Vehicle fault detection method and device, electronic equipment and readable medium

Abstract

Embodiments of the invention provide a vehicle fault detection method and apparatus, an electronic device and a readable medium. The method comprises the steps of obtaining at least one operation index of a control system of a preset vehicle and historical operation data of the operation index; the control system comprises at least one of a vehicle control unit, a battery management system and a vehicle dynamic control system; the operating indicator is associated with a fault likelihood of a high-voltage power system of the vehicle; obtaining a covariance matrix of historical operation data of the operation indexes; acquiring a characteristic value of any operation index based on the covariance matrix; the characteristic value is used for indicating the correlation degree between the operation index and the fault possibility; determining a target operation index from the at least one operation index according to the characteristic value; and judging whether the high-voltage power system of the vehicle has a fault risk or not based on the current operation data of the target operation index, and judging whether the high-voltage power system of the vehicle has the fault risk or not in advance through cross comprehensive analysis of the multi-dimensional index data.

Description

Technical Field

[0001] The present invention relates to the field of vehicle technology, and in particular to a vehicle fault detection method, a vehicle fault detection device, an electronic device, and a computer-readable medium. Background Art

[0002] With the rapid development of new energy vehicles, the complexity of vehicle internal systems is also increasing. In related technologies, vehicles are equipped with high-voltage power systems that provide power for driving. To ensure vehicle safety, timely warnings of high-voltage power system failures are required.

[0003] When detecting high-voltage power system faults and issuing warnings, high-voltage warning systems typically rely on a small amount of information provided by one or a few signal sources, such as collision detection and battery thermal runaway information. However, due to the limited number of signal sources they rely on, the high-voltage warning system may erroneously trigger warnings without an obvious external collision accident or battery thermal runaway, resulting in a misjudgment of the fault. Furthermore, if the high-voltage power system fault cannot be directly detected by these dependent signal sources, the high-voltage warning system may not be able to respond to the fault in a timely manner, resulting in a delayed response and failing to fully ensure the safety of the vehicle and its occupants. Summary of the Invention

[0004] Embodiments of the present invention provide a vehicle fault detection method, device, electronic device, and computer-readable storage medium to address the problem that, due to the limited signal sources it relies on, a high-voltage early warning system may erroneously trigger an early warning in the absence of an obvious external collision accident or battery thermal runaway, leading to a misjudgment of the fault; if the fault of the high-voltage power system cannot be directly detected by these dependent signal sources, the high-voltage early warning system may not be able to respond to the fault in a timely manner, resulting in a response delay, and thus failing to fully ensure the safety of the vehicle and its occupants.

[0005] An embodiment of the present invention discloses a vehicle fault detection method, comprising:

[0006] Obtaining at least one operating indicator of a control system of a preset vehicle and historical operating data of the operating indicator; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamics control system; the operating indicator is associated with a probability of failure of a high-voltage power system of the vehicle;

[0007] Obtaining a covariance matrix of historical operating data of the operating indicator;

[0008] Based on the covariance matrix, obtaining an eigenvalue of any of the operating indicators; the eigenvalue is used to indicate the degree of correlation between the operating indicator and the fault possibility;

[0009] determining a target operating indicator from the at least one operating indicator according to the characteristic value;

[0010] Based on the current operating data of the target operating indicator, it is determined whether there is a failure risk in the high-voltage power system of the vehicle.

[0011] Optionally, the operating indicators of the vehicle control unit include at least one of the alarm level of the vehicle, whether the software update function of the vehicle is activated, and whether the vehicle diagnostic function of the vehicle is activated; the operating indicators of the battery management system include at least one of the voltage of the battery of the vehicle, whether the battery has a thermal runaway problem, and whether the battery has a collision damage problem; the operating indicators of the vehicle dynamic control system include at least whether the vehicle has been hit by a collision.

[0012] Optionally, the determining whether there is a failure risk in the high-voltage power system of the vehicle based on the current operating data of the target operating indicator includes:

[0013] Using a preset threshold generation model to obtain the operating data threshold of the target operating indicator;

[0014] If the current operating data exceeds the operating data threshold, it is confirmed that there is a failure risk in the high-voltage power system.

[0015] Optionally, the failure risk has at least one risk level; and the determining whether the high-voltage power system of the vehicle has a failure risk based on the current operating data of the target operating indicator includes:

[0016] For any of the risk levels, taking the risk level as the risk level to be processed;

[0017] Acquire level operation data of at least one target operation indicator corresponding to the risk level to be processed;

[0018] obtaining a difference between the current operation data and the level operation data;

[0019] If the difference between the current operation data and the level operation data is smaller than a preset data threshold, it is confirmed that the risk level of the failure risk of the high-voltage power system is the risk level to be processed.

[0020] Optionally, the method comprises:

[0021] Obtaining training operation data of the target operation indicator, a label of the training operation data, and a training operation data threshold of the training operation data; the label is used to indicate whether there is a failure risk in the high-voltage power system of the vehicle corresponding to the training operation data;

[0022] The training operation data, the label and the training operation data threshold are used to train a preset machine learning model to obtain the threshold generation model.

[0023] Optionally, before obtaining the covariance matrix of the historical operation data of the operation indicator, the method includes:

[0024] removing at least one of noise, outliers and discrete values ​​from the historical operating data; and / or,

[0025] The historical operating data is adjusted to be within a preset data range.

[0026] Optionally, the obtaining of at least one operating indicator of a system of a preset vehicle and historical operating data of the operating indicator includes:

[0027] The historical operation data of the operation indicator is obtained from a preset cloud server.

[0028] The embodiment of the present invention further discloses a vehicle fault detection device, comprising:

[0029] a historical operating data acquisition module, configured to acquire at least one operating indicator of a control system of a preset vehicle and historical operating data of the operating indicator; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamics control system; the operating indicator is associated with a probability of failure of the high-voltage power system of the vehicle;

[0030] A matrix acquisition module, used to obtain the covariance matrix of the historical operation data of the operation indicator;

[0031] an eigenvalue acquisition module, configured to acquire an eigenvalue of any of the operating indicators based on the covariance matrix; the eigenvalue is used to indicate a degree of correlation between the operating indicator and the fault probability;

[0032] a target operating indicator determination module, configured to determine a target operating indicator from the at least one operating indicator according to the characteristic value;

[0033] A fault risk judgment module is used to judge whether there is a fault risk in the high-voltage power system of the vehicle based on the current operating data of the target operating index.

[0034] Optionally, the operating indicators of the vehicle control unit include at least one of the alarm level of the vehicle, whether the software update function of the vehicle is activated, and whether the vehicle diagnostic function of the vehicle is activated; the operating indicators of the battery management system include at least one of the voltage of the battery of the vehicle, whether the battery has a thermal runaway problem, and whether the battery has a collision damage problem; the operating indicators of the vehicle dynamic control system include at least whether the vehicle has been hit by a collision.

[0035] Optionally, the fault risk judgment module includes:

[0036] A threshold acquisition submodule is used to obtain the operating data threshold of the target operating indicator by using a preset threshold generation model;

[0037] The fault risk confirmation submodule is configured to confirm that the high-voltage power system has a fault risk if the current operating data exceeds the operating data threshold.

[0038] Optionally, the fault risk has at least one risk level; the fault risk judgment module includes:

[0039] The risk level to be processed is used as a submodule, for taking any of the risk levels as the risk level to be processed;

[0040] A level operation data acquisition submodule, configured to acquire level operation data of at least one target operation indicator corresponding to the risk level to be processed;

[0041] a difference acquisition submodule, configured to acquire a difference between the current operation data and the level operation data;

[0042] The risk level confirmation submodule to be processed is used to confirm that the risk level of the failure risk of the high-voltage power system is the risk level to be processed if the difference between the current operation data and the level operation data is less than a preset data threshold.

[0043] Optionally, the device comprises:

[0044] a training data acquisition module, configured to acquire training operation data of the target operation indicator, a label of the training operation data, and a training operation data threshold of the training operation data; the label being configured to indicate whether the high-voltage power system of the vehicle corresponding to the training operation data has a failure risk;

[0045] A training module is used to train a preset machine learning model using the training operation data, the label and the training operation data threshold to obtain the threshold generation model.

[0046] Optionally, the device comprises:

[0047] a removal module, configured to remove at least one of noise, abnormal values, and discrete values ​​from the historical operation data; and / or,

[0048] The historical operating data is adjusted to be within a preset data range.

[0049] Optionally, the historical operation data acquisition module includes:

[0050] The historical operation data acquisition submodule is used to obtain the historical operation data of the operation indicator from a preset cloud server.

[0051] An embodiment of the present invention further discloses an electronic device, comprising a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus;

[0052] The memory is used to store computer programs;

[0053] The processor is configured to implement the method described in the embodiment of the present invention when executing the program stored in the memory.

[0054] The embodiments of the present invention further disclose one or more computer-readable media having instructions stored thereon. When executed by one or more processors, the processors are enabled to perform the method according to the embodiments of the present invention.

[0055] The embodiments of the present invention include the following advantages:

[0056] In an embodiment of the present invention, at least one operating indicator and historical operating data of a control system of a preset vehicle are obtained; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamic control system; the operating indicator is associated with the possibility of failure of the vehicle's high-voltage power system; a covariance matrix of the historical operating data of the operating indicator is obtained; an eigenvalue of any operating indicator is obtained based on the covariance matrix; the eigenvalue is used to indicate the degree of correlation between the operating indicator and the possibility of failure; a target operating indicator is determined from at least one operating indicator based on the eigenvalue; and based on the current operating data of the target operating indicator, it is determined whether the vehicle's high-voltage power system has a failure risk. By performing principal component analysis on the historical operating data of at least one operating indicator of the vehicle system to determine the target operating indicator, and performing a comprehensive analysis on the current operating data of multiple target operating indicators, it is possible to determine in advance whether the vehicle's high-voltage power system has a failure risk through cross-comprehensive analysis of multi-dimensional indicator data, even when the vehicle has no obvious external collision or thermal runaway, and to warn of potential high-voltage system failures, thereby reducing safety hazards caused by failures and improving the system's response speed and accuracy while ensuring the safety of the vehicle and its occupants. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] Figure 1 is a flowchart of the steps of a vehicle fault detection method provided in an embodiment of the present invention;

[0058] Figure 2 is a flowchart of the steps of another vehicle fault detection method provided in an embodiment of the present invention;

[0059] Figure 3 This is a structural block diagram of a vehicle fault detection device provided in an embodiment of the present invention;

[0060] Figure 4 is a block diagram of an electronic device provided in an embodiment of the present invention;

[0061] Figure 5 is a schematic diagram of a computer-readable medium provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0062] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the present invention is further described in detail below with reference to the accompanying drawings and specific embodiments.

[0063] Reference Figure 1 , shows a flowchart of a vehicle fault detection method provided in an embodiment of the present invention, which may specifically include the following steps:

[0064] Step 101: Acquire at least one operating indicator of a control system of a preset vehicle and historical operating data of the operating indicator; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamics control system; the operating indicator is associated with a probability of failure of the high-voltage power system of the vehicle;

[0065] In an embodiment of the present invention, a vehicle has a high-voltage power system. The presence of a high-voltage power system failure risk can be determined by determining whether the vehicle has been impacted and whether the battery has experienced thermal runaway. If the vehicle has been impacted and / or the battery has experienced thermal runaway, the vehicle's high-voltage power system is determined to be at risk of failure.

[0066] In an embodiment of the present invention, the vehicle also has at least one of a vehicle control unit (VCU), a battery management system (BMS), and a vehicle dynamic control system (VDC). The vehicle control unit is used to coordinate and manage all major subsystems of the vehicle. The battery management system is a system that monitors and manages the status of the battery pack, ensuring that the battery operates under safe, efficient, and reliable conditions. The vehicle dynamic control system is used to control the driving dynamics of the vehicle by adjusting the engine output and the braking system.

[0067] In an embodiment of the present invention, in the process of the vehicle control unit, battery management system and vehicle dynamic control system realizing their respective functions, the vehicle control unit, battery management system and vehicle dynamic control system each need to collect operating data of at least one operating indicator through sensors, all of which involve multiple key monitoring signals. When the vehicle's high-voltage power system is in normal operating state, the operating data of these operating indicators are stable; however, when the vehicle's high-voltage power system enters a potentially dangerous state, abnormal changes in the operating data of these operating indicators can reflect possible hidden dangers within the high-voltage power system. Therefore, these operating indicators are associated with the possibility of failure of the vehicle's high-voltage power system.

[0068] In an embodiment of the present invention, at least one operating indicator and historical operating data of the operating indicator of a vehicle control system may be obtained. The control system may include at least one of a vehicle control unit, a battery management system, and a vehicle dynamic control system.

[0069] In some embodiments of the present invention, obtaining at least one operating indicator of a system of a preset vehicle and historical operating data of the operating indicator includes:

[0070] The historical operation data of the operation indicator is obtained from a preset cloud server.

[0071] In an embodiment of the present invention, the vehicle can upload historical operating data of the operating indicators of the vehicle control unit, battery management system, and vehicle dynamic control system to the cloud server. Therefore, the historical operating data of the operating indicators of the vehicle control unit, battery management system, and vehicle dynamic control system can be obtained from the cloud server.

[0072] In some embodiments of the present invention, the operating indicators of the vehicle control unit include at least one of the alarm level of the vehicle, whether the software update function of the vehicle is activated, and whether the vehicle diagnostic function of the vehicle is activated; the operating indicators of the battery management system include at least one of the voltage of the battery of the vehicle, whether the battery has a thermal runaway problem, and whether the battery has a collision damage problem; the operating indicators of the vehicle dynamic control system include at least whether the vehicle has been hit by a collision.

[0073] In an embodiment of the present invention, the operating indicators of the vehicle control unit include at least one of the vehicle's alarm level, whether the vehicle's software update function is activated, and whether the vehicle's vehicle diagnostic function is activated; the operating indicators of the battery management system include at least one of the vehicle's battery voltage, whether the battery has a thermal runaway problem, and whether the battery has a collision damage problem; the operating indicators of the vehicle dynamic control system include at least whether the vehicle has been hit by a collision. It should be noted that the battery collision damage problem refers to the problem of battery damage caused by a collision with the vehicle. When the historical operating data of the operating indicators is stored in the cloud server, the historical operating data is hexadecimal data. After obtaining the data from the cloud server, the historical operating data needs to be converted into decimal data.

[0074] In a specific example, the historical operating data of the operating indicators of the first vehicle type are as follows:

[0075] 1) Historical operating data of operating indicators of the vehicle control unit of the first vehicle model:

[0076] The vehicle control unit reports that the vehicle's alarm level is 15, indicating a serious system failure;

[0077] The OTA (Over-The-Air) function is not activated, that is, the vehicle's software update function is not activated;

[0078] The OBD (On-Board Diagnostics) diagnostic function is not activated, that is, the vehicle diagnostic function of the vehicle is not activated.

[0079] 2) Historical operating data of the battery management system operating indicators of the first vehicle model:

[0080] The vehicle battery voltage is within the normal range (9V to 16V) and there is no voltage abnormality;

[0081] The vehicle's battery is in normal condition with no signs of thermal runaway;

[0082] No collision event related to internal code 1521 was detected, which means that the battery has no collision damage problem.

[0083] 3) Historical operating data of the operating indicators of the vehicle dynamics control system of the first vehicle model:

[0084] The vehicle's crash sensors did not detect a collision with the vehicle.

[0085] The historical operating data of the second model's operating indicators are as follows:

[0086] 1) Historical operating data of the operating indicators of the vehicle control unit of the second vehicle model:

[0087] The vehicle control unit reports a fault level of 15, indicating a serious fault in the system;

[0088] The OTA function is not activated, that is, the vehicle's software update function is not activated;

[0089] The OBD diagnostic function is not activated, that is, the vehicle diagnostic function of the vehicle is not activated.

[0090] 2) Historical operating data of the battery management system operating indicators of the second vehicle model:

[0091] The vehicle's battery voltage is normal;

[0092] The vehicle's battery is in normal condition with no signs of thermal runaway;

[0093] The BMS has no collision fault signal, which means that the battery has no collision damage problem.

[0094] 3) Historical operating data of the operating indicators of the vehicle dynamics control system of the second vehicle model:

[0095] The vehicle's crash sensors did not detect a collision with the vehicle.

[0096] The historical operating data of the operating indicators of the third model are as follows:

[0097] 1) Historical operating data of the operating indicators of the vehicle control unit of the third vehicle type:

[0098] The OTA update mode is not activated, that is, the vehicle's software update function is not activated;

[0099] The OBD function is not activated, that is, the vehicle diagnostic function of the vehicle is not activated.

[0100] 2) Historical operating data of the battery management system operating indicators of the third vehicle model:

[0101] The battery pack voltage is within the normal range;

[0102] The BMS status is normal, with no signs of thermal runaway;

[0103] The BMS did not detect the collision status, which means that the battery did not have any collision damage problem.

[0104] 3) Historical operating data of the operating indicators of the vehicle dynamics control system of the third vehicle type:

[0105] No collision signal;

[0106] The vehicle dynamics control system reports a system fault level of 15, indicating a serious fault.

[0107] In some embodiments of the present invention, before obtaining the covariance matrix of the historical operation data of the operation indicator, the method includes:

[0108] removing at least one of noise, outliers and discrete values ​​from the historical operating data; and / or,

[0109] The historical operating data is adjusted to be within a preset data range.

[0110] In an embodiment of the present invention, the historical operation data of the operation indicator may be preprocessed, including removing noise from the historical operation data, processing abnormal values ​​and discrete values ​​in the historical operation data, and standardizing the historical operation data.

[0111] Outliers are data that differ significantly from other data, and discrete values ​​are values ​​that are not continuous but occur in specific intervals or categories. Addressing outliers and discrete values ​​in historical data involves deleting or replacing them. Standardizing historical data involves adjusting it to a consistent range, ensuring that data is comparable across the same dimensions.

[0112] Step 102: Obtain the covariance matrix of the historical operation data of the operation indicator;

[0113] In an embodiment of the present invention, a principal component analysis (PCA) may be performed on the preprocessed historical operating data of the operating indicator to determine a target operating indicator among at least one operating indicator. Specifically, a covariance matrix of the historical operating data of the operating indicator may be calculated.

[0114] Step 103: obtaining an eigenvalue of any of the operating indicators based on the covariance matrix; the eigenvalue is used to indicate the degree of correlation between the operating indicator and the fault possibility;

[0115] In this embodiment of the present invention, the covariance matrix of historical operating data for operating indicators can be decomposed to obtain the eigenvalues ​​and eigencomponents of each operating indicator. The eigenvalue indicates the degree of correlation between the operating indicator and the probability of failure in the high-voltage power system; the larger the eigenvalue, the stronger the correlation. The eigenvector represents the direction of each operating indicator combination.

[0116] Step 104: determining a target operating indicator from the at least one operating indicator based on the characteristic value;

[0117] In the embodiment of the present invention, based on the size of the eigenvalues, the operating indicators corresponding to the first several largest eigenvalues ​​can be selected as target operating indicators. Typically, operating indicators with a correlation degree reaching a certain threshold (such as 80% or 90%) are selected.

[0118] In this embodiment of the present invention, principal component analysis is performed on the historical operating data of preprocessed operating indicators to screen out target operating indicators that are highly correlated with the probability of failure in the vehicle's high-voltage power system. These target operating indicators serve as key indicators for analyzing whether there is a risk of failure in the high-voltage power system.

[0119] Step 105 : Based on the current operating data of the target operating indicator, determine whether there is a failure risk in the high-voltage power system of the vehicle.

[0120] In an embodiment of the present invention, based on current operating data of at least one target operating indicator, it can be determined whether there is a failure risk in the high-voltage power system of the vehicle.

[0121] In an embodiment of the present invention, if there is a failure risk in the high-voltage power system of a vehicle, an early warning can be triggered and a visual report can be generated to display detailed information on the failure risk and the status of the vehicle and the high-voltage power system.

[0122] In some embodiments of the present invention, the determining whether the high-voltage power system of the vehicle has a failure risk based on the current operating data of the target operating indicator includes:

[0123] Using a preset threshold generation model to obtain the operating data threshold of the target operating indicator;

[0124] If the current operating data exceeds the operating data threshold, it is confirmed that there is a failure risk in the high-voltage power system.

[0125] In an embodiment of the present invention, the operating data threshold of the target operating indicator can be set based on the fault diagnosis logic of the vehicle's high-voltage power system. It should be noted that the threshold is determined based on empirical data under normal operating conditions.

[0126] In an embodiment of the present invention, a preset threshold generation model may also be used to obtain operating data thresholds for target operating indicators. If the current operating data of at least one target operating indicator exceeds the corresponding operating data threshold, it is determined that there is a risk of failure in the vehicle's high-voltage power system.

[0127] In a specific example, when the current operating data of multiple target operating indicators exceed the operating data threshold at the same time, and the vehicle has no obvious external collision or thermal runaway signs, that is, the vehicle's collision sensor has not detected that the vehicle has been hit, the vehicle's battery status is normal, and there are no signs of thermal runaway, then it is judged that the vehicle has a potential high-voltage failure risk, and an emergency high-voltage warning is immediately triggered to cut off the high-voltage power supply.

[0128] In some embodiments of the present invention, the method comprises:

[0129] Obtaining training operation data of the target operation indicator, a label of the training operation data, and a training operation data threshold of the training operation data; the label is used to indicate whether there is a failure risk in the high-voltage power system of the vehicle corresponding to the training operation data;

[0130] The training operation data, the label and the training operation data threshold are used to train a preset machine learning model to obtain the threshold generation model.

[0131] In an embodiment of the present invention, the training operation data of the target operation indicator, the label of the training operation data, and the training operation data threshold of the training operation data can be obtained, and the label can indicate whether the high-voltage power system of the vehicle corresponding to the training operation data has a fault risk. Then, the training operation data of the target operation indicator, the label of the training operation data, and the training operation data threshold of the training operation data can be used to train the preset machine learning model to obtain a threshold generation model. During the operation of the high-voltage power system, the operation data threshold of the target operation indicator can be continuously optimized through big data analysis. Specifically, the threshold generation model can be used to perform regression analysis on historical operation data, and the threshold of each target operation indicator can be dynamically adjusted to improve the accuracy and real-time performance of judging whether the high-voltage power system has a fault risk.

[0132] In an embodiment of the present invention, the threshold generation model can be updated in real time according to the fault diagnosis logic of the high-voltage power system and the changes in the operating data of the target operating indicators to ensure that it can adapt to changes in vehicle status under different environments.

[0133] In some embodiments of the present invention, the failure risk has at least one risk level; and determining whether the high-voltage power system of the vehicle has a failure risk based on the current operating data of the target operating indicator includes:

[0134] For any of the risk levels, taking the risk level as the risk level to be processed;

[0135] Acquire level operation data of at least one target operation indicator corresponding to the risk level to be processed;

[0136] obtaining a difference between the current operation data and the level operation data;

[0137] If the difference between the current operation data and the level operation data is smaller than a preset data threshold, it is confirmed that the risk level of the failure risk of the high-voltage power system is the risk level to be processed.

[0138] In an embodiment of the present invention, a cluster analysis can be performed on the target operating indicators to obtain characteristic data units. Specifically, in an embodiment of the present invention, there is at least one target operating indicator; the failure risk of the high-voltage power system has at least one risk level, including a high risk level, a medium risk level, and a low risk level.

[0139] For any risk level, that risk level can be considered as a pending risk level. For each pending risk level, each target operating indicator has corresponding level operating data. For each pending risk level, the level operating data for all target operating indicators constitutes a characteristic data unit. This characteristic data unit characterizes the level of failure risk in the high-voltage power system. Therefore, cluster analysis of target operating indicators can accurately identify which data combinations characterize the presence of failure risk in the high-voltage power system and the corresponding risk level.

[0140] If the current operating data exceeds the operating data threshold, the vehicle's high-voltage power system is at risk of failure. In this case, the risk level of the failure risk can be determined based on the current operating data of each target operating indicator. If the difference between the current operating data of the target operating indicator and the level operating data of the pending risk level is less than the preset data threshold, that is, the current operating data of the target operating indicator is close to the level operating data of the pending risk level, the high-voltage power system failure risk risk level is determined to be the pending risk level.

[0141] In this embodiment of the present invention, if the high-voltage power system's fault risk level is high, an early warning is triggered and a visual report is generated, displaying detailed information about the fault risk, the vehicle status, and the status of the high-voltage power system. It should be noted that this visual report is updated daily for vehicle operators to review and implement appropriate maintenance measures based on the risk assessment results.

[0142] In an embodiment of the present invention, when determining whether a high-voltage power system has a fault risk, operating data thresholds can be set for target operating indicators respectively, and then the historical operating data of the target operating indicators are clustered and analyzed to obtain a characteristic data set of the high-voltage power system fault.

[0143] The high-voltage power system has at least one risk level for failure risk, which may include a high risk level, a medium risk level, and a low risk level. The feature data set may include a feature data set for a high risk level, a feature data set for a medium risk level, and a feature data set for a low risk level. The feature data set may include a combination of level operating data for multiple target operating indicators identified by cluster analysis.

[0144] When determining whether a high-voltage power system has a high-risk level of failure risk, it is possible to determine whether the current operation data exceeds the operation data threshold based on the current operation data of the target operation indicator. If the current operation data exceeds the operation data threshold, and the difference between the current operation data and the level operation data in the high-risk level feature data set is less than the preset data threshold, it is confirmed that the high-voltage power system has a high-risk level of failure risk. The steps for determining whether a high-voltage power system has a medium-risk level and a low-risk level of failure risk are similar to the steps for determining whether a high-voltage power system has a high-risk level of failure risk, and the present invention will not be repeated here.

[0145] In an embodiment of the present invention, at least one operating indicator and historical operating data of a control system of a preset vehicle are obtained; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamic control system; the operating indicator is associated with the possibility of failure of the vehicle's high-voltage power system; a covariance matrix of the historical operating data of the operating indicator is obtained; an eigenvalue of any operating indicator is obtained based on the covariance matrix; the eigenvalue is used to indicate the degree of correlation between the operating indicator and the possibility of failure; a target operating indicator is determined from at least one operating indicator based on the eigenvalue; and based on the current operating data of the target operating indicator, it is determined whether the vehicle's high-voltage power system has a failure risk. By performing principal component analysis on the historical operating data of at least one operating indicator of the vehicle system to determine the target operating indicator, and performing a comprehensive analysis on the current operating data of multiple target operating indicators, it is possible to determine in advance whether the vehicle's high-voltage power system has a failure risk through cross-comprehensive analysis of multi-dimensional indicator data, even when the vehicle has no obvious external collision or thermal runaway, and to warn of potential high-voltage system failures, thereby reducing safety hazards caused by failures and improving the system's response speed and accuracy while ensuring the safety of the vehicle and its occupants.

[0146] In this embodiment of the present invention, principal component analysis, cluster analysis, and machine learning techniques are used to cross-analyze historical operating data for at least one operating indicator across multiple vehicle systems, accurately identifying target operating indicators associated with high-voltage system faults. This multi-dimensional analysis of target operating indicators significantly improves the accuracy and real-time nature of fault prediction, reducing the likelihood of false positives and missed alerts.

[0147] In this embodiment of the present invention, through continuous big data analysis and machine learning, the threshold generation model is continuously optimized to adapt to changes in vehicle status in different environments, ensuring the reliability and adaptability of the early warning system. As more data is accumulated and analyzed, the accuracy of high-voltage power system fault prediction will be further improved.

[0148] In an embodiment of the present invention, the method of obtaining target operating indicators and judging whether the system has a failure risk based on the current operating data of the target operating indicators is not only applicable to the high-voltage power system of new energy vehicles, but can also be extended to other core systems, such as the battery management system (BMS), the power transmission system (VCU), etc., to achieve comprehensive monitoring and early warning of the entire vehicle.

[0149] In this embodiment of the present invention, by collecting, analyzing, and triggering early warnings from current operating data, vehicle failure risks can be detected and responded to immediately, reducing safety hazards caused by delayed processing. Furthermore, the visual display and daily updates of data enable after-sales service personnel to promptly understand vehicle status, conduct proactive maintenance, and enhance the user experience.

[0150] Reference Figure 2 , shows a flowchart of the steps of another vehicle fault detection method provided in an embodiment of the present invention, which may specifically include the following steps:

[0151] Step 201: Data collection: The vehicle's control unit (VCU, BMS, VDC, etc.) uses sensors to collect key signal data in real time.

[0152] Step 202: Upload data to the cloud. Upload the data stored on the vehicle to the cloud server.

[0153] Step 203: Data parsing. The cloud data is downloaded to the local server and parsed from hexadecimal to decimal.

[0154] Step 204: Data processing: decimal data labeling.

[0155] Step 205: Algorithm model: Build the algorithm model according to the emergency high-voltage diagnosis logic.

[0156] Step 206: Sample Verification: Based on the massive vehicle data in the database, the output of the algorithm model is compared to perform data inference verification and threshold tuning.

[0157] Step 207: Data product: A visual report presents the final data product.

[0158] It should be noted that for the sake of simplicity, the method embodiments are described as a series of actions. However, those skilled in the art should be aware that the embodiments of the present invention are not limited by the order of the actions described, because according to the embodiments of the present invention, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in this specification are all preferred embodiments, and the actions involved are not necessarily required by the embodiments of the present invention.

[0159] Reference Figure 3 , shows a structural block diagram of a vehicle fault detection device provided in an embodiment of the present invention, which may specifically include the following modules:

[0160] A historical operating data acquisition module 301 is configured to acquire at least one operating indicator of a control system of a preset vehicle and historical operating data of the operating indicator; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamics control system; the operating indicator is associated with a probability of failure of the high-voltage power system of the vehicle;

[0161] A matrix acquisition module 302 is used to obtain the covariance matrix of the historical operation data of the operation indicator;

[0162] The eigenvalue acquisition module 303 is configured to acquire an eigenvalue of any of the operating indicators based on the covariance matrix; the eigenvalue is used to indicate the degree of correlation between the operating indicator and the fault probability;

[0163] a target operating indicator determining module 304, configured to determine a target operating indicator from the at least one operating indicator according to the characteristic value;

[0164] The fault risk judgment module 305 is used to judge whether there is a fault risk in the high-voltage power system of the vehicle based on the current operating data of the target operating index.

[0165] In an optional embodiment of the present invention, the operating indicators of the vehicle control unit include at least one of the alarm level of the vehicle, whether the software update function of the vehicle is activated, and whether the vehicle diagnostic function of the vehicle is activated; the operating indicators of the battery management system include at least one of the voltage of the battery of the vehicle, whether the battery has a thermal runaway problem, and whether the battery has a collision damage problem; the operating indicators of the vehicle dynamic control system include at least whether the vehicle has been hit by a collision.

[0166] In an optional embodiment of the present invention, the fault risk judgment module includes:

[0167] A threshold acquisition submodule is used to obtain the operating data threshold of the target operating indicator by using a preset threshold generation model;

[0168] The fault risk confirmation submodule is configured to confirm that the high-voltage power system has a fault risk if the current operating data exceeds the operating data threshold.

[0169] In an optional embodiment of the present invention, the fault risk has at least one risk level; the fault risk judgment module includes:

[0170] The risk level to be processed is used as a submodule, for taking any of the risk levels as the risk level to be processed;

[0171] A level operation data acquisition submodule, configured to acquire level operation data of at least one target operation indicator corresponding to the risk level to be processed;

[0172] a difference acquisition submodule, configured to acquire a difference between the current operation data and the level operation data;

[0173] The risk level confirmation submodule to be processed is used to confirm that the risk level of the failure risk of the high-voltage power system is the risk level to be processed if the difference between the current operation data and the level operation data is less than a preset data threshold.

[0174] In an optional embodiment of the present invention, the device includes:

[0175] a training data acquisition module, configured to acquire training operation data of the target operation indicator, a label of the training operation data, and a training operation data threshold of the training operation data; the label being configured to indicate whether the high-voltage power system of the vehicle corresponding to the training operation data has a failure risk;

[0176] A training module is used to train a preset machine learning model using the training operation data, the label and the training operation data threshold to obtain the threshold generation model.

[0177] In an optional embodiment of the present invention, the device includes:

[0178] a removal module, configured to remove at least one of noise, abnormal values, and discrete values ​​from the historical operation data; and / or,

[0179] The historical operating data is adjusted to be within a preset data range.

[0180] In an optional embodiment of the present invention, the historical operation data acquisition module includes:

[0181] The historical operation data acquisition submodule is used to obtain the historical operation data of the operation indicator from a preset cloud server.

[0182] As for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0183] In addition, an embodiment of the present invention further provides an electronic device, such as Figure 4 As shown, it includes a processor 401, a communication interface 402, a memory 403 and a communication bus 404, wherein the processor 401, the communication interface 402, and the memory 403 communicate with each other through the communication bus 404.

[0184] Memory 403, used for storing computer programs;

[0185] The processor 401 is configured to execute the program stored in the memory 403 by performing the following steps:

[0186] Obtaining at least one operating indicator of a control system of a preset vehicle and historical operating data of the operating indicator; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamics control system; the operating indicator is associated with a probability of failure of a high-voltage power system of the vehicle;

[0187] Obtaining a covariance matrix of historical operating data of the operating indicator;

[0188] Based on the covariance matrix, obtaining an eigenvalue of any of the operating indicators; the eigenvalue is used to indicate the degree of correlation between the operating indicator and the fault possibility;

[0189] determining a target operating indicator from the at least one operating indicator according to the characteristic value;

[0190] Based on the current operating data of the target operating indicator, it is determined whether there is a failure risk in the high-voltage power system of the vehicle.

[0191] In an optional embodiment of the present invention, the operating indicators of the vehicle control unit include at least one of the alarm level of the vehicle, whether the software update function of the vehicle is activated, and whether the vehicle diagnostic function of the vehicle is activated; the operating indicators of the battery management system include at least one of the voltage of the battery of the vehicle, whether the battery has a thermal runaway problem, and whether the battery has a collision damage problem; the operating indicators of the vehicle dynamic control system include at least whether the vehicle has been hit by a collision.

[0192] In an optional embodiment of the present invention, the determining whether there is a failure risk in the high-voltage power system of the vehicle based on the current operating data of the target operating indicator includes:

[0193] Using a preset threshold generation model to obtain the operating data threshold of the target operating indicator;

[0194] If the current operating data exceeds the operating data threshold, it is confirmed that there is a failure risk in the high-voltage power system.

[0195] In an optional embodiment of the present invention, the failure risk has at least one risk level; and judging whether the high-voltage power system of the vehicle has a failure risk based on the current operating data of the target operating indicator includes:

[0196] For any of the risk levels, taking the risk level as the risk level to be processed;

[0197] Acquire level operation data of at least one target operation indicator corresponding to the risk level to be processed;

[0198] obtaining a difference between the current operation data and the level operation data;

[0199] If the difference between the current operation data and the level operation data is smaller than a preset data threshold, it is confirmed that the risk level of the failure risk of the high-voltage power system is the risk level to be processed.

[0200] In an optional embodiment of the present invention, the method includes:

[0201] Obtaining training operation data of the target operation indicator, a label of the training operation data, and a training operation data threshold of the training operation data; the label is used to indicate whether there is a failure risk in the high-voltage power system of the vehicle corresponding to the training operation data;

[0202] The training operation data, the label and the training operation data threshold are used to train a preset machine learning model to obtain the threshold generation model.

[0203] In an optional embodiment of the present invention, before obtaining the covariance matrix of the historical operation data of the operation indicator, the method includes:

[0204] removing at least one of noise, outliers and discrete values ​​from the historical operating data; and / or,

[0205] The historical operating data is adjusted to be within a preset data range.

[0206] In an optional embodiment of the present invention, the obtaining of at least one operating indicator of a system of a preset vehicle and historical operating data of the operating indicator includes:

[0207] The historical operation data of the operation indicator is obtained from a preset cloud server.

[0208] The communication bus mentioned in the terminal can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. This communication bus can be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is used in the figure, but this does not mean that there is only one bus or only one type of bus.

[0209] The communication interface is used for communication between the above terminal and other devices.

[0210] The memory may include random access memory (RAM) or non-volatile memory, such as at least one disk storage. Alternatively, the memory may be at least one storage device located away from the processor.

[0211] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, and discrete hardware components.

[0212] like Figure 5 As shown, in another embodiment provided by the present invention, a computer-readable storage medium 501 is also provided, in which instructions are stored. When the computer-readable storage medium 501 is run on a computer, the computer executes a vehicle fault detection method described in the above embodiment.

[0213] In another embodiment of the present invention, a computer program product including instructions is provided. When the computer program product is run on a computer, the computer is enabled to execute the vehicle fault detection method described in the above embodiment.

[0214] In the above embodiments, all or part of the embodiments can be implemented by software, hardware, firmware, or any combination thereof. When implemented using software, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via a wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) method. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more available media. The available medium can be a magnetic medium (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)).

[0215] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply the existence of any such actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article, or device comprising a series of elements includes not only those elements, but also other elements not explicitly listed, or elements inherent to such process, method, article, or device. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not exclude the presence of other identical elements in the process, method, article, or device comprising the element.

[0216] Each embodiment in this specification is described in a related manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiment is generally similar to the method embodiment, so the description is relatively simple. For related parts, refer to the description of the method embodiment.

[0217] The above description is only a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent replacements, improvements, etc. made within the spirit and principles of the present invention are included in the scope of protection of the present invention.

Claims

1. A vehicle fault detection method, characterized in that: include: Obtaining at least one operating indicator of a control system of a preset vehicle and historical operating data of the operating indicator; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamics control system; the operating indicator is associated with a probability of failure of a high-voltage power system of the vehicle; Obtaining a covariance matrix of historical operating data of the operating indicator; Based on the covariance matrix, obtaining an eigenvalue of any of the operating indicators; The characteristic value is used to indicate the degree of correlation between the operating indicator and the fault possibility; determining a target operating indicator from the at least one operating indicator according to the characteristic value; Based on the current operating data of the target operating indicator, it is determined whether there is a failure risk in the high-voltage power system of the vehicle.

2. The method according to claim 1, characterized in that The operating indicators of the vehicle control unit include at least one of the alarm level of the vehicle, whether the software update function of the vehicle is activated, and whether the vehicle diagnostic function of the vehicle is activated; the operating indicators of the battery management system include at least one of the voltage of the battery of the vehicle, whether the battery has a thermal runaway problem, and whether the battery has a collision damage problem; the operating indicators of the vehicle dynamic control system include at least whether the vehicle has been hit by a collision.

3. The method according to claim 1, characterized in that The determining, based on the current operating data of the target operating indicator, whether there is a failure risk in the high-voltage power system of the vehicle includes: Using a preset threshold generation model to obtain the operating data threshold of the target operating indicator; If the current operating data exceeds the operating data threshold, it is confirmed that there is a failure risk in the high-voltage power system.

4. The method according to claim 1, wherein The failure risk has at least one risk level; and judging whether the high-voltage power system of the vehicle has a failure risk based on the current operating data of the target operating indicator includes: For any of the risk levels, taking the risk level as the risk level to be processed; Acquire level operation data of at least one target operation indicator corresponding to the risk level to be processed; obtaining a difference between the current operation data and the level operation data; If the difference between the current operation data and the level operation data is smaller than a preset data threshold, it is confirmed that the risk level of the failure risk of the high-voltage power system is the risk level to be processed.

5. The method according to claim 3, characterized in that The method comprises: Obtaining training operation data of the target operation indicator, a label of the training operation data, and a training operation data threshold of the training operation data; the label is used to indicate whether there is a failure risk in the high-voltage power system of the vehicle corresponding to the training operation data; The training operation data, the label and the training operation data threshold are used to train a preset machine learning model to obtain the threshold generation model.

6. The method according to claim 1, characterized in that Before obtaining the covariance matrix of the historical operation data of the operation indicator, the method includes: removing at least one of noise, abnormal values, and discrete values ​​from the historical operating data; and / or adjusting the historical operating data to be within a preset data range.

7. The method according to claim 1, characterized in that The obtaining of at least one operating indicator of a system of a preset vehicle and historical operating data of the operating indicator includes: The historical operation data of the operation indicator is obtained from a preset cloud server.

8. A vehicle fault detection device, characterized in that: include: a historical operating data acquisition module, configured to acquire at least one operating indicator of a control system of a preset vehicle and historical operating data of the operating indicator; the control system includes at least one of a vehicle control unit, a battery management system, and a vehicle dynamics control system; the operating indicator is associated with a probability of failure of the high-voltage power system of the vehicle; A matrix acquisition module, used to obtain the covariance matrix of the historical operation data of the operation indicator; An eigenvalue acquisition module, configured to acquire an eigenvalue of any of the operating indicators based on the covariance matrix; The characteristic value is used to indicate the degree of correlation between the operating indicator and the fault possibility; a target operating indicator determination module, configured to determine a target operating indicator from the at least one operating indicator according to the characteristic value; A fault risk judgment module is used to judge whether there is a fault risk in the high-voltage power system of the vehicle based on the current operating data of the target operating index.

9. An electronic device, characterized in that: comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other via the communication bus; The memory is used to store computer programs; The processor is configured to implement the method according to any one of claims 1 to 7 when executing a program stored in the memory.

10. One or more computer-readable media having instructions stored thereon, which, when executed by one or more processors, cause the processors to perform the method of any one of claims 1-7.

Images