Vehicle fault identification and diagnosis method, device, equipment and storage medium

Abstract

The present invention discloses a vehicle fault identification and diagnosis method, device, equipment and storage medium, belonging to the field of vehicle fault diagnosis technology. This method first constructs the vehicle's operating characteristics and working condition changes when the fault occurs through actual fault cases, obtains a mapping table that associates the fault with the vehicle's operating characteristics, and then obtains the vehicle's state characteristics and working conditions through real-time monitoring of the vehicle's state. Then, based on the real-time data and the mapping table, the vehicle's state characteristic data is derived and compared with the reference data in the table to identify potential faults. Through real-time monitoring and intelligent analysis, this solution realizes the early identification and accurate diagnosis of potential faults of new energy vehicles, significantly improves the accuracy and early warning capabilities of fault detection, and enhances the safety of vehicle operation and the level of intelligent maintenance.

Description

Technical Field

[0001] The present invention relates to the technical field of vehicle fault diagnosis, and in particular to a vehicle fault identification and diagnosis method, device, equipment and storage medium. Background Art

[0002] With the rapid development of technology, the automotive industry is undergoing unprecedented transformation. New energy vehicles, with their clean energy, low carbon emissions, and advanced intelligence, have become a key development direction for the global automotive industry. These vehicles integrate a large number of advanced electronic components and complex control systems, not only improving energy efficiency and driving experience but also contributing to environmental protection and sustainable development. However, with the increasing level of electronics and intelligence, new challenges are emerging in fault diagnosis and maintenance of new energy vehicles.

[0003] The widespread adoption of new energy vehicles has significantly increased the complexity of electronic components and control systems. The proper functioning of these systems is crucial to vehicle performance. Minor faults, while not easily noticeable to the driver, can impact vehicle safety and reliability. Currently, most vehicles have limited self-diagnostic capabilities, often requiring specialized maintenance personnel to use complex testing tools to identify faults. This reliance on specialized technicians is not only inefficient but can also lead to more serious consequences due to delayed fault detection.

[0004] Therefore, how to develop an efficient fault diagnosis method to monitor the complex electronic devices and control systems of new energy vehicles in real time, accurately identify and warn of minor faults, and thus improve the safety and reliability of the vehicle has become a technical problem to be solved in this field. Summary of the Invention

[0005] The main purpose of the present invention is to provide a vehicle fault identification and diagnosis method, device, equipment and storage medium, aiming to solve the technical problem of how to develop an efficient fault diagnosis method to monitor the complex electronic devices and control systems of new energy vehicles in real time, accurately identify and warn of minor faults, thereby improving the safety and reliability of the vehicle.

[0006] To achieve the above objectives, the present invention provides a vehicle fault identification and diagnosis method, the vehicle fault identification and diagnosis method comprising:

[0007] According to the real-time operation data, the vehicle status characteristic data and vehicle working condition are obtained;

[0008] Obtaining vehicle state reference data according to the vehicle operating condition and fault-operation characteristic mapping table;

[0009] A fault diagnosis result is obtained based on the vehicle state characteristic data and the vehicle state reference data.

[0010] Optionally, before obtaining the vehicle state characteristic data and the vehicle operating condition according to the real-time operating data, the method further includes:

[0011] Obtain a fault case dataset;

[0012] Dividing the fault case data set to obtain fault vehicle operation data divided according to fault type;

[0013] Inputting the fault vehicle operation data into a fault analysis model for analysis to obtain operation status characteristic data corresponding to the fault type;

[0014] A fault-operation feature mapping table is obtained according to the operating state feature data and the fault type.

[0015] Optionally, obtaining a fault-operation feature mapping table according to the operation status feature data and the fault type includes:

[0016] Determine the vehicle operating conditions within a preset time period before the fault occurs in each case based on the fault vehicle operating data;

[0017] determining a characteristic operating condition according to a proportion of the vehicle operating condition;

[0018] The fault-operation characteristic mapping table is constructed according to the characteristic working condition, the operating state characteristic data and the fault type.

[0019] Optionally, obtaining vehicle status characteristic data and vehicle operating conditions based on real-time operating data includes:

[0020] determining a vehicle operating condition based on the real-time operating data;

[0021] Determining characteristic data items according to the vehicle operating condition and fault-operation characteristic mapping table;

[0022] Based on the real-time operation data of the vehicle, data derivation is performed according to the characteristic data items to obtain vehicle status characteristic data.

[0023] Optionally, obtaining vehicle state reference data according to the vehicle operating condition and fault-operation characteristic mapping table includes:

[0024] Determining operating state characteristic data corresponding to the vehicle operating condition according to the fault-operation characteristic mapping table;

[0025] Obtaining a characteristic data reference range according to the operating status characteristic data;

[0026] The characteristic data reference range is used as the vehicle state reference data.

[0027] Optionally, obtaining a fault diagnosis result according to the vehicle state characteristic data and the vehicle state reference data includes:

[0028] Comparing each feature data item in the vehicle state reference data with a corresponding reference interval in the vehicle state reference data, determining a feature data item located in the reference interval, and using the feature data item located in the reference interval as mapping data;

[0029] determining, based on the fault-operation characteristic mapping table, a fault event including the mapping data;

[0030] Calculating the degree of overlap between the mapping data and the characteristic data corresponding to each fault event;

[0031] A fault diagnosis result is obtained according to the overlap degree of the characteristic data.

[0032] Optionally, obtaining a fault diagnosis result according to the characteristic data overlap includes:

[0033] The fault event corresponding to the feature data overlap being greater than the first overlap judgment threshold is regarded as a potential fault event;

[0034] If the number of potential fault events is less than the event concurrency threshold, it is determined that the current vehicle is in a fault-free state;

[0035] If the number of potential fault events is greater than the event concurrency threshold, it is determined that the current vehicle is in a critical fault state;

[0036] If the degree of overlap of the characteristic data of any of the potential fault events is greater than a second overlap determination threshold, it is determined that the current vehicle has experienced the potential fault.

[0037] Furthermore, to achieve the above-mentioned objectives, the present invention provides a vehicle fault identification and diagnosis device, comprising:

[0038] The vehicle data processing module is used to obtain vehicle status characteristic data and vehicle operating conditions based on real-time operating data;

[0039] A reference data generation module, configured to obtain vehicle status reference data based on the vehicle operating condition and fault-operation characteristic mapping table;

[0040] The fault diagnosis module is used to obtain a fault diagnosis result based on the vehicle state characteristic data and the vehicle state reference data.

[0041] In addition, to achieve the above-mentioned purpose, the present invention provides a vehicle fault identification and diagnosis device, which includes: a memory, a processor, and a vehicle fault identification and diagnosis program stored on the memory and executable on the processor, wherein the vehicle fault identification and diagnosis program is configured to implement the steps of the vehicle fault identification and diagnosis method.

[0042] In addition, to achieve the above-mentioned purpose, the present invention provides a storage medium, on which a vehicle fault identification and diagnosis program is stored. When the vehicle fault identification and diagnosis program is executed by a processor, the steps of the vehicle fault identification and diagnosis method are implemented.

[0043] This method first uses actual fault cases to construct a mapping table that correlates faults with vehicle operating characteristics and operating conditions. It then uses real-time vehicle status monitoring to determine vehicle status characteristics and operating conditions. Based on this real-time data and the mapping table, it derives vehicle status characteristic data and compares it with reference data in the table to identify potential faults. Through real-time monitoring and intelligent analysis, this solution enables early identification and accurate diagnosis of potential faults in new energy vehicles, significantly improving fault detection accuracy and early warning capabilities, and enhancing vehicle operational safety and intelligent maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] 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.

[0045] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0046] Figure 1 This is a flow chart of the first embodiment of the vehicle fault identification and diagnosis method of the present application;

[0047] Figure 2 This is a flow chart of a second embodiment of the vehicle fault identification and diagnosis method of the present application;

[0048] Figure 3 This is a flow chart of the third embodiment of the vehicle fault identification and diagnosis method of the present application;

[0049] Figure 4 This is a schematic diagram of the functional modules of the vehicle fault identification and diagnosis device of this application;

[0050] Figure 5It is a structural diagram of the terminal device of the hardware operating environment involved in the embodiment of the present application.

[0051] The purpose, features and advantages of the present invention will be further described with reference to the accompanying drawings and in conjunction with the embodiments. DETAILED DESCRIPTION

[0052] It should be understood that the specific embodiments described herein are merely used to explain the technical solutions of the present application and are not intended to limit the present application.

[0053] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0054] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication, and program execution functions, such as a tablet computer, personal computer, mobile phone, etc., or an electronic device capable of performing the above functions, such as a vehicle fault identification and diagnosis device. This embodiment and the following embodiments will be described below using the vehicle fault identification and diagnosis device as an example.

[0055] The present invention provides a method for identifying and diagnosing vehicle faults. Figure 1 , Figure 1 This is a flowchart of the first embodiment of the present application.

[0056] In this embodiment, the vehicle fault identification and diagnosis method includes:

[0057] Step S10: Obtain vehicle status characteristic data and vehicle operating conditions based on real-time operating data.

[0058] It should be noted that real-time operating data usually includes but is not limited to parameters such as speed, acceleration, engine speed, temperature, pressure, torque, etc. These are parameters for evaluating vehicle status and can be read directly from the vehicle system. Further processing based on these basic operating data can obtain characteristic data that can express the current overall operating status of the vehicle.

[0059] In one embodiment, obtaining vehicle status characteristic data and vehicle operating conditions based on real-time operating data includes: determining the vehicle operating conditions based on the real-time operating data; determining characteristic data items based on the vehicle operating conditions and fault-operation characteristic mapping table; and deriving data according to the characteristic data items based on the real-time vehicle operating data to obtain vehicle status characteristic data.

[0060] It should be understood that the vehicle operating conditions here are relatively broadly defined. Under normal circumstances, the vehicle operating conditions include operating states or modes within a specific time, such as idling, constant speed driving, acceleration, deceleration, climbing, downhill, etc., and in the further expansion of the concept of operating conditions, for example, switching between two normal operating conditions, this switching itself is a working condition, such as switching from constant speed motion to accelerated motion, which normally only includes acceleration conditions and constant speed conditions, while this embodiment also considers the existence of a constant speed to acceleration condition, because this detailed working condition division method can more easily lock in some potential characteristics when a fault event occurs.

[0061] It is understandable that since most of the parameters in the vehicle system are relatively basic data, such as vehicle speed, rotational speed, torque, temperature, etc., which are all directly read from sensors or systems, the vehicle's acceleration, rotational speed change rate, stress in the transmission system, temperature rise rate, etc. need to be derived in a corresponding way. These derived high-order data can reflect the changing trend of the vehicle status or performance indicators under specific conditions, so that these data can be used as characteristic data that can represent the vehicle status.

[0062] Step S20: Obtain vehicle status reference data according to the vehicle operating condition and fault-operation characteristic mapping table.

[0063] It should be noted that vehicle status reference data is based on the normal or expected operating parameter ranges recorded in the fault-operational characteristic mapping table. This data serves as a benchmark for assessing whether the current vehicle status is normal. Vehicle status reference data includes both basic and derived data. Derivative data, in particular, is more representative than basic data. By comparing it with reference data, deviations in vehicle performance can be quickly identified, providing a basis for fault diagnosis.

[0064] In one embodiment, obtaining vehicle status reference data based on the vehicle operating condition and fault-operation characteristic mapping table includes: determining the operation status characteristic data corresponding to the vehicle operating condition based on the fault-operation characteristic mapping table; obtaining a characteristic data reference range based on the operation status characteristic data; and using the characteristic data reference range as the vehicle status reference data.

[0065] It is understandable that the parameter ranges recorded in the fault-operation characteristic mapping table may include multiple levels, such as normal range, warning range, and fault range, so that problems of different levels can be appropriately identified and handled. The reference data in the table provides a quantitative basis for fault diagnosis, which helps to improve the accuracy of diagnosis and reduce the possibility of misdiagnosis.

[0066] Step S30: Obtaining a fault diagnosis result based on the vehicle state characteristic data and the vehicle state reference data.

[0067] It should be noted that fault diagnosis is a data-driven process. Through in-depth analysis of vehicle status characteristic data, deviations from reference data can be identified, thereby inferring potential faults. Because there is a certain degree of data overlap between reference data and actual data, with some items having higher overlap and others having lower overlap, the probability of recurrence of fault events corresponding to items with higher overlap is higher on the current vehicle, while the probability of recurrence of fault events corresponding to items with lower overlap is lower.

[0068] It is understandable that fault diagnosis is not a one-time process but an ongoing process. As the vehicle's operating status changes, the diagnostic results may need to be dynamically updated, and the credibility of the diagnostic results is also related to the degree of overlap of the actual data. If more than half or even three-quarters of the sensors or parameter readings consistently indicate the same problem, this will enhance the credibility of the fault diagnosis results. If the degree of overlap has never exceeded half, it means that even if this type of data points to a certain type of fault, the probability of its occurrence is still very small.

[0069] It should be understood that during the comparison process, appropriate thresholds need to be set to determine whether the data deviation is large enough to indicate a fault. In addition, multiple diagnostic logic needs to be applied to handle situations where the same fault may be caused by multiple causes, or where one cause may cause multiple faults.

[0070] This embodiment provides a vehicle fault identification and diagnosis method. This embodiment obtains vehicle status characteristic data and vehicle operating conditions by analyzing the real-time operating data of the current vehicle; obtains vehicle status reference data based on the vehicle operating condition and fault-operation characteristic mapping table; obtains fault diagnosis results based on the vehicle status characteristic data and vehicle status reference data. The diagnosis results are not only used to identify the current fault, but also should support predictive maintenance to prevent possible problems in the future. For example, when the reference data overlap of a certain fault event continues to rise, it means that this fault is likely to occur in subsequent use.

[0071] In summary, this application first constructs the vehicle's operating characteristics and operating condition changes when a fault occurs through actual fault cases, obtaining a mapping table that associates faults with vehicle operating characteristics. It then obtains vehicle status characteristics and operating conditions through real-time monitoring of the vehicle's status. Based on the real-time data and the mapping table, it derives vehicle status characteristic data and compares it with reference data in the table to identify potential faults. Through real-time monitoring and intelligent analysis, this solution achieves early identification and accurate diagnosis of potential faults in new energy vehicles, significantly improving the accuracy and early warning capabilities of fault detection, and enhancing the safety of vehicle operation and the level of intelligent maintenance.

[0072] Reference Figure 2 , Figure 2 This is a flow chart of the second embodiment of the vehicle fault identification and diagnosis method of the present application. Based on the above-mentioned first embodiment, the second embodiment of the vehicle fault identification and diagnosis method of the present application is proposed.

[0073] In this embodiment, before step S10, the following steps are further included:

[0074] Step S001: Acquire a fault case data set, divide the fault case data set, and obtain fault vehicle operation data divided according to fault type.

[0075] It should be noted that due to the large number and complex structure of electronic components inside new energy vehicles, most failure events with the same manifestation may be caused by completely different reasons. For example, the circuit board in the vehicle system has a large number of electronic components. Therefore, after the components in two completely different positions fail, the circuit board may not be used normally. Therefore, if we only look at the failure effect of the circuit board being unusable, the same failure case corresponds to multiple different faulty components or failure causes at the same time. Therefore, before machine learning, cases with the same fault manifestation are divided into one category, and then grouped for machine learning. Then, big data analysis is used to automatically generate the operating characteristics formed by various parameters in the vehicle system under the same fault type.

[0076] It should be understood that due to the limitations of case data, some fault characteristics are relatively prominent, and the fault causes are very obvious. Fault types will be divided more finely, which makes it relatively convenient to determine the fault causes. However, for some faults with fewer cases and relatively general causes, they may be classified into broader fault categories, resulting in the inability to immediately determine the specific fault causes during fault analysis.

[0077] Step S002: Inputting the operating data of the faulty vehicle into a fault analysis model for analysis to obtain operating status characteristic data corresponding to the fault type.

[0078] It should be noted that most faults do not affect the normal operation of the vehicle. For example, when a vehicle's fault manifests itself as uneven acceleration or deceleration, if the driver does not feel this situation strongly, then the fault may not be handled in a timely manner. In principle, this situation should be caused by a failure of a sensor related to speed data in the drive system. Conventional manual detection methods can only detect these sensors one by one. For the fault analysis model after machine learning, as long as the real-time sensor data of the vehicle system is imported into it for data analysis, it can quickly determine the sensor data that is different from the normal operating state, indicating that this sensor has a greater probability of failure at this time; on the other hand, for some situations with the same appearance but completely different principles, for example, the cause of the failure includes: fuel supply problems (such as fuel pump failure, fuel filter blockage), ignition system failure (such as spark plug damage, ignition coil failure), sensor failure (such as crankshaft position sensor failure), intake system problem (such as throttle failure or air flow meter problem), etc., and the specific problem cannot be determined only from the fault symptoms. However, for the fault analysis model, based on real-time vehicle operation data, the parameters of each system operation can be compared with the fault case or the operation data under normal circumstances to determine the cause of the failure.

[0079] It should be understood that since the data from various systems in the vehicle do not necessarily point directly to the cause of the fault, it is necessary to use the existing vehicle operation data for data derivation. The cause of the vehicle failure can be determined based on the results of the data derivation. For example, when the vehicle's transmission system fails, if the vehicle's real-time operation data includes the transmission torque and speed, the stress level of the contact surface when the clutch is currently working can be obtained based on the existing torque and speed data, and the working state of the clutch can be judged to be relatively tight or loose.

[0080] Step S003: Determine the vehicle operating conditions within a preset time before the fault occurs in each case based on the fault vehicle operating data.

[0081] It should be noted that by analyzing the operating conditions in the period preceding a fault, specific operating conditions that may have led to the fault can be identified, helping to predict the likelihood of future faults under similar operating conditions, such as whether the fault was triggered by specific operations, loads, or environmental conditions. For example, if a vehicle experiences frequent rapid acceleration and deceleration and the automatic transmission experiences shifting difficulties, the pre-fault operating condition analysis may reveal that the transmission was operating under high load and high-frequency shifting, leading to internal wear or overheating. These two conditions have a clear causal relationship. When other vehicles identify such operating conditions, they will determine in advance that if the current vehicle experiences a fault, the fault is likely to be caused by internal wear or overheating in the shifting system.

[0082] It is understandable that by collecting and analyzing the working conditions before failure in different cases, the patterns and regularities of failure occurrence can be discovered, providing a basis for fault classification and diagnosis.

[0083] Step S004: Determine a characteristic operating condition based on the proportion of the vehicle operating condition.

[0084] It should be noted that for the same type of fault cases, the types of operating conditions that occurred before the fault occurred are not necessarily exactly the same, but through statistical analysis, we can find out the operating conditions that appear more frequently, and these operating conditions can be defined as characteristic operating conditions. By identifying the various operating conditions that the vehicle was in before the fault occurred, such as idling, constant speed, sudden acceleration, sudden deceleration, etc., and then recording the time of each operating condition from the perspective of the total amount of time, and then accumulating the time of each operating condition in the same case, it can be determined that the operating condition type with the largest proportion is the characteristic operating condition. Another idea is to count the operating condition types that appear in most cases as characteristic operating conditions. If this operating condition appears in almost all cases of a fault type, then even if the overall duration accounts for a small proportion, it should still be considered that this operating condition has a certain degree of representativeness.

[0085] It should be understood that the operating condition data for a period of time before the failure is extracted from each case of the same fault cause, and the time window for each fault case when it is extracted should be consistent. For example, the operating data extracted from each case is 5 minutes or 10 minutes before the failure occurs. This helps to ensure the accuracy of the characteristic operating condition selection.

[0086] Step S005: constructing the fault-operation characteristic mapping table according to the characteristic working condition, the operating state characteristic data and the fault type.

[0087] It should be noted that after data preparation is complete, a fault-operational characteristic mapping table is available, which includes characteristic operating conditions, operating status characteristic data, and fault types. For vehicles of the same type, when the vehicle's real-time operating condition matches the characteristic operating condition in the table, this can be used as an anchor point to obtain the relevant operating parameters of the current vehicle. This is then compared against the data range corresponding to the data items appearing in the operating status characteristic data. If this data is not included in the real-time data, data derivation is performed to obtain this data and then compared. If the comparison results show a certain level of overlap, it indicates that the current vehicle is likely to have experienced the fault type corresponding to the operating condition and operating status characteristic data.

[0088] It is understandable that the same characteristic operating condition may correspond to multiple different fault events at the same time, and the characteristic data items corresponding to the fault types are also different. The above example is used to further illustrate: when the vehicle stalls, most vehicles will experience insufficient power and a sudden drop in speed, which are relatively obvious vehicle operating conditions. These are the characteristic operating conditions that will be identified. After the causes of vehicle stall faults are finely divided, they can be divided into vehicle stall-fuel supply faults, vehicle stall-ignition system faults, vehicle stall-intake system faults, and vehicle stall-sensor faults. Then the characteristic data items corresponding to each sub-category of faults are different. The characteristic data items of vehicle stall-fuel supply faults are a series of operating parameters related to the fuel pump, such as fuel pressure, fuel flow, etc.; and the characteristic data items of vehicle stall-ignition system faults may include parameters such as ignition timing, secondary voltage of the ignition coil, and spark intensity of the spark plug.

[0089] It should be understood that the fault-operational characteristic map also includes the parameter ranges of these characteristic data items. For example, during normal driving, the vehicle speed may be 80-120 km / h, but when a certain speed fault occurs, the speed may suddenly drop to 20 km / h or lower. During normal operation, the clutch slip rate is close to 0% and the temperature is between 70-100 degrees Celsius. When a certain clutch fault occurs, the slip rate may exceed 5%, and the temperature may rapidly rise to over 200 degrees Celsius. Normal operating temperatures are typically between 85-115 degrees Celsius, but when certain engine faults occur, the temperature may exceed 130 degrees Celsius. Using these parameter ranges, the system can quickly identify whether the vehicle is in a potential fault state and take appropriate diagnostic and repair measures. The fault-operational characteristic map provides a systematic approach to identifying and responding to various fault conditions.

[0090] The present embodiment provides a vehicle fault identification and diagnosis method, which first obtains a fault case data set; divides the fault case data set to obtain fault vehicle operation data divided according to fault type; inputs the fault vehicle operation data into a fault analysis model for analysis to obtain operation status characteristic data corresponding to the fault type; determines the vehicle operation condition within a preset time before the fault occurs in each case based on the fault vehicle operation data; determines the characteristic operating condition based on the proportion of the vehicle operation condition; and constructs the fault-operation characteristic mapping table based on the characteristic operating condition, the operation status characteristic data, and the fault type.

[0091] In summary, through the systematic analysis of historical fault case data, we can gain a deeper understanding of the operating characteristics when a fault occurs, determine the specific operating conditions before the fault occurs, and construct a fault-operation characteristic mapping table. This effectively improves the accuracy and predictive ability of fault diagnosis, optimizes the fault analysis process, reduces dependence on professional maintenance personnel, and improves the safety and reliability of vehicle operation. At the same time, it provides data support for preventive maintenance, reduces maintenance costs, and enhances the intelligence and automation level of vehicles.

[0092] Reference Figure 3 , Figure 3 This is a flow chart of the third embodiment of the vehicle fault identification and diagnosis method of the present application. Based on the above-mentioned first embodiment, the third embodiment of the vehicle fault identification and diagnosis method of the present application is proposed.

[0093] In this embodiment, step S30 includes:

[0094] Step S301: Compare each feature data item in the vehicle state reference data with a corresponding reference interval in the vehicle state reference data to determine the feature data item located in the reference interval.

[0095] It should be noted that since the types of data items in the vehicle status reference data are of the type that will be counted as long as one characteristic operating condition occurs, the characteristic data items that appear here are actually relatively redundant. There are relatively few characteristic data items in the real-time status data that can actually be used for analysis. Therefore, when the real-time status data does not fall within the reference interval corresponding to the reference data, it does not need to participate in subsequent fault diagnosis and analysis.

[0096] Understandably, let's assume that a monitored vehicle's fault-operational signature map indicates that during normal operation, the engine coolant temperature should be maintained between 85°C and 115°C. During real-time monitoring, the following data is collected: Engine coolant temperature: 95°C (within the normal reference range); Fuel pressure: 300 kPa (the normal reference range is 350 kPa to 450 kPa, which is lower); Ignition coil secondary voltage: 15 kV (the normal reference range is 20 kV to 30 kV, which is lower). The comparison here is based on the normal operating range of parameters, while the parameter range corresponding to abnormal conditions often does not overlap with, or only partially overlaps with, the parameter range during normal operation.

[0097] It should be understood that the reference interval in this embodiment specifically refers to the reference interval of the vehicle's status data when a fault occurs, that is, the data at this time refers to the data represented by the abnormality. In theory, the parameters of a normal vehicle will not fall within this interval. On the contrary, if multiple characteristic data fall within this interval, the probability of such a fault occurring is higher.

[0098] Step S302: using the characteristic data items located in the reference interval as mapping data, and determining a fault event containing the mapping data based on the fault-operation characteristic mapping table.

[0099] It should be noted that the characteristic data items screened out in the previous steps, that is, they are within the reference interval, and the combination formed by these characteristic data items may be associated with certain known failure modes. The purpose of this step is to further analyze these data items through the failure-operation characteristic mapping table to determine whether a failure event exists.

[0100] It is understandable that the mapping table may include multiple fault modes, each of which is associated with specific characteristic data items and reference intervals. The data items in the reference interval may match operating parameters under normal operating conditions or specific fault conditions.

[0101] Step S303: Calculate the degree of coincidence between the mapping data and the characteristic data corresponding to each fault event.

[0102] It should be noted that calculating the overlap may involve a variety of statistical methods, such as Euclidean distance, Manhattan distance, cosine similarity, etc., to quantify the similarity between data.

[0103] Understandably, assuming one of the fault events is engine overheating, the overlap is quantified using one of the aforementioned statistical methods—Euclidean distance. The normal operating temperature range is 85°C to 105°C; the real-time monitored engine coolant temperature is 108°C; and the engine coolant temperature recorded in the fault case is 105°C to 115°C. Since 108°C deviates by 2°C from the median of the fault range (110°C) and spans 3°C from the edge of the range, the overlap is relatively high.

[0104] Step S304: Obtain a fault diagnosis result based on the characteristic data overlap.

[0105] In one embodiment, the fault diagnosis result is obtained based on the overlap of the characteristic data, including: taking the fault event corresponding to the characteristic data overlap greater than the first overlap judgment threshold as a potential fault event; if the number of the potential fault events is less than the event concurrency threshold, then it is judged that the current vehicle is in a fault-free state; if the number of the potential fault events is greater than the event concurrency threshold, then it is judged that the current vehicle is in a critical fault state; if the characteristic data overlap of any of the potential fault events is greater than the second overlap judgment threshold, then it is judged that the current vehicle has occurred the potential fault.

[0106] It can be understood that, assuming that the first overlap judgment threshold is set to 0.5, that is, as long as more than half of the feature items overlap with the actual data, it can be regarded as reaching the first overlap judgment threshold. The second overlap judgment threshold is set to 0.8, and the principle is the same as the first overlap judgment threshold. The event concurrency threshold is set to 3. The event concurrency threshold here is used to assess the risk of multiple fault events occurring at the same time. This is because of the system linkage of vehicle control. A faulty component may cause multiple fault events with different manifestations at the same time. If the overlap between the real-time feature data and the fault event exceeds 0.5, the event will be regarded as a potential fault. If there are multiple potential fault events at the same time, but the number does not exceed 3, the vehicle will be judged to be in a non-fault state. If the number of potential fault events exceeds 3, it will be judged to be in a critical fault state. If the overlap of any event exceeds 0.8, the vehicle is deemed to have experienced such a fault.

[0107] This embodiment provides a vehicle fault identification and diagnosis method. This embodiment first compares each characteristic data item in the vehicle status reference data with the corresponding reference interval in the vehicle status reference data to determine the characteristic data item located in the reference interval, and uses the characteristic data item located in the reference interval as mapping data; based on the fault-operation characteristic mapping table, determines the fault event containing the mapping data; calculates the overlap degree between the mapping data and the characteristic data corresponding to each fault event; and obtains the fault diagnosis result based on the characteristic data overlap degree.

[0108] In summary, this embodiment proposes a comprehensive vehicle fault diagnosis method that screens out abnormal data items by monitoring vehicle status data in real time and comparing it with preset reference intervals. These data items are further analyzed using a fault-operational feature map, calculating their degree of overlap with known fault patterns. The presence and severity of the fault are then determined using predefined discrimination and event concurrency thresholds. This method effectively identifies and predicts potential vehicle faults, improves the accuracy of fault diagnosis, reduces the impact of human factors, and provides robust data support for vehicle maintenance and safe operation.

[0109] Reference Figure 4 The present application also provides a vehicle fault identification and diagnosis device, the vehicle fault identification and diagnosis device comprising:

[0110] The vehicle data processing module 10 is used to obtain vehicle status characteristic data and vehicle operating conditions based on real-time operating data;

[0111] A reference data generating module 20 is configured to obtain vehicle state reference data based on the vehicle operating condition and fault-operation characteristic mapping table;

[0112] The fault diagnosis module 30 is configured to obtain a fault diagnosis result based on the vehicle state characteristic data and the vehicle state reference data.

[0113] In one embodiment, the reference data generation module 20 is further used to obtain a fault case data set; divide the fault case data set to obtain fault vehicle operation data divided according to fault type; input the fault vehicle operation data into a fault analysis model for analysis to obtain operation status characteristic data corresponding to the fault type; and obtain a fault-operation characteristic mapping table based on the operation status characteristic data and the fault type.

[0114] In one embodiment, the reference data generation module 20 is further used to determine the vehicle operating conditions within a preset time before the fault occurs in each case based on the fault vehicle operating data; determine the characteristic operating conditions based on the proportion of the vehicle operating conditions; and construct the fault-operation characteristic mapping table based on the characteristic operating conditions, operating status characteristic data and fault type.

[0115] In one embodiment, the vehicle data processing module 10 is further used to determine the vehicle operating condition based on the real-time operating data; determine the characteristic data items based on the vehicle operating condition and fault-operation characteristic mapping table; and derive data according to the characteristic data items based on the real-time vehicle operating data to obtain vehicle status characteristic data.

[0116] In one embodiment, the reference data generation module 20 is further used to determine the operating status characteristic data corresponding to the vehicle operating condition based on the fault-operation characteristic mapping table; obtain a characteristic data reference range based on the operating status characteristic data; and use the characteristic data reference range as the vehicle status reference data.

[0117] In one embodiment, the fault diagnosis module 30 is further used to compare each characteristic data item in the vehicle status reference data with the corresponding reference interval in the vehicle status reference data, determine the characteristic data item located in the reference interval, and use the characteristic data item located in the reference interval as mapping data; based on the fault-operation characteristic mapping table, determine the fault event containing the mapping data; calculate the degree of overlap between the mapping data and the characteristic data corresponding to each fault event; and obtain a fault diagnosis result based on the degree of overlap of the characteristic data.

[0118] In one embodiment, the fault diagnosis module 30 is further used to treat the fault event corresponding to the characteristic data overlap greater than the first overlap judgment threshold as a potential fault event; if the number of the potential fault events is less than the event concurrency threshold, it is judged that the current vehicle is in a fault-free state; if the number of the potential fault events is greater than the event concurrency threshold, it is judged that the current vehicle is in a critical fault state; if the characteristic data overlap of any of the potential fault events is greater than the second overlap judgment threshold, it is judged that the current vehicle has occurred the potential fault.

[0119] An embodiment of the present application also provides a vehicle fault identification and diagnosis device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the vehicle fault identification and diagnosis method in the above-mentioned embodiment one.

[0120] Reference below Figure 5 , which shows a schematic structural diagram of a vehicle fault identification and diagnosis device suitable for implementing an embodiment of the present application. The vehicle fault identification and diagnosis device in the embodiment of the present application may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), in-vehicle terminals (e.g., in-vehicle navigation terminals), and fixed terminals such as digital TVs and desktop computers. Figure 5The vehicle fault identification and diagnosis device shown is merely an example and should not limit the functions and scope of use of the embodiments of the present application.

[0121] like Figure 5 As shown, the vehicle fault identification and diagnosis device may include a processing device 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes based on programs stored in a read-only memory (ROM) 1002 or programs loaded from a storage device 1003 into a random access memory (RAM) 1004. RAM 1004 also stores various programs and data required for the operation of the vehicle fault identification and diagnosis device. Processing device 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems may be connected to I / O interface 1006: input devices 1007, such as a touchscreen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008, such as a liquid crystal display (LCD), speaker, vibrator, etc.; storage device 1003, such as a magnetic tape or hard disk; and communication device 1009. The communication device 1009 can allow the vehicle fault identification and diagnosis device to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a vehicle fault identification and diagnosis device with various systems, it should be understood that it is not required to implement or have all of the systems shown. More or fewer systems can be implemented or provided instead.

[0122] In particular, according to the embodiments disclosed in the present application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, the embodiments disclosed in the present application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program comprising program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network via a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0123] The vehicle fault identification and diagnosis device provided in this application, which utilizes the vehicle fault identification and diagnosis method described in the aforementioned embodiment, can address the technical problem of developing an efficient fault diagnosis method to monitor the complex electronic components and control systems of new energy vehicles in real time, accurately identify and warn of minor faults, and thus improve the safety and reliability of the vehicle. Compared to the prior art, the beneficial effects of the vehicle fault identification and diagnosis device provided in this application are the same as those of the vehicle fault identification and diagnosis method described in the aforementioned embodiment, and the other technical features of the vehicle fault identification and diagnosis device are the same as those disclosed in the method of the previous embodiment, and are not further elaborated here.

[0124] It should be understood that the various parts disclosed in this application can be implemented using hardware, software, firmware, or a combination thereof. In the description of the above embodiments, specific features, structures, materials, or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0125] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

[0126] The present application also provides a storage medium, on which a vehicle fault identification and diagnosis program is stored. When the vehicle fault identification and diagnosis program is executed by a processor, the steps of any one of the vehicle fault identification and diagnosis methods described above are implemented.

[0127] The storage medium provided in this application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination thereof. More specific examples of storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this embodiment, the storage medium may be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, system or device. The program code contained on the storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0128] The above-mentioned storage medium may be included in the vehicle fault identification and diagnosis device; or may exist independently without being assembled into the vehicle fault identification and diagnosis device.

[0129] The above-mentioned computer-readable storage medium carries one or more programs. When the above-mentioned one or more programs are executed by the vehicle fault identification and diagnosis equipment, the vehicle fault identification and diagnosis equipment: obtains vehicle status characteristic data and vehicle operating conditions based on real-time operation data; obtains vehicle status reference data based on the vehicle operating conditions and fault-operation characteristic mapping table; and obtains fault diagnosis results based on the vehicle status characteristic data and vehicle status reference data.

[0130] Computer program code for performing the operations of the present application may be written in one or more programming languages, or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer via any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0131] The flow charts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram can represent a module, program segment or a part of code, and the module, program segment or a part of code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order than that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart can be implemented by a dedicated hardware-based system that performs the specified function or operation, or can be implemented by a combination of dedicated hardware and computer instructions.

[0132] The modules described in the embodiments of the present application may be implemented in software or hardware, wherein the name of a module does not necessarily limit the unit itself.

[0133] The storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the aforementioned vehicle fault identification and diagnosis method. This computer-readable storage medium addresses the technical problem of developing an efficient fault diagnosis method for real-time monitoring of the complex electronic components and control systems of new energy vehicles, accurately identifying and warning of minor faults, and thereby improving vehicle safety and reliability. Compared to the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the vehicle fault identification and diagnosis method provided in the aforementioned embodiments, and are not further elaborated here.

[0134] The above description is only part of the embodiments of the present application and does not limit the patent scope of the present application. All equivalent structural transformations made by using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect application in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A vehicle fault identification and diagnosis method, characterized in that: The vehicle fault identification and diagnosis method comprises: Determine vehicle operating conditions based on real-time operating data; Determining characteristic data items according to the vehicle operating condition and fault-operation characteristic mapping table; Based on the real-time vehicle operation data, data is derived according to the characteristic data items to obtain vehicle status characteristic data; Obtaining vehicle state reference data according to the vehicle operating condition and fault-operation characteristic mapping table; Obtaining a fault diagnosis result based on the vehicle state characteristic data and the vehicle state reference data; Obtaining a fault diagnosis result based on the vehicle state characteristic data and the vehicle state reference data includes: Comparing each feature data item in the vehicle state feature data with a corresponding reference interval in the vehicle state reference data, determining a feature data item located in the reference interval, and using the feature data item located in the reference interval as mapping data, wherein the reference interval refers to a reference interval of the vehicle state data when the fault occurs; determining, based on the fault-operation characteristic mapping table, a fault event including the mapping data; Calculating the degree of overlap between the mapping data and the characteristic data corresponding to each fault event; A fault diagnosis result is obtained according to the overlap degree of the characteristic data.

2. The vehicle fault identification and diagnosis method according to claim 1, characterized in that: Before obtaining the vehicle status characteristic data and the vehicle operating condition according to the real-time operating data, the method further includes: Obtain a fault case dataset; Dividing the fault case data set to obtain fault vehicle operation data divided according to fault type; Inputting the fault vehicle operation data into a fault analysis model for analysis to obtain operation status characteristic data corresponding to the fault type; A fault-operation feature mapping table is obtained according to the operating state feature data and the fault type.

3. The vehicle fault identification and diagnosis method according to claim 2, characterized in that: The fault-operation feature mapping table is obtained according to the operation status feature data and the fault type, including: Determine the vehicle operating conditions within a preset time period before the fault occurs in each case based on the fault vehicle operating data; determining a characteristic operating condition according to a proportion of the vehicle operating condition; The fault-operation characteristic mapping table is constructed according to the characteristic working condition, the operating state characteristic data and the fault type.

4. The vehicle fault identification and diagnosis method according to claim 1, characterized in that: The obtaining of vehicle state reference data according to the vehicle operating condition and fault-operation characteristic mapping table includes: Determining operating state characteristic data corresponding to the vehicle operating condition according to the fault-operation characteristic mapping table; Obtaining a characteristic data reference range according to the operating status characteristic data; The characteristic data reference range is used as the vehicle state reference data.

5. The vehicle fault identification and diagnosis method according to claim 1, characterized in that: Obtaining a fault diagnosis result according to the characteristic data overlap includes: The fault event corresponding to the feature data overlap being greater than the first overlap judgment threshold is regarded as a potential fault event; If the number of potential fault events is less than the event concurrency threshold, it is determined that the current vehicle is in a fault-free state; If the number of potential fault events is greater than the event concurrency threshold, it is determined that the current vehicle is in a critical fault state; If the degree of overlap of the characteristic data of any of the potential fault events is greater than a second overlap determination threshold, it is determined that the current vehicle has experienced the potential fault.

6. A vehicle fault identification and diagnosis device, characterized in that: The vehicle fault identification and diagnosis device comprises: A vehicle data processing module is configured to determine a vehicle operating condition based on real-time operating data; determine characteristic data items based on a mapping table of vehicle operating conditions and fault-operation characteristics; and perform data derivation based on the characteristic data items based on the real-time vehicle operating data to obtain vehicle status characteristic data; A reference data generation module, configured to obtain vehicle status reference data based on the vehicle operating condition and fault-operation characteristic mapping table; a fault diagnosis module, configured to obtain a fault diagnosis result based on the vehicle state characteristic data and the vehicle state reference data; The fault diagnosis module is further configured to compare each characteristic data item in the vehicle status characteristic data with a corresponding reference interval in the vehicle status reference data, determine the characteristic data item located in the reference interval, and use the characteristic data item located in the reference interval as mapping data, wherein the reference interval refers to a reference interval of the vehicle status data when a fault occurs; determine a fault event containing the mapping data based on the fault-operation characteristic mapping table; calculate a degree of overlap between the mapping data and the characteristic data corresponding to each fault event; and obtain a fault diagnosis result based on the degree of overlap of the characteristic data.

7. A vehicle fault identification and diagnosis device, characterized in that: The vehicle fault identification and diagnosis device includes: a memory, a processor, and a vehicle fault identification and diagnosis program stored in the memory and executable on the processor. The vehicle fault identification and diagnosis program is configured to implement the steps of the vehicle fault identification and diagnosis method according to any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores a vehicle fault identification and diagnosis program, which, when executed by a processor, implements the steps of the vehicle fault identification and diagnosis method according to any one of claims 1 to 5.

Images