is abnormal based on the abnormal characteristics, and finally treats the vehicle differently according to the risk frequency, and selects high-frequency risk vehicles to calculate the insulation resistance attenuation coefficient. This method requires a streamlined number of data fields, relatively loose data quality requirements, and concise and clear algorithm logic, which greatly reduces the demand for computing power and is conducive to the deployment, supervision and effective implementation of vehicles on the large-scale market end. In addition, the algorithm has been successfully deployed and verified on many models with a high accuracy rate (over 80%). With the help of this algorithm, companies can achieve long-term and effective tracking of low-risk vehicles, take rapid preventive measures for medium-risk vehicles, and immediately initiate emergency response mechanisms for high-risk vehicles, reducing vehicle failure rates and optimizing the user's driving experience.

[0081] Figure 5 This is a schematic diagram of the structure of a vehicle anomaly identification device provided by an exemplary embodiment of the present application. The device includes:

[0082] An acquisition module 401 is configured to acquire vehicle data, wherein the vehicle data includes periodically collected information such as a timestamp, insulation resistance, and vehicle status.

[0083] A screening module 402 is configured to screen the vehicle data to obtain an abnormal data segment based on the abnormal interval of the insulation resistance; the insulation resistance in the abnormal data segment is within the abnormal interval;

[0084] A determination module 403 is configured to determine a risk level of the vehicle based on the abnormal data segment; the risk level is associated with the frequency of occurrence of the abnormal data segment;

[0085] The alarm module 404 is configured to generate an alarm message of vehicle insulation abnormality according to the vehicle state and the risk level.

[0086] In an optional embodiment, the vehicle status indication information includes: total current, total mileage;

[0087] The alarm module 404 is configured to calculate the average vehicle speed of the abnormal data segment based on the total mileage and the timestamp;

[0088] The alarm module 404 is configured to calculate an average current of the abnormal data segment based on the total current and the timestamp;

[0089] The alarm module 404 is configured to determine the vehicle state according to the average vehicle speed and the average current;

[0090] The alarm module 404 is configured to identify abnormal situations corresponding to the risk levels according to the vehicle status and generate alarm information corresponding to the abnormal situations.

[0091] In an optional embodiment, the warning module 404 is configured to determine the vehicle state as driving when the average vehicle speed is higher than a first vehicle speed threshold;

[0092] The alarm module 404 is configured to determine the vehicle state as charging when the average vehicle speed is not higher than the first vehicle speed threshold and the average current is lower than a first current threshold;

[0093] The alarm module 404 is configured to determine the vehicle state as stationary when the average vehicle speed is not higher than the first vehicle speed threshold and the average current is not lower than the first current threshold and lower than a second current threshold;

[0094] The alarm module 404 is configured to determine the vehicle state as driving when the average vehicle speed is not higher than the first vehicle speed threshold and the average current is not lower than the second current threshold.

[0095] In an optional embodiment, the risk level includes low risk, medium risk and high risk;

[0096] The warning module 404 is configured to not generate the warning information and continue to monitor the vehicle data if the duration of the low risk is not greater than a first duration threshold and the duration of the medium risk is not greater than a second duration threshold;

[0097] The alarm module 404 is configured to obtain historical vehicle data within a historical target duration when the duration of occurrence of the low risk is less than the first duration threshold, or when the duration of occurrence of the medium risk is less than the second duration threshold, analyze the historical vehicle data according to the vehicle status, and generate the alarm information;

[0098] The alarm module 404 is configured to determine the cause of the insulation abnormality according to the vehicle status and generate the alarm information when the high risk exists.

[0099] In an optional embodiment, the alarm module 404 is configured to perform linear regression fitting on the insulation resistance in the historical vehicle data to obtain a fitting curve;

[0100] The alarm module 404 is configured to calculate the slope of the fitting curve to obtain the attenuation coefficient of the insulation resistance;

[0101] The alarm module 404 is configured to generate the alarm information when the attenuation coefficient is greater than a first threshold, wherein the alarm information is used to remind the vehicle of insulation abnormality; the first threshold is determined according to the vehicle state;

[0102] The alarm module 404 is configured to not generate the alarm information and continuously monitor the vehicle data when the attenuation coefficient is not greater than the first threshold.

[0103] In an optional embodiment, the determining module 403 is configured to obtain risk level intervals corresponding to at least two risk levels respectively;

[0104] The determining module 403 is configured to slide on the abnormal data segment and obtain the maximum insulation resistance value within the window according to the sliding window and the sliding step size;

[0105] The determining module 403 is configured to determine the risk level corresponding to the sliding window according to the risk level interval to which the maximum insulation resistance value belongs.

[0106] In an optional embodiment, the screening module 402 is configured to mark x consecutive frames of vehicle data as the abnormal data segment when the insulation resistance in the x consecutive frames of vehicle data is all within the abnormal range, where x is a positive integer.

[0107] It should be noted that the vehicle anomaly identification device provided in the above embodiment is merely exemplified by the division of the above-mentioned functional modules. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above. In addition, the vehicle anomaly identification device provided in the above embodiment and the vehicle anomaly identification method embodiment are based on the same concept. The specific implementation process is detailed in the method embodiment and will not be repeated here.

[0108] Embodiments of the present application further provide a computer device comprising: a processor and a memory, wherein the memory stores at least one instruction, at least one program, code set, or instruction set, and the at least one instruction, at least one program, code set, or instruction set is loaded and executed by the processor to implement the vehicle anomaly identification methods provided in the above-described method embodiments. The computer device may be implemented as a server.

[0109] For example, Figure 6 It is a structural diagram of a computer device provided by an exemplary embodiment of the present application.

[0110] Typically, the computer device 1700 includes a processor 1701 and a memory 1702 .

[0111] The processor 1701 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 1701 may be implemented in at least one hardware form of DSP (Digital Signal Processing), FPGA (Field-Programmable Gate Array), or PLA (Programmable Logic Array). The processor 1701 may also include a main processor and a coprocessor. The main processor is a processor for processing data in the awake state, also known as a CPU (Central Processing Unit); the coprocessor is a low-power processor for processing data in the standby state. In some embodiments, the processor 1701 may be integrated with a GPU (Graphics Processing Unit), which is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 1701 may also include an AI (Artificial Intelligence) processor, which is used to process computing operations related to machine learning.

[0112] Memory 1702 may include one or more computer-readable storage media, which may be non-transitory. Memory 1702 may also include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash memory storage devices. In some embodiments, the non-transitory computer-readable storage medium in memory 1702 is used to store at least one instruction, which is executed by processor 1701 to implement the vehicle anomaly identification method provided in the method embodiment of the present application.

[0113] Those skilled in the art will understand that Figure 6 The structure shown in the figure does not constitute a limitation on the computer device 1700, and the computer device 1700 may include more or fewer components than shown in the figure, or combine some components, or adopt a different component arrangement.

[0114] A computer-readable storage medium is also provided in an embodiment of the present application, which stores at least one instruction, at least one program, code set or instruction set. When the at least one instruction, at least one program, code set or instruction set is loaded and executed by a processor of a computer device, the vehicle abnormality identification method provided by the above-mentioned method embodiments is implemented.

[0115] The present application also provides a computer program product or computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium and executes the computer instructions, causing the computer device to perform the vehicle anomaly identification method provided by each of the above method embodiments.

[0116] Those skilled in the art will understand that all or part of the steps of implementing the above embodiments may be accomplished by hardware, or may be accomplished by a program instructing the relevant hardware, and the program may be stored in a computer-readable storage medium, and the above-mentioned readable storage medium may be a read-only memory, a disk or an optical disk, etc.

[0117] The above description is merely an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent switches, improvements, etc. made within the spirit and principles of the present application shall be included in the scope of protection of the present application.

Claims

1. A method for identifying vehicle abnormalities, characterized in that: The method comprises: Acquiring vehicle data, the vehicle data including periodically collected information such as a timestamp, insulation resistance, and vehicle status; According to the abnormal range of the insulation resistance, an abnormal data segment is obtained by screening the vehicle data; the insulation resistance in the abnormal data segment is within the abnormal range; Determining a risk level of the vehicle based on the abnormal data segment; the risk level is associated with the frequency of occurrence of the abnormal data segment; An alarm message of vehicle insulation abnormality is generated according to the vehicle state and the risk level.

2. The method according to claim 1, characterized in that The vehicle status indication information includes: total current, total mileage; Generating vehicle insulation abnormality warning information according to the vehicle state and the risk level includes: Calculating an average vehicle speed of the abnormal data segment based on the total mileage and the timestamp; calculating an average current of the abnormal data segment according to the total current and the timestamp; determining the vehicle state according to the average vehicle speed and the average current; An abnormal situation corresponding to the risk level is identified according to the vehicle state, and warning information corresponding to the abnormal situation is generated.

3. The method according to claim 2, characterized in that The determining the vehicle state according to the average vehicle speed and the average current includes: When the average vehicle speed is higher than a first vehicle speed threshold, determining the vehicle state as driving; When the average vehicle speed is not higher than the first vehicle speed threshold and the average current is lower than a first current threshold, determining the vehicle state as charging; When the average vehicle speed is not higher than the first vehicle speed threshold, and the average current is not lower than the first current threshold and lower than a second current threshold, determining the vehicle state as stationary; When the average vehicle speed is not higher than the first vehicle speed threshold and the average current is not lower than the second current threshold, the vehicle state is determined to be driving.

4. The method according to claim 2, characterized in that Said risk levels include low risk, medium risk and high risk; The identifying, based on the vehicle state, an abnormal situation corresponding to the risk level and generating warning information corresponding to the abnormal situation includes: If the duration of occurrence of the low risk is not greater than a first duration threshold, and the duration of occurrence of the medium risk is not greater than a second duration threshold, not generating the warning information and continuously monitoring the vehicle data; When the duration of occurrence of the low risk is less than the first duration threshold, or when the duration of occurrence of the medium risk is less than the second duration threshold, acquiring historical vehicle data within a historical target duration, analyzing the historical vehicle data according to the vehicle status, and generating the warning information; In the case of the high risk, the cause of the insulation abnormality is determined according to the vehicle state, and the warning information is generated.

5. The method according to claim 4, characterized in that The step of analyzing the historical vehicle data according to the vehicle status to generate the warning information includes: Performing linear regression fitting on the insulation resistance in the historical vehicle data to obtain a fitting curve; Calculating the slope of the fitting curve to obtain the attenuation coefficient of the insulation resistance; When the attenuation coefficient is greater than a first threshold, generating the warning information, the warning information is used to remind the vehicle that there is an insulation abnormality; the first threshold is determined according to the vehicle state; When the attenuation coefficient is not greater than the first threshold, the warning information is not generated and the vehicle data is continuously monitored.

6. The method according to any one of claims 1 to 5, characterized in that: Determining the risk level of the vehicle based on the abnormal data segment includes: Obtain risk level intervals corresponding to at least two risk levels; Slide on the abnormal data segment according to the sliding window and the sliding step to obtain the maximum insulation resistance within the window; The risk level corresponding to the sliding window is determined according to the risk level interval to which the maximum value of the insulation resistance belongs.

7. A vehicle abnormality identification device, characterized in that: The device comprises: An acquisition module is used to acquire vehicle data, wherein the vehicle data includes periodically collected information such as a timestamp, insulation resistance, and vehicle status; a screening module, configured to screen the vehicle data to obtain an abnormal data segment based on the abnormal interval of the insulation resistance; wherein the insulation resistance in the abnormal data segment is within the abnormal interval; a determination module, configured to determine a risk level of the vehicle based on the abnormal data segment; the risk level is associated with the frequency of occurrence of the abnormal data segment; An alarm module is used to generate alarm information of vehicle insulation abnormality according to the vehicle state and the risk level.

8. A computer device, characterized in that: The computer device includes a processor and a memory, wherein the memory stores at least one program, and the at least one program is loaded and executed by the processor to implement the vehicle abnormality identification method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that The readable storage medium stores at least one program, and the at least one program is loaded and executed by the processor to implement the vehicle abnormality identification method according to any one of claims 1 to 6.

10. A computer program product, characterized in that The computer program product includes computer instructions, which are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the vehicle abnormality identification method as described in any one of claims 1 to 6.

Images