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

Abstract

The invention discloses a vehicle fault diagnosis method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining the operation data of each system in n systems of a target vehicle in a preset historical time period, obtaining n groups of operation data, determining the fault probability corresponding to each system in the n systems based on the n groups of operation data, and determining the fault probability of each system in the n systems based on the fault probability. The method comprises the steps of obtaining n fault probabilities, then determining k fault probabilities greater than a fault probability threshold in the n fault probabilities, then determining k systems and k groups of operation data corresponding to the k fault probabilities, and finally performing fault diagnosis on the k systems based on the k groups of operation data to obtain a first target diagnosis result. According to the embodiment of the invention, the efficiency of vehicle fault diagnosis is improved.

Description

Technical Field

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

[0002] With the rapid development of the automotive industry and the continuous increase in the number of cars on the road, the safety and reliability of vehicles are receiving increasing attention. During the use of vehicles, system failures often occur due to factors such as the natural wear of components, external environmental influences, and driving habits. Once a vehicle system fails, it will not only affect the normal operation of the vehicle, but may also cause serious traffic accidents, resulting in casualties and property losses. Current vehicle fault diagnosis methods can only detect a single system or component, making it difficult to conduct a comprehensive and accurate diagnosis of the vehicle's overall faults, resulting in low efficiency in vehicle fault diagnosis. Therefore, how to improve the efficiency of vehicle fault diagnosis is an urgent problem to be solved. Summary of the Invention

[0003] The embodiments of the present application provide a vehicle fault diagnosis method, which improves the efficiency of vehicle fault diagnosis.

[0004] In a first aspect, an embodiment of the present application provides a vehicle fault diagnosis method, the method comprising:

[0005] Obtaining operating data of each of n systems of a target vehicle within a preset historical time period to obtain n sets of operating data; n is an integer greater than 1;

[0006] determining a failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities;

[0007] Determine k fault probabilities greater than a fault probability threshold among the n fault probabilities; k is an integer less than n;

[0008] Determining k systems and k groups of operating data corresponding to the k failure probabilities;

[0009] Fault diagnosis is performed on the k systems based on the k groups of operating data to obtain a first target diagnosis result.

[0010] In a second aspect, an embodiment of the present application provides a vehicle fault diagnosis device, the device comprising: an acquisition unit and a processing unit;

[0011] The acquisition unit is used to acquire the operating data of each of the n systems of the target vehicle within a preset historical time period to obtain n sets of operating data; n is an integer greater than 1;

[0012] The processing unit is configured to determine a failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities;

[0013] Determine k fault probabilities greater than a fault probability threshold among the n fault probabilities; k is an integer less than n;

[0014] Determining k systems and k groups of operating data corresponding to the k failure probabilities;

[0015] Fault diagnosis is performed on the k systems based on the k groups of operating data to obtain a first target diagnosis result.

[0016] In a third aspect, an embodiment of the present invention provides an electronic device comprising: a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor so that the electronic device performs the method of the first aspect.

[0017] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method of the first aspect.

[0018] In a fifth aspect, an embodiment of the present invention provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, so that a computer executes the method of the first aspect.

[0019] The implementation of the present invention has the following beneficial effects:

[0020] It can be seen that the vehicle fault diagnosis method described in the embodiment of the present invention first obtains the operating data of each of the n systems of the target vehicle within a preset historical time period to obtain n groups of operating data, and then determines the fault probability corresponding to each of the n systems based on the n groups of operating data to obtain n fault probabilities, and then determines k fault probabilities greater than the fault probability threshold among the n fault probabilities, and then determines the k systems and k groups of operating data corresponding to the k fault probabilities, and finally performs fault diagnosis on the k systems based on the k groups of operating data to obtain a first target diagnosis result, thereby improving the efficiency of vehicle fault diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] In order to more clearly illustrate the technical solutions in the implementation methods or background technologies of the present application, the drawings required for use in the implementation methods or background technologies of the present application will be described below.

[0022] Figure 1 This is a schematic diagram of the structure of a vehicle fault diagnosis system provided by an embodiment of the present application;

[0023] Figure 2 This is a flow chart of a vehicle fault diagnosis method provided by an embodiment of the present application;

[0024] Figure 3 This is a flow chart for determining n fault probabilities provided by an embodiment of the present application;

[0025] Figure 4 This is a flow chart for determining a failure probability corresponding to a first system provided by an embodiment of the present application;

[0026] Figure 5 This is a flow chart of generating alarm information provided by an embodiment of the present application;

[0027] Figure 6 This is a flow chart for determining a target failure probability provided by an embodiment of the present application;

[0028] Figure 7 This is a schematic structural diagram of a vehicle fault diagnosis device provided by an embodiment of the present application;

[0029] Figure 8 It is a structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0030] In order to enable those skilled in the art to better understand the present invention, the following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0031] The terms "first," "second," and the like in the specification and claims of this application and the accompanying drawings are used to distinguish between different objects, not to describe a particular order. Furthermore, the terms "including," "having," and any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or elements is not limited to the listed steps or elements but may optionally include steps or elements not listed, or may optionally include other steps or elements inherent to the process, method, product, or apparatus.

[0032] Reference herein to an "embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment may be included in at least one embodiment of the present application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor does it refer to independent or alternative embodiments that are mutually exclusive of other embodiments. It is understood, both explicitly and implicitly, by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0033] See also Figure 1 , Figure 1 1 is a schematic structural diagram of a vehicle fault diagnosis system provided in an embodiment of the present application. The vehicle fault diagnosis system 100 includes a battery system 101 , a braking system 102 , an air conditioning system 103 , and an engine cooling system 104 .

[0034] In this embodiment, the system failure probability is primarily assessed based on the system's temperature and pressure values. The normal operating conditions of the battery system 101, braking system 102, air conditioning system 103, and engine cooling system 104 are closely related to these temperature and pressure parameters. Therefore, this embodiment primarily uses these systems to explain and illustrate the vehicle fault diagnosis method. In actual operation, vehicle fault diagnosis can also be performed by analyzing the parameters of more systems.

[0035] It can be seen that the battery system 101, the braking system 102, the air conditioning system 103, and the engine cooling system 104 are key parts of vehicle operation and are closely related to temperature and pressure. Fault diagnosis for these systems can directly focus on the parts of the vehicle that are most prone to failure due to temperature and pressure problems, thereby improving the pertinence and effectiveness of diagnosis. Temperature and pressure are relatively intuitive and easy-to-understand physical parameters. Explaining the fault diagnosis method using these systems as an example can enable readers or technicians to understand the principles of fault diagnosis more clearly. In actual operation, the measurement of temperature and pressure is relatively easy to achieve, and there are mature sensors and measuring equipment. Focusing on these systems and using temperature and pressure values ​​for fault diagnosis facilitates the installation of corresponding monitoring equipment on the vehicle and obtains accurate data, thereby providing a reliable basis for fault diagnosis.

[0036] See also Figure 2 , Figure 2 This is a flow chart of a vehicle fault diagnosis method provided by an embodiment of the present application, including but not limited to the following steps:

[0037] S201: Obtain operating data of each of n systems of a target vehicle within a preset historical time period to obtain n groups of operating data.

[0038] In this embodiment, n is an integer greater than 1. For each system, operating data is collected for a pre-set historical time period. This time period can be the past day, week, or month, depending on actual needs and vehicle usage. Each system has its own independent operating data. By acquiring the operating data of each of n systems within the pre-set historical time period, n sets of operating data are obtained, each set of data corresponding to a record of the operating status of a system within the pre-set historical time period. For example, for a vehicle, the operating data of the engine system may include the time-varying changes in parameters such as speed, temperature, and fuel injection volume. The operating data of the battery system may include the records of parameters such as temperature, voltage, current, and power within the same time period.

[0039] S202: Determine the failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities.

[0040] In this implementation, see Figure 3 , Figure 3 This is a flowchart of determining n fault probabilities provided by an embodiment of the present application, including but not limited to the following steps:

[0041] S301: Acquire a temperature value, a pressure value, and an information interaction frequency corresponding to a first system based on first operating data to obtain a first temperature value, a first pressure value, and a first information interaction frequency.

[0042] In this embodiment, the first system is any one of the n systems, and the first operating data is the operating data corresponding to the first system among the n sets of operating data. From the n sets of operating data previously acquired, the set of operating data corresponding to the first system is found, i.e., the first operating data. Then, three key parameters corresponding to the system, namely, the temperature value, pressure value, and information exchange frequency, are extracted from the first operating data to obtain the first temperature value, first pressure value, and first information exchange frequency, respectively. For example, if the first system is a vehicle's battery system, three key parameters are extracted from the first operating data of the battery system: the temperature value of the battery system (the first temperature value). Since the battery generates heat during charging and discharging, its temperature is an important operating indicator; the pressure value within the battery system (the first pressure value), such as the air pressure or hydraulic pressure within the battery pack. Some battery technologies may focus on internal pressure changes; and the frequency of information exchange between the battery management system and other vehicle systems (the first information exchange frequency), such as the frequency at which the battery management system sends battery status information to the vehicle control system.

[0043] S302: Determine a temperature difference between the first temperature value and a preset temperature value, a pressure difference between the first pressure value and a preset pressure value, and an information interaction frequency difference between the first information interaction frequency and a preset information interaction frequency.

[0044] In this embodiment, when the first system is a battery system, there is a preset normal operating temperature range and a corresponding preset temperature value, a normal operating pressure range and a corresponding preset pressure value, and a normal information interaction frequency range and a corresponding preset information interaction frequency for the battery system. The first temperature value of the battery system obtained from the first operating data is compared with the preset temperature value, and the difference between the two, that is, the temperature difference, is calculated. For example, the preset temperature value is 20°C-30°C, and the current first temperature value is 35°C, then the temperature difference is 35-30=5°C (here taking the upper limit as an example), indicating that the battery temperature It exceeds the normal range. Similarly, the pressure difference between the first pressure value and the preset pressure value is calculated. Assuming that the preset pressure value is 1-1.2 atmospheres and the first pressure value is 1.5 atmospheres, the pressure difference is 1.5-1.2=0.3 atmospheres, indicating that the internal pressure of the battery system is higher than the normal level. The information interaction frequency difference between the first information interaction frequency and the preset information interaction frequency is calculated. If the preset information interaction frequency is 10 times per minute and the actual first information interaction frequency is 8 times per minute, then the information interaction frequency difference is 8-10=-2 times / minute, indicating that the information interaction frequency is lower than the normal frequency.

[0045] S303: Determine a failure probability corresponding to the first system based on the temperature difference, the pressure difference, and the information interaction frequency difference.

[0046] In this implementation, see Figure 4 , Figure 4 This is a flowchart of determining a failure probability corresponding to a first system provided by an embodiment of the present application, including but not limited to the following steps:

[0047] S401: Acquire a first mapping relationship between temperature difference and stability value, a second mapping relationship between pressure difference and stability value, and a third mapping relationship between information interaction frequency difference and stability value.

[0048] In this embodiment, to assess the system's status, it is necessary to establish a mapping between different parameter differences and stability values. This is done for temperature difference, pressure difference, and information exchange frequency difference. The first mapping relationship determines the correspondence between temperature difference and stability values ​​by analyzing historical data, system characteristics, or based on relevant technical standards. For example, research has found that when the temperature difference is within ±2°C, the system stability value is high, set at 90 (out of 100); when the temperature difference exceeds ±5°C, the stability value drops significantly, perhaps to 40. The second mapping relationship determines the correspondence between pressure difference and stability values. For example, if the pressure difference is within ±0.1 atmosphere, the stability value is 85; when the pressure difference reaches ±0.3 atmosphere, the stability value drops to 50. The third mapping relationship clarifies the relationship between information exchange frequency difference and stability values. For example, if the information exchange frequency difference is within ±1 time / minute, the stability value is 95; when the difference reaches ±3 times / minute, the stability value is 60.

[0049] S402: Determine a first stability value corresponding to the temperature difference based on the first mapping relationship.

[0050] In this embodiment, according to the first mapping relationship established previously, the temperature difference of the battery system obtained by actual calculation is substituted therein to obtain the corresponding stability value, i.e., the first stability value. For example, if the temperature difference of the battery system is 3°C, according to the corresponding rules specified in the first mapping relationship, the corresponding first stability value is 70.

[0051] S403: Determine a second stability value corresponding to the pressure difference based on the second mapping relationship.

[0052] In this embodiment, similar to the method for determining the first stability value, the pressure difference of the battery system is substituted according to the second mapping relationship to obtain a corresponding stability value, namely the second stability value. For example, if the pressure difference is 0.2 atmospheres, the corresponding second stability value may be 65 according to the second mapping relationship.

[0053] S404: Determine a third stability value corresponding to the information interaction frequency difference based on the third mapping relationship.

[0054] In this embodiment, the battery system's information exchange frequency difference is substituted according to the third mapping relationship to determine the corresponding stability value, which is the third stability value. For example, if the information exchange frequency difference is -2 times / minute, the corresponding third stability value may be 75 according to the third mapping relationship.

[0055] S405: Determine a target stability value based on the first stability value, the second stability value, and the third stability value.

[0056] In this embodiment, exemplarily, a first weight corresponding to the first stability value, a second weight corresponding to the second stability value, and a third weight corresponding to the third stability value are determined, and the sum of the first weight, the second weight, and the third weight is 1. Specifically, in order to comprehensively consider the different degrees of influence of temperature, pressure, and information interaction frequency on system stability, it is necessary to assign a weight to each stability value. The first stability value (determined by the temperature difference) corresponds to the first weight, the second stability value (determined by the pressure difference) corresponds to the second weight, and the third stability value (determined by the information interaction frequency difference) corresponds to the third weight. It can be a preset mapping relationship between stability values ​​and weights. Based on this mapping relationship, the first weight corresponding to the first stability value, the second weight corresponding to the second stability value, and the third weight corresponding to the third stability value can be determined.

[0057] Exemplarily, the load corresponding to the first system is obtained. Specifically, a large load change may cause the output voltage of the battery system to fluctuate, because the load change may cause changes in the chemical reaction rate inside the battery, as well as the dynamic process of adjustment of the power management system, which may cause the voltage to fluctuate within a certain range. Such fluctuations will also reduce the voltage stability value. When the load changes are small, the battery system is more likely to maintain voltage stability, and the voltage fluctuation may be alleviated, thereby improving the voltage stability value to a certain extent. Therefore, it is necessary to obtain the load corresponding to the first system.

[0058] Exemplarily, determining the first optimization factor corresponding to the load may specifically be a preset mapping relationship between the load and the optimization factor, and the first optimization factor corresponding to the load may be determined based on the mapping relationship.

[0059] Exemplarily, the second weight is optimized based on the first optimization factor to obtain a first target weight. Specifically, the first target weight is calculated according to the following formula:

[0060] First target weight = second weight × (1 + first optimization factor);

[0061] According to the above formula, the second weight can be optimized based on the first optimization factor to obtain the first target weight.

[0062] Exemplarily, the bandwidth of the information interaction line corresponding to the first system is obtained to obtain the target bandwidth. Specifically, sufficient bandwidth can provide sufficient channel capacity for information transmission, so that data can be smoothly transmitted between various components in the system. This means that the information interaction frequency can be maintained at a relatively stable level, and there will be no data congestion, delay or loss due to insufficient bandwidth, thereby improving the stability value corresponding to the information interaction frequency. When the bandwidth is sufficient, the system has a stronger adaptability to external interference or sudden changes in information flow. For example, when the system is subject to temporary network fluctuations or other interference, sufficient bandwidth can allow the system to maintain the stability of the information interaction frequency by appropriately adjusting the data transmission rate, thereby maintaining a higher stability value. Insufficient bandwidth will cause bottlenecks in data transmission. Information may be congested during transmission, making it impossible for the frequency of information interaction to be maintained at the expected level. The frequency may drop or fluctuate from time to time, seriously affecting the stability of information interaction and reducing the stability value. Due to bandwidth limitations, some data may be discarded because they cannot be transmitted in time, or errors may occur during transmission, which will lead to incomplete and inaccurate information interaction, and further affect the system's judgment and control of the frequency of information interaction, reducing the stability value. In addition, in order to deal with data loss or errors, the system may adopt mechanisms such as retransmission, which will further increase the bandwidth burden, forming a vicious circle and further reducing the stability of the information interaction frequency. Therefore, it is necessary to obtain the bandwidth of the information interaction line corresponding to the first system to obtain the target bandwidth.

[0063] Exemplarily, the second optimization factor corresponding to the target bandwidth is determined. Specifically, it may be a mapping relationship between a preset bandwidth and an optimization factor. The second optimization factor corresponding to the target bandwidth may be determined based on the mapping relationship.

[0064] Exemplarily, the third weight is optimized based on the second optimization factor to obtain a second target weight. Specifically, the second target weight is calculated according to the following formula:

[0065] Second target weight = third weight × (1 + second optimization factor);

[0066] According to the above formula, the third weight can be optimized based on the second optimization factor to obtain a second target weight.

[0067] Exemplarily, the third target weight is determined based on the first target weight and the second target weight. Specifically, since the sum of the three weights is 1, after obtaining the first target weight and the second target weight, the third target weight can be determined by subtracting the first target weight and the second target weight from 1.

[0068] Exemplarily, the target stability value is obtained by performing calculation based on the first stability value, the second stability value, the third stability value, the first target weight, the second target weight, and the third target weight. Specifically, the target stability value is calculated according to the following formula:

[0069] Target stability value = first stability value × third target weight + second stability value × first target weight + third stability value × second target weight;

[0070] According to the above formula, the target stability value can be obtained by calculation based on the first stability value, the second stability value, the third stability value, the first target weight, the second target weight and the third target weight.

[0071] As can be seen, by assigning weights to the first, second, and third stability values ​​and optimizing them based on system load and information exchange line bandwidth, the method comprehensively considers the impact of multiple factors on system stability, such as temperature, pressure, information exchange frequency, system load, and bandwidth, enabling the target stability value to more accurately reflect the actual system stability. Dynamically adjusting the weights based on system load and bandwidth allows the target stability value to better adapt to changes in system operating conditions. For example, when the system load is high or the bandwidth is low, optimizing the weights can highlight the stability values ​​that are most affected by these factors, thereby more promptly and accurately reflecting changes in system stability and helping to promptly identify potential system issues. A more accurate target stability value provides a more reliable basis for determining system failure probability, thereby improving the accuracy of fault prediction. Because this calculation method fully considers various factors and their interrelationships, it provides a more refined and comprehensive assessment of system stability. This allows for more effective identification of the possibility of system instability and the implementation of appropriate preventive measures. This method provides system administrators with richer information and more accurate evaluation indicators. System administrators can monitor, adjust and optimize the system more specifically based on the target stability value and the weight changes of each stability value, thereby improving the overall performance and reliability of the system and enhancing the manageability of the system.

[0072] S406: Determine a failure probability corresponding to the first system based on the target stability value; the larger the target stability value is, the smaller the failure probability corresponding to the first system is.

[0073] In this embodiment, for example, a reference failure probability corresponding to the first system is determined based on the target stability value. Specifically, the target stability value is a numerical value reflecting the overall stability of the system, obtained by comprehensively considering multiple aspects of the system (such as temperature, pressure, information exchange frequency, etc.). The larger the target stability value, the more stable the system and the lower the possibility of failure. Conversely, the smaller the target stability value, the greater the possibility of system failure. By establishing a corresponding functional relationship or mapping relationship between the target stability value and the reference failure probability, a preliminary estimate of the failure probability of the system in its current state can be made based on the target stability value. This preliminary estimated failure probability is the reference failure probability.

[0074] Exemplarily, the operating time of the first system is obtained. Specifically, the operating time of the system refers to the time elapsed from the start of the first system operation to the current moment. Operating time is an important parameter because, over time, various components of the system may experience wear and aging, which will affect the reliability and failure probability of the system. Therefore, it is necessary to clearly determine how long the system has been operating so that the impact of operating time on failure probability can be considered in subsequent steps. Therefore, it is necessary to obtain the operating time of the first system.

[0075] Exemplarily, the target adjustment parameter corresponding to the operating time is determined. Specifically, it can be a mapping relationship between a preset operating time and an adjustment parameter. Based on this mapping relationship, the target adjustment parameter corresponding to the operating time can be determined. Different operating times usually correspond to different system state change trends, which will have different degrees of impact on the probability of failure. The target adjustment parameter is a numerical value used to quantify this impact. It is also possible to determine a function or rule related to the operating time based on the characteristics of the system, historical data, or empirical formulas. The target adjustment parameter corresponding to the current operating time is calculated through this function or rule. For example, for some equipment, the longer the operating time, the faster the probability of failure increases. Then, as the operating time increases, the target adjustment parameter may gradually increase the adjustment range of the probability of failure.

[0076] Exemplarily, the reference failure probability is adjusted based on the target adjustment parameter to obtain the failure probability corresponding to the first system. Specifically, the reference failure probability is preliminarily estimated based only on the target stability value, without considering the impact of the operating time, while the target adjustment parameter reflects the impact of the operating time on the failure probability. By applying the target adjustment parameter to the reference failure probability and correcting or adjusting it, a more comprehensive and accurate failure probability corresponding to the first system can be obtained that takes into account both system stability and operating time. Specifically, the failure probability corresponding to the first system is calculated according to the following formula:

[0077] The failure probability corresponding to the first system = reference failure probability × (1 + target adjustment parameter);

[0078] According to the above formula, the reference failure probability can be adjusted based on the target adjustment parameter to obtain the failure probability corresponding to the first system.

[0079] As can be seen, the target stability value reflects the current comprehensive stability of the system. Determining the reference failure probability based on this value allows for a preliminary assessment of the system's failure probability in its current state. Furthermore, by factoring in runtime, the system takes into account issues such as component aging and performance degradation that arise with increasing runtime, making the calculation of the failure probability more closely aligned with the system's actual operating conditions and enabling an accurate assessment of the system's failure probability. The target adjustment parameter is determined based on runtime, quantifying the impact of runtime on the failure probability. For systems with varying runtimes, the reference failure probability can be adjusted accordingly based on the corresponding target adjustment parameter. For example, for a system with a long runtime, even if the current stability value is high, the target adjustment parameter will appropriately increase the failure probability, taking into account the potential risks accumulated over long-term operation, thereby avoiding underestimation of the failure risk. For a system with a short runtime, if the stability value is high, the target adjustment parameter will maintain the failure probability at a low level, preventing overestimation of the failure risk due to excessive consideration of runtime, thereby improving the accuracy and reliability of fault prediction. This method can provide accurate failure probability information for system maintenance, helping maintenance personnel develop reasonable maintenance plans based on different failure probabilities. For systems with a high failure probability, maintenance measures such as overhaul and replacement of wearing parts can be arranged in advance to prevent failures. For systems with a low failure probability, the maintenance cycle can be appropriately extended to save maintenance costs and resources, achieve reasonable allocation of system maintenance resources and optimize maintenance strategies. Whether the system is simple or complex, whether it is a continuously operating system or an intermittently operating system, this method can be used to determine the failure probability. Based on the characteristics and operating data of different systems, the relationship between the target stability value and the reference failure probability, as well as the relationship between the operating time and the target adjustment parameters, can be established. It has strong flexibility and versatility and can adapt to the needs of various systems and operating scenarios.

[0080] As can be seen, by mapping the temperature, pressure, and information exchange frequency differences to the stability value, a quantitative description of the system state is provided from multiple dimensions. Temperature, pressure, and information exchange frequency are key indicators during system operation, and their changes can reflect the system's internal operating conditions. For example, a large temperature difference may indicate a cooling problem, an abnormal pressure difference may indicate abnormal loads on the system's mechanical components, and an unstable information exchange frequency difference may indicate a potential failure in the system's communication or control links. By considering these various factors, a comprehensive understanding of the system's overall stability can be achieved, avoiding the one-sidedness caused by relying solely on a single indicator. Determining the first, second, and third stability values ​​based on different mapping relationships allows for a more accurate assessment of the system's stability in various aspects. Each mapping relationship characterizes the relationship between a specific parameter and stability, capturing the unique impact of that parameter's changes on system stability. The target stability value is then determined by combining these three stability values. This further integrates information from various aspects, making the assessment of the system's overall stability more accurate and refined, and providing a solid foundation for subsequently accurately determining the probability of system failure. Because the target stability value is derived by comprehensively considering multiple key system indicators, it establishes a closer and more realistic relationship with the system's failure probability. Generally speaking, the larger the target stability value, the better the system's operating conditions across multiple key aspects and the lower the likelihood of failure. This multi-dimensional information-based failure probability prediction method can more accurately reflect the system's true failure risk compared to traditional simple empirical judgments or single-parameter predictions, helping to take appropriate preventive measures in advance, reduce the likelihood of failure, and minimize losses caused by failure. This method not only assesses the system's current stability and failure probability, but also provides valuable information for system optimization and improvement by analyzing the mapping between various parameters and stability values. For example, if it is found that temperature difference has a significant impact on stability, then the system's cooling system can be optimized specifically. If pressure difference is the primary factor affecting system stability, then improvements or maintenance of related pressure-bearing components can be prioritized. In this way, targeted system optimization can be implemented to improve system reliability and stability, extending system service life.

[0081] It should be explained that the first system is any one of the n systems, so the failure probability corresponding to each of the n systems can be determined according to the method for determining the failure probability corresponding to the first system, resulting in n failure probabilities. For any one of the n systems (taking the first system as an example), key indicators such as temperature, pressure, and information exchange frequency are obtained through its corresponding first operating data, and compared with their respective preset values ​​to obtain corresponding differences. This method can accurately analyze the individual operating status of each system. Because different systems may have different specific operating parameters even under similar overall operating environments, by focusing on these differences, the actual situation of each system can be more accurately grasped. Temperature, pressure, and information exchange frequency are important indicators reflecting the system's operating status, and they each reveal possible system problems from different perspectives. For example, abnormal temperature may indicate poor system heat dissipation or internal component overload; abnormal pressure may indicate a failure in the system's mechanical structure or fluid transmission; and abnormal information exchange frequency may indicate a disorder in the system's communication or control logic. Comprehensively considering the differences between these three indicators can comprehensively assess the system's failure risk, avoiding the situation where other potential problems are ignored based on a single indicator. Determining the corresponding failure probability of a system based on the differences between these three key indicators can more accurately reflect the actual failure probability of the system. The difference in each indicator reflects, to some extent, the degree to which the system has deviated from its normal operating state. By combining these differences, a more comprehensive measure of system stability and reliability can be achieved, thereby improving the accuracy of the failure probability calculation. The resulting failure probability can more realistically reflect the health of the system and provide a more reliable basis for subsequent maintenance decisions and risk management. This method is applicable to each of n systems and has good versatility and scalability. Whether analyzing different types of systems or the same system at different operating stages or in different environments, the same method can be used to obtain key indicator differences and calculate failure probability. Moreover, if additional operating indicators are needed in the future to more comprehensively assess the system failure probability, the existing method can be expanded by adding corresponding indicators and calculation logic without requiring large-scale modifications to the overall architecture.

[0082] In this implementation, see Figure 5 , Figure 5 This is a flowchart of generating alarm information provided by an embodiment of the present application, including but not limited to the following steps:

[0083] S501: Determine a target failure probability of the target vehicle based on the n failure probabilities.

[0084] In this implementation, see Figure 6 , Figure 6This is a flowchart for determining a target failure probability provided by an embodiment of the present application, including but not limited to the following steps:

[0085] S601: Determine the average value of the n fault probabilities to obtain an average fault probability.

[0086] In this embodiment, the n failure probabilities are added together and then divided by n. The result is the average failure probability, which represents an overall average level of the failure probabilities of these n systems and can provide a rough estimate of the overall failure probability of these systems.

[0087] S602: Determine the standard deviation of the n failure probabilities.

[0088] In this implementation, the standard deviation is a statistic used to measure the degree of dispersion in a set of data. For each of the n failure probabilities, the difference between each failure probability and the average failure probability is calculated. These differences are squared and averaged, and the square root of this average is taken to obtain the standard deviation. A larger standard deviation indicates greater variation among the n failure probabilities and more dispersed data. A smaller standard deviation indicates that the failure probabilities are closer to the average and more concentrated data.

[0089] S603: Determine a fine-tuning parameter corresponding to the standard deviation.

[0090] In this embodiment, a mapping relationship between a preset standard deviation and a fine-tuning parameter can be used, and the fine-tuning parameter corresponding to the standard deviation can be determined based on the mapping relationship. Alternatively, a linear or nonlinear functional relationship between the standard deviation and the fine-tuning parameter can exist, which is not limited here.

[0091] S604: Adjust the average failure probability based on the fine-tuning parameter to obtain the target failure probability.

[0092] In this embodiment, the target failure probability is calculated specifically according to the following formula:

[0093] Target failure probability = average failure probability × (1 + fine-tuning parameter);

[0094] According to the above formula, the average failure probability can be adjusted based on the fine-tuning parameter to obtain the target failure probability.

[0095] It can be seen that calculating the average value of n failure probabilities to obtain the average failure probability can summarize the failure probability levels of multiple systems or components of the target vehicle as a whole, provide an intuitive overall indicator, and help quickly understand the overall failure possibility trend of the vehicle. By calculating the standard deviation of n failure probabilities, the distribution dispersion of these failure probabilities can be understood. The larger the standard deviation, the greater the difference in the failure probability of each system or component, and the uneven failure risk of different parts of the vehicle. The smaller the standard deviation, the relatively concentrated failure probability and the relatively stable and balanced failure risk of the vehicle as a whole. This helps to further analyze the consistency and stability of the vehicle failure risk. According to the standard deviation, the corresponding fine-tuning parameters can be determined, and the average failure probability can be adjusted in a targeted manner according to the degree of dispersion of the failure probability. When the standard deviation is large, it means that the failure probability of each system or component is large, and it may be necessary to adjust the failure probability of each system or component. The average failure probability is adjusted to a greater extent to more accurately reflect the actual failure risk faced by the vehicle. When the standard deviation is small, fine-tuning the parameters will result in a smaller adjustment of the average failure probability, because the failure probabilities of various systems or components are relatively close at this time, and the average failure probability can already better represent the overall situation. This standard deviation-based fine-tuning method can more accurately determine the target failure probability of the target vehicle, making it more consistent with the actual operating conditions and failure risk characteristics of the vehicle. The target failure probability obtained through the above steps comprehensively considers the failure probabilities and their discreteness of multiple systems or components of the vehicle, and can more comprehensively and accurately reflect the actual failure risk of the target vehicle. This provides a more reliable basis for vehicle maintenance, repair decisions, insurance pricing, etc., helps to improve the scientific nature and rationality of related decisions, and reduce the risks and losses caused by inaccurate failure probability estimates.

[0096] S502: When the target failure probability is less than or equal to a preset failure probability, performing the operation of determining k failure probabilities among the n failure probabilities that are greater than a failure probability threshold.

[0097] In this embodiment, the preset failure probability is a pre-set standard value used to measure whether the failure risk of the target vehicle is within an acceptable range. When the calculated target failure probability is less than or equal to the preset failure probability, it means that the overall failure risk of the vehicle is relatively low and within an acceptable range. However, even if the overall risk is low, there may still be some systems with a higher failure probability that require further investigation. Therefore, in this case, an operation will be performed to determine k failure probabilities greater than a failure probability threshold among n failure probabilities. The failure probability threshold is also a pre-set value used to distinguish between high and low system failure probabilities. Failure probabilities greater than this threshold are found from the n failure probabilities. The systems corresponding to these failure probabilities are considered to have a higher possibility of failure. K is used to represent the number of these failure probabilities greater than the threshold (k is less than n). Through this step, we can further focus on those systems that may have problems for more in-depth inspection and diagnosis.

[0098] S503: When the target failure probability is greater than the preset failure probability, an alarm message is generated based on the target failure probability, and fault diagnosis is performed on the n systems based on the n sets of operating data to obtain a second target diagnosis result.

[0099] In this embodiment, the alarm information is used to indicate that a serious fault has occurred in the target vehicle. When the target fault probability is greater than the preset fault probability, it indicates that the overall vehicle fault risk is high enough to warrant attention, indicating that the vehicle may have experienced a serious fault. Therefore, an alarm information is generated based on the target fault probability. The alarm information indicates that a serious fault has occurred in the target vehicle and serves as a warning to the vehicle user, maintenance personnel, or related systems.

[0100] The alarm message may include a fault type prompt: it will clearly indicate the type of serious fault that may occur in the vehicle. For example, if it is an engine cooling system fault, the alarm message may display "Engine cooling system fault, which may cause engine overheating, please stop and check immediately." If it is a brake system fault, it may display "Braking system abnormality, braking force may be insufficient, drive carefully and repair as soon as possible." It can also include a fault impact description: explaining the impact that the fault may have on vehicle operation and safety. For example, for a serious battery system fault, the alarm message may state "Battery system fault, which may cause the vehicle to suddenly lose power and pose a safety hazard" to let users understand the severity of the problem. It can also include recommended operations: providing some recommended operations for dealing with the fault. For example, "Please find a safe place to stop as soon as possible and avoid driving" and "Do not attempt to repair it yourself, please contact professional maintenance personnel", etc., to guide users to take correct measures to prevent the fault from further deteriorating or causing a safety accident.

[0101] The alarm information can be presented as a visual prompt: a conspicuous warning light on the vehicle's dashboard will light up, such as a flashing or steady red fault indicator light, to attract the driver's attention. At the same time, detailed text alarm information may also be displayed on the vehicle's display screen. It can also be an auditory prompt: a specific alarm sound, such as a beep or voice prompt, will be emitted to alert the driver to a serious vehicle fault. Different fault types may correspond to different alarm sounds, so that the driver can quickly identify the general type of fault. For connected vehicles, the alarm information may also be sent to the owner or relevant vehicle management department through mobile phone software, vehicle networking platforms, etc., so that even if the driver is not in the car, he or she can still understand the vehicle's fault status in a timely manner.

[0102] Generating alarm information based on the target failure probability can promptly remind the driver of serious vehicle failures, prompting him or her to take appropriate measures to avoid traffic accidents caused by the failure and ensure the safety of the driver, passengers and other road users. It can also allow the driver to stop and check or contact maintenance personnel as soon as possible to prevent the failure from further expanding, reduce the degree of vehicle damage and reduce maintenance costs. It can also provide maintenance personnel with preliminary fault information to help them have a certain understanding of the failure before arriving at the scene, prepare the corresponding maintenance tools and parts, and improve maintenance efficiency.

[0103] At the same time, comprehensive fault diagnosis is performed on n systems based on n sets of operating data. These n sets of operating data contain detailed operating information for each system over a pre-set historical period. Through in-depth analysis of this data and application of various fault diagnosis methods and techniques, the specific fault points and causes of each system are identified, ultimately yielding a secondary diagnostic result. This diagnostic result provides detailed guidance for subsequent repairs and procedures, helping maintenance personnel more accurately locate and resolve issues and restore the vehicle to normal operation as quickly as possible. Specifically, the n sets of operating data are first collated and preprocessed, including data cleaning, removal of outliers and noise, and filling in missing values. This ensures data accuracy and completeness, providing a reliable data foundation for subsequent analysis. Feature parameters related to system faults are then extracted from the collated data. These features can be statistics calculated directly from the raw data, such as mean, variance, maximum, and minimum values, or they can be derived through signal processing or data analysis methods, such as spectral features and time-frequency features. A fault pattern library is then established, containing various known system fault modes and their corresponding characteristic manifestations. By comparing and matching the extracted features with those in the fault pattern library, possible fault modes can be identified. Various methods can be used for fault pattern recognition, such as rule-based reasoning methods, which determine whether a feature conforms to a certain fault pattern based on preset rules. Machine learning algorithms such as decision trees, support vector machines, and neural networks can also be used to establish a fault pattern classification model through learning and training a large amount of known fault data. New data can then be classified and identified, and then a second target diagnostic result is generated based on the results of fault pattern recognition. The diagnostic result should include the system where the fault occurred, the fault type, an assessment of the fault severity, and an analysis of possible fault causes. For complex fault situations, it may be necessary to comprehensively consider the operating data and fault modes of multiple systems, conduct in-depth analysis and reasoning, and determine the final diagnostic result. At the same time, the diagnostic result can be further verified and improved by combining maintenance experience and vehicle usage history. The generated diagnostic results can also be compared and verified with the actual situation. The accuracy of the diagnostic results can be confirmed through further inspection, testing or feedback after repair of the vehicle. If the diagnostic results do not match the actual situation, it is necessary to analyze the reasons, which may be inaccurate data collection, inappropriate feature extraction, incomplete fault mode library or defects in the diagnostic method, etc. Then, the corresponding links should be adjusted and improved, and the fault diagnosis should be repeated until accurate and reliable diagnostic results are obtained.

[0104] As can be seen, a preliminary judgment is made by calculating the target failure probability of the target vehicle, dividing the situations into two categories: those with a target failure probability less than or equal to a preset failure probability and those with a target failure probability greater than the preset failure probability. Different handling strategies are then adopted for different situations, avoiding comprehensive fault diagnosis for all situations, improving fault diagnosis efficiency, and enabling more targeted responses to vehicle conditions. When the target failure probability is less than or equal to the preset failure probability, the system further determines the k fault probabilities of the n fault probabilities that are greater than the failure probability threshold. This helps to more accurately locate the systems that may have faults, focusing attention on these systems that are more likely to have problems and conducting targeted analysis and processing, reducing unnecessary inspection and analysis work and improving the accuracy and efficiency of fault location. When the target failure probability is greater than the preset failure probability, an alarm is promptly generated to indicate that the vehicle has a serious fault, allowing the driver or relevant personnel to immediately understand the critical condition of the vehicle and take appropriate measures, such as stopping the vehicle as soon as possible or contacting professional maintenance personnel, to avoid more serious consequences caused by continued use of the vehicle. At the same time, comprehensive fault diagnosis of n systems based on n sets of operating data can comprehensively and in-depth analyze the status of each vehicle system, providing detailed and accurate information for subsequent maintenance, facilitating rapid fault repair and ensuring vehicle safety. By presetting parameters such as fault probability and fault probability threshold, the fault judgment criteria and handling methods can be flexibly adjusted according to factors such as the actual vehicle usage and safety requirements. Different thresholds and preset values ​​can be set for different vehicle types, usage environments and user needs to achieve personalized fault diagnosis and management, and better meet the diverse needs of actual applications.

[0105] S203: Determine k fault probabilities among the n fault probabilities that are greater than a fault probability threshold.

[0106] In this embodiment, k is an integer less than n. A fault probability threshold is set in advance. This threshold is a critical value for judging whether a system may have a fault. Then, the n fault probabilities obtained previously are compared with this threshold to find the fault probability greater than the threshold, thereby obtaining k fault probabilities.

[0107] S204: Determine k systems and k groups of operating data corresponding to the k failure probabilities.

[0108] In this embodiment, after finding k fault probabilities greater than the fault probability threshold, the systems corresponding to these fault probabilities, that is, k systems, are determined. At the same time, the operating data corresponding to each of these k systems, that is, k groups of operating data, are found from the n groups of operating data previously obtained.

[0109] S205: Perform fault diagnosis on the k systems based on the k groups of operating data to obtain a first target diagnosis result.

[0110] In this embodiment, the k groups of operating data are checked for missing values, outliers, or erroneous data. For missing values, appropriate filling methods can be selected according to the specific situation, such as mean filling, median filling, or interpolation filling based on similar data. For outliers, it is necessary to determine whether they are real abnormalities or data entry errors. If they are erroneous data, they are corrected or deleted. Feature parameters that can reflect the operating status of the system are extracted from the preprocessed data. These features can be time domain features, such as mean, variance, peak, kurtosis, etc., or frequency domain features, such as frequency distribution, power spectral density, etc., or features based on other transform domains, such as wavelet features. From the many extracted features, the most representative and discriminative feature subset for fault diagnosis is selected. Some feature selection algorithms can be used, such as methods based on correlation analysis to remove redundant features that are highly correlated with other features, and feature selection methods based on machine learning, such as recursive feature elimination and feature importance assessment based on decision trees, to select features that contribute most to fault classification or prediction. Then, based on the experience and knowledge of domain experts, a series of diagnostic rules can be formulated. For example, if the engine speed fluctuation exceeds a certain range and the oil temperature rises abnormally, it is judged that the engine may have a mechanical fault. The extracted features are matched with these rules to obtain the fault diagnosis results. A mathematical model or physical model of the system can also be established to compare the actual operating data with the model prediction results to determine whether the system has a fault and the location and type of the fault. Machine learning algorithms can also be used to train a large amount of labeled data (known fault types and corresponding feature data) to establish a fault classification or regression model. According to these methods, fault diagnosis can be performed on the k systems based on the k groups of operating data to obtain the first target diagnostic result.

[0111] In summary, the implementation of the present invention has the following beneficial effects:

[0112] It can be seen that the vehicle fault diagnosis method described in the embodiment of the present invention first obtains the operating data of each of the n systems of the target vehicle within a preset historical time period to obtain n groups of operating data, and then determines the fault probability corresponding to each of the n systems based on the n groups of operating data to obtain n fault probabilities, and then determines k fault probabilities greater than the fault probability threshold among the n fault probabilities, and then determines the k systems and k groups of operating data corresponding to the k fault probabilities, and finally performs fault diagnosis on the k systems based on the k groups of operating data to obtain a first target diagnosis result, thereby improving the efficiency of vehicle fault diagnosis.

[0113] See also Figure 7 , Figure 7is a structural diagram of a vehicle fault diagnosis device provided in an embodiment of the present application. The vehicle fault diagnosis device 700 includes: an acquisition unit 701 and a processing unit 702;

[0114] The acquisition unit 701 is used to acquire the operating data of each of the n systems of the target vehicle within a preset historical time period to obtain n sets of operating data; n is an integer greater than 1;

[0115] The processing unit 702 is configured to determine a failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities;

[0116] Determine k fault probabilities greater than a fault probability threshold among the n fault probabilities; k is an integer less than n;

[0117] Determining k systems and k groups of operating data corresponding to the k failure probabilities;

[0118] Fault diagnosis is performed on the k systems based on the k groups of operating data to obtain a first target diagnosis result.

[0119] In some possible implementations, in determining the failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities, the processing unit 702 is specifically configured to:

[0120] acquiring a temperature value, a pressure value, and an information interaction frequency corresponding to a first system based on first operating data, to obtain a first temperature value, a first pressure value, and a first information interaction frequency; the first system being any one of the n systems, and the first operating data being operating data corresponding to the first system in the n sets of operating data;

[0121] Determining a temperature difference between the first temperature value and a preset temperature value, a pressure difference between the first pressure value and a preset pressure value, and an information interaction frequency difference between the first information interaction frequency and a preset information interaction frequency;

[0122] A failure probability corresponding to the first system is determined based on the temperature difference, the pressure difference, and the information interaction frequency difference.

[0123] In some possible implementations, in determining the failure probability corresponding to the first system based on the temperature difference, the pressure difference, and the information interaction frequency difference, the processing unit 702 is specifically configured to:

[0124] Obtaining a first mapping relationship between temperature difference and stability value, a second mapping relationship between pressure difference and stability value, and a third mapping relationship between information interaction frequency difference and stability value;

[0125] Determine a first stability value corresponding to the temperature difference based on the first mapping relationship;

[0126] Determining a second stability value corresponding to the pressure difference based on the second mapping relationship;

[0127] Determine a third stability value corresponding to the information interaction frequency difference based on the third mapping relationship;

[0128] determining a target stability value based on the first stability value, the second stability value, and the third stability value;

[0129] The failure probability corresponding to the first system is determined based on the target stability value; the larger the target stability value is, the smaller the failure probability corresponding to the first system is.

[0130] In some possible implementations, in determining the target stability value based on the first stability value, the second stability value, and the third stability value, the processing unit 702 is specifically configured to:

[0131] Determining a first weight corresponding to the first stability value, a second weight corresponding to the second stability value, and a third weight corresponding to the third stability value; the sum of the first weight, the second weight, and the third weight is 1;

[0132] Obtaining a load corresponding to the first system;

[0133] determining a first optimization factor corresponding to the load;

[0134] Optimizing the second weight based on the first optimization factor to obtain a first target weight;

[0135] Obtaining a bandwidth of an information interaction line corresponding to the first system to obtain a target bandwidth;

[0136] Determining a second optimization factor corresponding to the target bandwidth;

[0137] Optimizing the third weight based on the second optimization factor to obtain a second target weight;

[0138] Determining a third target weight based on the first target weight and the second target weight;

[0139] The target stability value is obtained by performing calculation based on the first stability value, the second stability value, the third stability value, the first target weight, the second target weight and the third target weight.

[0140] In some possible implementations, in determining the failure probability corresponding to the first system based on the target stability value, the processing unit 702 is specifically configured to:

[0141] determining a reference failure probability corresponding to the first system based on the target stability value;

[0142] Obtaining the running time of the first system;

[0143] determining a target adjustment parameter corresponding to the running time;

[0144] The reference failure probability is adjusted based on the target adjustment parameter to obtain a failure probability corresponding to the first system.

[0145] In some possible implementations, the processing unit 702 is further specifically configured to:

[0146] Determining a target failure probability of the target vehicle based on the n failure probabilities;

[0147] When the target failure probability is less than or equal to the preset failure probability, performing the operation of determining k failure probabilities greater than a failure probability threshold among the n failure probabilities;

[0148] When the target failure probability is greater than the preset failure probability, an alarm message is generated based on the target failure probability, and a fault diagnosis is performed on the n systems based on the n sets of operating data to obtain a second target diagnosis result; the alarm message is used to prompt that a serious fault has occurred in the target vehicle.

[0149] In some possible implementations, in determining the target failure probability of the target vehicle based on the n failure probabilities, the processing unit 702 is specifically configured to:

[0150] Determine an average of the n failure probabilities to obtain an average failure probability;

[0151] determining a standard deviation of the n failure probabilities;

[0152] determining a fine-tuning parameter corresponding to the standard deviation;

[0153] The average failure probability is adjusted based on the fine-tuning parameter to obtain the target failure probability.

[0154] See also Figure 8 , Figure 8 This is a schematic diagram of the structure of an electronic device provided by the embodiment of this application. Figure 8As shown, electronic device 800 includes a transceiver 801, a processor 802, and a memory 803. These are connected via a bus 804. The memory 803 is used to store computer programs and data, and the transceiver 801 can transmit the data stored in the memory 803 to the processor 802. The above program includes instructions for executing the following steps:

[0155] Obtaining operating data of each of n systems of a target vehicle within a preset historical time period to obtain n sets of operating data; n is an integer greater than 1;

[0156] determining a failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities;

[0157] Determine k fault probabilities greater than a fault probability threshold among the n fault probabilities; k is an integer less than n;

[0158] Determining k systems and k groups of operating data corresponding to the k failure probabilities;

[0159] Fault diagnosis is performed on the k systems based on the k groups of operating data to obtain a first target diagnosis result.

[0160] In some possible implementations, in determining the failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities, the program includes instructions for performing the following steps:

[0161] acquiring a temperature value, a pressure value, and an information interaction frequency corresponding to a first system based on first operating data, to obtain a first temperature value, a first pressure value, and a first information interaction frequency; the first system being any one of the n systems, and the first operating data being operating data corresponding to the first system in the n sets of operating data;

[0162] Determining a temperature difference between the first temperature value and a preset temperature value, a pressure difference between the first pressure value and a preset pressure value, and an information interaction frequency difference between the first information interaction frequency and a preset information interaction frequency;

[0163] A failure probability corresponding to the first system is determined based on the temperature difference, the pressure difference, and the information interaction frequency difference.

[0164] In some possible implementations, in terms of determining the failure probability corresponding to the first system based on the temperature difference, the pressure difference, and the information exchange frequency difference, the program includes instructions for executing the following steps:

[0165] Obtaining a first mapping relationship between temperature difference and stability value, a second mapping relationship between pressure difference and stability value, and a third mapping relationship between information interaction frequency difference and stability value;

[0166] Determine a first stability value corresponding to the temperature difference based on the first mapping relationship;

[0167] Determining a second stability value corresponding to the pressure difference based on the second mapping relationship;

[0168] Determine a third stability value corresponding to the information interaction frequency difference based on the third mapping relationship;

[0169] determining a target stability value based on the first stability value, the second stability value, and the third stability value;

[0170] The failure probability corresponding to the first system is determined based on the target stability value; the larger the target stability value is, the smaller the failure probability corresponding to the first system is.

[0171] In some possible implementations, in determining the target stability value based on the first stability value, the second stability value, and the third stability value, the program includes instructions for performing the following steps:

[0172] Determining a first weight corresponding to the first stability value, a second weight corresponding to the second stability value, and a third weight corresponding to the third stability value; the sum of the first weight, the second weight, and the third weight is 1;

[0173] Obtaining a load corresponding to the first system;

[0174] determining a first optimization factor corresponding to the load;

[0175] Optimizing the second weight based on the first optimization factor to obtain a first target weight;

[0176] Obtaining a bandwidth of an information interaction line corresponding to the first system to obtain a target bandwidth;

[0177] Determining a second optimization factor corresponding to the target bandwidth;

[0178] Optimizing the third weight based on the second optimization factor to obtain a second target weight;

[0179] Determining a third target weight based on the first target weight and the second target weight;

[0180] The target stability value is obtained by performing calculation based on the first stability value, the second stability value, the third stability value, the first target weight, the second target weight and the third target weight.

[0181] In some possible implementations, in terms of determining the failure probability corresponding to the first system based on the target stability value, the program includes instructions for executing the following steps:

[0182] determining a reference failure probability corresponding to the first system based on the target stability value;

[0183] Obtaining the running time of the first system;

[0184] determining a target adjustment parameter corresponding to the running time;

[0185] The reference failure probability is adjusted based on the target adjustment parameter to obtain a failure probability corresponding to the first system.

[0186] In some possible implementations, the above program includes instructions for performing the following steps:

[0187] Determining a target failure probability of the target vehicle based on the n failure probabilities;

[0188] When the target failure probability is less than or equal to the preset failure probability, performing the operation of determining k failure probabilities greater than a failure probability threshold among the n failure probabilities;

[0189] When the target failure probability is greater than the preset failure probability, an alarm message is generated based on the target failure probability, and a fault diagnosis is performed on the n systems based on the n sets of operating data to obtain a second target diagnosis result; the alarm message is used to prompt that a serious fault has occurred in the target vehicle.

[0190] In some possible implementations, in determining the target failure probability of the target vehicle based on the n failure probabilities, the program includes instructions for performing the following steps:

[0191] Determine an average of the n failure probabilities to obtain an average failure probability;

[0192] determining a standard deviation of the n failure probabilities;

[0193] determining a fine-tuning parameter corresponding to the standard deviation;

[0194] The average failure probability is adjusted based on the fine-tuning parameter to obtain the target failure probability.

[0195] It should be understood that the electronic devices in this application may include vehicle fault diagnosis devices, smartphones (such as Android phones, iOS phones, Windows Phone phones, etc.), tablet computers, PDAs, laptop computers, mobile Internet devices (MIDs) or wearable devices, or servers, edge computing nodes, etc. The above electronic devices are only examples and are not exhaustive, and include but are not limited to the above electronic devices.

[0196] The embodiments of the present application further provide a computer-readable storage medium, which stores a computer program. The computer program is executed by a processor to implement part or all of the steps of any one of the methods described in the above method embodiments.

[0197] The embodiments of the present application also provide a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute part or all of the steps of any one of the methods described in the above method embodiments.

[0198] It should be noted that for the aforementioned method implementations, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that this application is not limited by the order of the actions described, because according to this application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the implementations described in the specification are all optional implementations, and the actions and modules involved are not necessarily required by this application.

[0199] In the above embodiments, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, please refer to the relevant description of other embodiments.

[0200] In the several embodiments provided in this application, it should be understood that the disclosed devices can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0201] Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, that is, they may be located in one place or distributed across multiple network units. Some or all of these units may be selected to achieve the purpose of this embodiment according to actual needs.

[0202] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or in the form of software program modules.

[0203] If the integrated unit is implemented in the form of a software program module and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product, which is stored in a memory and includes a number of instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to execute all or part of the steps of the various implementation methods of the present application. The aforementioned memory includes: various media that can store program codes, such as a USB flash drive, a read-only memory (ROM), a random access memory (RAM), a mobile hard disk, a magnetic disk or an optical disk.

[0204] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.

[0205] The above is a detailed introduction to the implementation methods of the present application. Specific examples are used herein to illustrate the principles and implementation methods of the present application. The description of the above implementation methods is only used to help understand the method and core idea of ​​the present application. At the same time, for those skilled in the art, based on the ideas of the present application, there may be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A vehicle fault diagnosis method, characterized in that: include: Obtaining operating data of each of n systems of the target vehicle within a preset historical time period to obtain n sets of operating data; n is an integer greater than 1; determining a failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities; Determine k fault probabilities greater than a fault probability threshold among the n fault probabilities; k is an integer less than n; Determining k systems and k groups of operating data corresponding to the k failure probabilities; Fault diagnosis is performed on the k systems based on the k groups of operating data to obtain a first target diagnosis result.

2. The method according to claim 1, wherein Determining the failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities includes: acquiring a temperature value, a pressure value, and an information interaction frequency corresponding to a first system based on first operating data, to obtain a first temperature value, a first pressure value, and a first information interaction frequency; the first system being any one of the n systems, and the first operating data being operating data corresponding to the first system in the n sets of operating data; Determining a temperature difference between the first temperature value and a preset temperature value, a pressure difference between the first pressure value and a preset pressure value, and an information interaction frequency difference between the first information interaction frequency and a preset information interaction frequency; A failure probability corresponding to the first system is determined based on the temperature difference, the pressure difference, and the information interaction frequency difference.

3. The method according to claim 2, wherein The determining the failure probability corresponding to the first system based on the temperature difference, the pressure difference, and the information interaction frequency difference includes: Obtaining a first mapping relationship between temperature difference and stability value, a second mapping relationship between pressure difference and stability value, and a third mapping relationship between information interaction frequency difference and stability value; Determine a first stability value corresponding to the temperature difference based on the first mapping relationship; Determining a second stability value corresponding to the pressure difference based on the second mapping relationship; Determine a third stability value corresponding to the information interaction frequency difference based on the third mapping relationship; determining a target stability value based on the first stability value, the second stability value, and the third stability value; The failure probability corresponding to the first system is determined based on the target stability value; the larger the target stability value is, the smaller the failure probability corresponding to the first system is.

4. The method according to claim 2, wherein The determining of a target stability value based on the first stability value, the second stability value, and the third stability value includes: Determining a first weight corresponding to the first stability value, a second weight corresponding to the second stability value, and a third weight corresponding to the third stability value; the sum of the first weight, the second weight, and the third weight is 1; Obtaining a load corresponding to the first system; determining a first optimization factor corresponding to the load; Optimizing the second weight based on the first optimization factor to obtain a first target weight; Obtaining a bandwidth of an information interaction line corresponding to the first system to obtain a target bandwidth; Determining a second optimization factor corresponding to the target bandwidth; Optimizing the third weight based on the second optimization factor to obtain a second target weight; Determining a third target weight based on the first target weight and the second target weight; The target stability value is obtained by performing calculation based on the first stability value, the second stability value, the third stability value, the first target weight, the second target weight and the third target weight.

5. The method according to claim 4, wherein The determining, based on the target stability value, a failure probability corresponding to the first system includes: determining a reference failure probability corresponding to the first system based on the target stability value; Obtaining the running time of the first system; determining a target adjustment parameter corresponding to the running time; The reference failure probability is adjusted based on the target adjustment parameter to obtain a failure probability corresponding to the first system.

6. The method according to any one of claims 1 to 5, wherein: The method further comprises: Determining a target failure probability of the target vehicle based on the n failure probabilities; When the target failure probability is less than or equal to the preset failure probability, performing the operation of determining k failure probabilities greater than a failure probability threshold among the n failure probabilities; When the target failure probability is greater than the preset failure probability, an alarm message is generated based on the target failure probability, and a fault diagnosis is performed on the n systems based on the n sets of operating data to obtain a second target diagnosis result; the alarm message is used to prompt that a serious fault has occurred in the target vehicle.

7. The method according to claim 6, wherein Determining a target failure probability of the target vehicle based on the n failure probabilities includes: Determine an average of the n failure probabilities to obtain an average failure probability; determining a standard deviation of the n failure probabilities; determining a fine-tuning parameter corresponding to the standard deviation; The average failure probability is adjusted based on the fine-tuning parameter to obtain the target failure probability.

8. A vehicle fault diagnosis device, characterized in that: The device comprises: an acquisition unit and a processing unit; The acquisition unit is used to acquire the operating data of each of the n systems of the target vehicle within a preset historical time period to obtain n sets of operating data; n is an integer greater than 1; The processing unit is configured to determine a failure probability corresponding to each of the n systems based on the n sets of operating data to obtain n failure probabilities; Determine k fault probabilities greater than a fault probability threshold among the n fault probabilities; k is an integer less than n; Determining k systems and k groups of operating data corresponding to the k failure probabilities; Fault diagnosis is performed on the k systems based on the k groups of operating data to obtain a first target diagnosis result.

9. An electronic device, characterized in that: The method comprises a processor, a memory, a communication interface, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the processor, and the one or more programs include instructions for executing the steps in the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and the computer program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images