Vehicle fault determination method and device and vehicle

Abstract

The invention discloses a vehicle fault determination method and device and a vehicle. The method comprises the steps that current operation data of the compressor system in the vehicle are obtained, and the current operation data are used for recording operation attributes of any component in the compressor system; fault prediction analysis is carried out on the current operation data to obtain a fault prediction result, and the fault prediction result is used for representing the fault occurrence probability of multiple preset fault categories in the current operation data; in response to the situation that the fault occurrence probability corresponding to any preset fault category is larger than a preset probability threshold value, a first maintenance strategy is determined based on any preset fault category, and the first maintenance strategy is used for repairing a fault corresponding to any preset fault category in the compressor system; and maintaining the compressor system based on the at least one first maintenance strategy. The technical problems that the diagnosis mode of the exhaust temperature of the compressor is single and the fault reason of the compressor is difficult to accurately recognize in the related technology are solved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle heat pump system control, in particular to a vehicle fault determination method and device and vehicle. BACKGROUND

[0002] In a conventional vehicle heat pump system, the diagnosis of the fault of the excessively high compressor discharge temperature mainly relies on artificial experience or a fixed threshold-based judgment method. The above-mentioned diagnosis method of the compressor discharge temperature is not only single, but also difficult to accurately identify the fault cause of the compressor.

[0003] At present, no effective solution has been proposed for the above problems. SUMMARY

[0004] The embodiments of the present application provide a vehicle fault determination method, device and vehicle, so as to at least solve the technical problem that the diagnosis method of the compressor discharge temperature in the related art is single and difficult to accurately identify the fault cause of the compressor.

[0005] According to an aspect of the embodiments of the present application, a vehicle fault determination method is provided, including: obtaining current operation data of a compressor system in a vehicle, wherein the current operation data is used to record the operation attribute of any component in the compressor system; performing fault prediction analysis on the current operation data to obtain a fault prediction result, wherein the fault prediction result is used to represent the fault occurrence probability of a plurality of preset fault categories in the current operation data; in response to the fault occurrence probability corresponding to any preset fault category being greater than a preset probability threshold, determining a first maintenance strategy based on any preset fault category, wherein the first maintenance strategy is used to repair the fault in the compressor system corresponding to any preset fault category; and maintaining the compressor system based on at least one first maintenance strategy.

[0006] Further, the maintenance of the compressor system based on at least one first maintenance strategy includes: determining the execution priority of any first maintenance strategy based on a preset execution rule; determining a target maintenance strategy based on the first maintenance strategy and the execution priority, wherein the target maintenance strategy is used to execute any first maintenance strategy according to the execution priority; and maintaining the compressor system based on the target maintenance strategy.

[0007] Further, the current operation data is subjected to fault prediction analysis to obtain a fault prediction result, including: performing fault prediction analysis on the current operation data based on a target diagnosis model to obtain the fault prediction result, wherein the target diagnosis model is trained based on operation data samples, the operation data samples include normal operation data samples and fault operation data samples, the fault operation data samples include a plurality of preset fault categories, and the plurality of preset fault categories include refrigerant charge abnormality, condenser blockage, cooling fan failure, compressor wear, compressor failure, compressor oil return failure, expansion valve failure, temperature sensor abnormality, and vehicle working condition abnormality.

[0008] Further, before performing fault prediction analysis on the current operation data based on the target diagnosis model, the method further includes: obtaining operation data samples of the compressor system in a preset time period; training an initial diagnosis model based on the operation data samples to obtain fault prediction probabilities of the plurality of preset fault categories in the operation data samples; and adjusting training parameters of the initial diagnosis model based on real fault probabilities corresponding to the operation data samples and the fault prediction probabilities to obtain the target diagnosis model.

[0009] Further, obtaining the operation data samples of the compressor system in the preset time period includes: obtaining first operation data samples of the compressor system in the preset time period; performing feature extraction on the first operation data samples to obtain feature data samples; performing dimension reduction processing on the feature data samples to obtain second operation data samples; dividing the second operation data samples to obtain normal operation data samples and fault operation data samples, wherein the normal operation data samples carry normal labels, and the fault operation data samples carry fault labels corresponding to any preset fault category; and determining the operation data samples based on the normal operation data samples and the fault operation data samples.

[0010] Further, obtaining the current operation data of the compressor system in the vehicle includes: obtaining perception data based on vehicle-mounted sensors of the vehicle, wherein the perception data includes perception data collected by at least one sensor; performing preprocessing on the perception data to obtain initial current operation data; and performing data fusion on the initial current operation data to obtain the current operation data.

[0011] According to another aspect of the embodiments of the present application, a vehicle fault determination apparatus is further provided, comprising: an acquisition module, configured to acquire current operation data of a compressor system in a vehicle, wherein the current operation data is used to record operation attributes of any component in the compressor system; an analysis module, configured to perform fault prediction analysis on the current operation data to obtain a fault prediction result, wherein the fault prediction result is used to represent fault occurrence probabilities of a plurality of preset fault categories in the current operation data; a determination module, configured to determine a first maintenance strategy based on any preset fault category in response to the fault occurrence probability corresponding to the any preset fault category being greater than a preset probability threshold, wherein the first maintenance strategy is used to repair a fault in the compressor system corresponding to the any preset fault category; and a maintenance module, configured to perform maintenance on the compressor system based on at least one first maintenance strategy.

[0012] Further, the maintenance module is further configured to determine an execution priority of any first maintenance strategy based on a preset execution rule, determine a target maintenance strategy based on the first maintenance strategy and the execution priority, wherein the target maintenance strategy is used to execute any first maintenance strategy according to the execution priority, and perform maintenance on the compressor system based on the target maintenance strategy.

[0013] Further, the analysis module is further configured to perform fault prediction analysis on the current operation data based on a target diagnosis model to obtain a fault prediction result, wherein the target diagnosis model is obtained based on training of operation data samples, the operation data samples include normal operation data samples and fault operation data samples, the fault operation data samples include a plurality of preset fault categories, and the plurality of preset fault categories include refrigerant charge abnormality, condenser blockage, cooling fan failure, compressor wear, compressor failure, compressor oil return failure, expansion valve failure, temperature sensor abnormality, and vehicle working condition abnormality.

[0014] Further, before performing fault prediction analysis on the current operation data based on the target diagnosis model, the vehicle fault determination apparatus further comprises a training module, configured to acquire operation data samples of the compressor system in a preset time period, train an initial diagnosis model based on the operation data samples to obtain fault prediction probabilities of a plurality of preset fault categories in the operation data samples, and adjust training parameters of the initial diagnosis model based on real fault probabilities corresponding to the operation data samples and the fault prediction probabilities to obtain the target diagnosis model.

[0015] Further, the training module is further configured to acquire a first operation data sample of the compressor system in a preset time period, perform feature extraction on the first operation data sample to obtain a feature data sample, perform dimension reduction processing on the feature data sample to obtain a second operation data sample, divide the second operation data sample to obtain a normal operation data sample and a fault operation data sample, wherein the normal operation data sample carries a normal label, and the fault operation data sample carries a fault label corresponding to any preset fault category, and determine the operation data sample based on the normal operation data sample and the fault operation data sample.

[0016] Further, the acquisition module is further configured to acquire perception data based on a vehicle-mounted sensor of the vehicle, wherein the perception data comprises perception data collected by at least one sensor, pre-process the perception data to obtain initial current operation data, and perform data fusion on the initial current operation data to obtain the current operation data.

[0017] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, and the storage medium stores a computer program, wherein the computer program is configured to execute the vehicle fault determination method in the various embodiments of the present application when running on a computer or a processor.

[0018] According to another aspect of the embodiments of the present application, an electronic device is also provided, comprising a memory and a processor, the memory stores a computer program, and the processor is configured to execute the computer program to perform the vehicle fault determination method in the various embodiments of the present application.

[0019] According to another aspect of the embodiments of the present application, a vehicle is also provided, comprising a memory and a processor, the memory stores a computer program, and the computer program is configured to execute the vehicle fault determination method in the various embodiments of the present application when executed by the processor.

[0020] According to another aspect of the embodiments of the present application, a computer program product is also provided, comprising a computer program, and the computer program is configured to implement the vehicle fault determination method in the various embodiments of the present application when executed by a processor.

[0021] In the embodiment of the present application, the current operation data of the compressor system in the vehicle is obtained, wherein the current operation data is used to record the operation attributes of any component in the compressor system; the current operation data is subjected to fault prediction analysis to obtain a fault prediction result, wherein the fault prediction result is used to represent the fault occurrence probability of a plurality of preset fault categories in the current operation data; in response to the fault occurrence probability corresponding to any preset fault category being greater than a preset probability threshold, a first maintenance strategy is determined based on any preset fault category, wherein the first maintenance strategy is used to repair the fault in the compressor system corresponding to any preset fault category. The technical scheme as a whole achieves the purpose of accurately identifying the reason for the high exhaust temperature of the compressor, thereby realizing the technical effect of improving the efficiency and accuracy of compressor fault diagnosis, and further solving the technical problems in the related art that the diagnosis method of the exhaust temperature of the compressor is single and it is difficult to accurately identify the reason for the compressor fault. BRIEF DESCRIPTION OF DRAWINGS

[0022] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0023] Figure 1 is a flowchart of an optional vehicle fault determination method according to an embodiment of the present application;

[0024] Figure 2 is a module schematic diagram of an optional vehicle fault determination device according to an embodiment of the present application. DETAILED DESCRIPTION

[0025] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0026] In order for those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the accompanying drawings of the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, but not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should fall within the scope of protection of the present application.

[0027] A heat pump system is a device that can absorb heat from a low-temperature heat source and transfer it to a high-temperature heat source, and is widely used in heating, refrigeration and other fields. In the automotive industry, a heat pump system is used for vehicle heating and air conditioning, and heat transfer is achieved through the operation of a compressor.

[0028] Electronic expansion valves are a key component in heat pump systems, used to precisely regulate refrigerant flow and control the superheat of refrigerant at the evaporator outlet to maintain high efficiency operation of the system.

[0029] It should be noted that the terms "first", "second", and the like in the description and in the claims of the present application and above-described accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular sequential or chronological order. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0030] According to an embodiment of the present application, an embodiment of a vehicle fault determination method is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0031] The embodiment of the present application provides a vehicle fault determination method. The vehicle fault determination method can be used to provide a vehicle fault determination function for a preset application scenario. The above-mentioned preset application scenario can include the following scenarios in the field of vehicles: commuting autonomous driving scenarios, artificial intelligence (AI) for home car driving scenarios, automatic parking assistance (APA) scenarios (such as memory parking for self-owned parking spaces in garages, intelligent parking for designated parking spaces in parking lots, etc.), intelligent navigation assistance (NGP) scenarios in urban areas or high-speed areas. In addition, the above-mentioned preset application scenario can include but is not limited to: vehicle fault determination scenarios of intelligent driving trucks or unmanned trucks in the field of logistics transportation, vehicle fault determination scenarios of autonomous driving agricultural vehicles in the field of agricultural machinery.

[0032] Figure 1 is a flowchart of an optional vehicle fault determination method according to an embodiment of the present application, as shown in Figure 1 The method comprises the following steps:

[0033] Step S10, obtaining current operation data of the compressor system in the vehicle, wherein the current operation data is used to record the operation attributes of any component in the compressor system;

[0034] In the embodiment of the present application, the compressor system can be understood as the core part of the vehicle thermal management system, mainly responsible for the compression process of the refrigerant to realize the transfer of heat energy. Exemplarily, the compressor system usually includes a compressor, a condenser, an expansion valve (such as an electronic expansion valve), an evaporator, and related pipelines and control units, which are not limited here.

[0035] The current operation data can be understood as a collection of the operation state and attribute information of each component in the compressor system within a period of time. Exemplarily, the current operation data includes but is not limited to the discharge temperature and suction temperature of the compressor, the discharge pressure and suction pressure of the compressor, the temperature of the condenser, the opening of the electronic expansion valve, the speed of the compressor, the ambient temperature, the fan speed, the refrigerant charge, the system vibration data, etc., which are not limited here.

[0036] Obtaining the current operation data of the compressor system in the vehicle can be understood as using sensors installed at key positions of the compressor system to monitor and collect various parameter information in real time when the compressor system is running. Exemplarily, obtaining the current operation data of the compressor system in the vehicle includes but is not limited to the discharge temperature, suction temperature, discharge pressure and suction pressure of the compressor, the temperature of the condenser, the opening of the electronic expansion valve, the speed of the compressor, and the ambient temperature, etc., which are not limited here.

[0037] The current operation data used to record the operation attributes of any component in the compressor system can be understood as that the current operation data contains the real-time state and performance indicators of each component of the compressor system. Exemplarily, the speed and temperature of the compressor reflect the working intensity and heat generation, the temperature of the condenser reflects the heat dissipation efficiency, and the opening of the electronic expansion valve indicates the adjustment state of the refrigerant flow, which are not limited here.

[0038] In the embodiment of the present application, by monitoring and collecting the operation data of the compressor and its related components in the vehicle heat pump system in real time, it is ensured that the fault diagnosis system can analyze based on real-time and comprehensive operation data.

[0039] Step S12, performing fault prediction analysis on the current operation data to obtain a fault prediction result, wherein the fault prediction result is used to represent the fault occurrence probability of a plurality of preset fault categories in the current operation data;

[0040] In the embodiment of the present application, the fault prediction result can be understood as a quantitative result of predicting the possibility of occurrence of a preset fault category in the compressor system after analyzing the obtained current operation data. This result is presented in the form of probability, and each preset fault category has a corresponding probability value indicating the possibility of occurrence of the fault category under the given current operation data.

[0041] The plurality of preset fault categories can be understood as various potential faults that may cause the compressor discharge temperature to be too high in the heat pump system. For example, the preset fault categories include, but are not limited to, excessive refrigerant charge, insufficient refrigerant charge, poor heat dissipation (such as condenser blockage, cooling fan failure), compressor itself problem (such as wear or failure, oil return problem), expansion valve failure, long time high load operation, temperature sensor abnormality, etc., which are not limited herein.

[0042] The fault prediction analysis on the current operation data to obtain the fault prediction result can be understood as inputting the real-time collected operation data of the vehicle compressor system into the pre-trained model for processing and analysis. Through the calculation of the model, it can be predicted whether the system may fail and the specific fault type that may occur under the current operating environment.

[0043] The fault prediction result for indicating the fault occurrence probability of the plurality of preset fault categories in the current operation data can be understood as that the fault prediction result obtained through the fault prediction analysis gives a probability value for each preset possible fault category, which is used to reflect the possibility of occurrence of the fault category under the current operation state.

[0044] In the embodiment of the present application, the fault prediction analysis by the model can quantize the potential risks of different fault categories under the current operation state in the form of probability, which provides strong support for the intelligent maintenance and fault prevention of the automotive heat pump system.

[0045] In step S14, in response to the fault occurrence probability corresponding to any preset fault category being greater than a preset probability threshold, a first maintenance strategy is determined based on any preset fault category, wherein the first maintenance strategy is used to repair the fault in the compressor system corresponding to any preset fault category.

[0046] In the embodiment of the present application, the preset probability threshold can be understood as a defined value for judging the possibility of occurrence of a certain preset fault category. For example, the preset probability threshold can be set to 0.6 or 0.7 according to actual application requirements and reliability requirements, which are not limited herein.

[0047] The first maintenance strategy can be understood as identifying that a certain preset fault category has a high probability of occurrence, and the system recommends a first-hand operation guide or suggestion for repairing or mitigating the fault. For example, if the refrigerant charge is too much, the first maintenance strategy can be to adjust the refrigerant charge to the normal range; if the condenser is blocked, clean or replace the condenser; if the compressor itself is worn or fails, professional inspection is recommended, which may require replacement of compressor parts or the entire compressor, which is not limited here.

[0048] In response to any preset fault category corresponding to the fault occurrence probability being greater than the preset probability threshold, determining the first maintenance strategy based on any preset fault category can be understood as follows: if the occurrence probability of a certain preset fault category in the current operation data obtained through model analysis exceeds the set preset probability threshold, the system will determine the first maintenance strategy based on the preset fault category, aiming to take prompt action to correct or prevent the fault and ensure the stable and safe operation of the compressor system.

[0049] In the embodiments of the present application, by responding to any preset fault category corresponding to the fault occurrence probability being greater than the preset probability threshold, determining the first maintenance strategy based on any preset fault category, the system can respond to potential faults in the compressor system in a timely manner and take targeted maintenance measures, thereby avoiding greater losses caused by fault escalation and maintaining the optimal operating state of the vehicle heat pump system.

[0050] Step S16, maintaining the compressor system based on at least one first maintenance strategy.

[0051] In the embodiments of the present application, maintaining the compressor system based on at least one first maintenance strategy can be understood as implementing specific maintenance operations or taking appropriate preventive measures on the compressor system based on the determined first maintenance strategy to eliminate or avoid the occurrence of potential faults.

[0052] In the embodiments of the present application, through the above steps, the problems of the compressor system can be solved and the expansion of the fault can be prevented, thereby ensuring the continuous and stable operation of the vehicle thermal management system and improving the overall driving experience and safety.

[0053] In the embodiment of the present application, the current operation data of the compressor system in the vehicle is obtained, wherein the current operation data is used to record the operation attributes of any component in the compressor system; the fault prediction analysis is performed on the current operation data to obtain the fault prediction result, wherein the fault prediction result is used to represent the fault occurrence probability of a plurality of preset fault categories in the current operation data; in response to the fault occurrence probability corresponding to any preset fault category being greater than a preset probability threshold, a first maintenance strategy is determined based on any preset fault category, wherein the first maintenance strategy is used to repair the fault in the compressor system corresponding to any preset fault category. The technical scheme as a whole achieves the purpose of accurately identifying the reason for the high exhaust temperature of the compressor, thereby realizing the technical effect of improving the efficiency and accuracy of the compressor fault diagnosis, and further solving the technical problems in the related art that the diagnosis method of the exhaust temperature of the compressor is single and it is difficult to accurately identify the fault reason of the compressor.

[0054] Further, in step S16, the compressor system is maintained based on at least one first maintenance strategy, including the following steps:

[0055] Step S161, determining the execution priority of any first maintenance strategy based on a preset execution rule;

[0056] Step S162, determining a target maintenance strategy based on the first maintenance strategy and the execution priority, wherein the target maintenance strategy is used to execute any first maintenance strategy according to the execution priority;

[0057] Step S163, maintaining the compressor system based on the target maintenance strategy.

[0058] In the embodiment of the present application, the preset execution rule can be understood as a logical framework or algorithm defined in advance, which is used to determine the execution order and priority between different first maintenance strategies. The preset execution rule is usually based on the influence degree of the fault category on the safety and efficiency of the system operation, the urgent demand of the maintenance action, the consideration of the required time and resources, and the possible risk-benefit ratio. For example, if the fault categories include "severe wear of the compressor" and "slight leakage of the refrigerant", the preset execution rule may prefer to handle "severe wear of the compressor", which is not limited here.

[0059] The execution priority determines the sequence of the maintenance action, which is used to indicate which one should be handled first when multiple maintenance strategies need to be executed. For example, if both "excessive refrigerant charge" and "condenser blockage" are predicted by the model, and the prediction probability of the former is higher, then the maintenance strategy of "adjusting the refrigerant charge" will be given a higher execution priority, which is not limited here.

[0060] The target maintenance strategy can be understood as a specific maintenance plan determined based on the execution priority. The target maintenance strategy contains a set of maintenance strategies that the system finally selects to execute according to the preset execution rules and the currently identified fault categories. For example, if "excessive refrigerant charge" and "compressor oil return fault" are both predicted as high probability events, the target maintenance strategy may first select to adjust the refrigerant charge, and then check the oil return condition of the compressor, and clean or replace the oil return equipment if necessary. The formulation and execution of the target maintenance strategy ensure that the maintenance work is both targeted and systematic in solving problems, improving maintenance efficiency and vehicle operation safety.

[0061] The execution priority of any first maintenance strategy determined based on the preset execution rules can be understood as that the system determines when and under what conditions each first maintenance strategy should be executed according to the preset execution rules (such as the severity of the fault, the impact on system operation, the availability of required maintenance resources, etc.). The determination of the execution priority ensures that when facing multiple faults, the problems that have the greatest impact on system stability, safety or operating efficiency can be handled first.

[0062] The target maintenance strategy determined based on the first maintenance strategy and the execution priority can be understood as that the system formulates the target maintenance strategy by comprehensively considering all first maintenance strategies corresponding to the predicted potential faults and all execution priorities corresponding to the potential faults. The target maintenance strategy includes at least one first maintenance strategy, thereby realizing the most efficient and reasonable way to solve or prevent faults in the system.

[0063] The target maintenance strategy for executing any first maintenance strategy according to the execution priority can be understood as that the target maintenance strategy indicates how the maintenance personnel should sequentially or simultaneously execute multiple first maintenance strategies according to the priority order, thereby ensuring that the maintenance activities are orderly and efficient, and each strategy is handled at the appropriate time, avoiding resource waste and time delay.

[0064] The maintenance of the compressor system based on the target maintenance strategy can be understood as that the maintenance personnel or the automated maintenance system will execute specific maintenance operations on the compressor system according to the maintenance order in the target maintenance strategy.

[0065] In the embodiments of the present application, through the process of determining the priority of the maintenance strategy and formulating and implementing the target maintenance strategy, the maintenance process can be effectively managed and optimized in complex and variable fault scenarios, and the maintenance quality and efficiency are improved.

[0066] Further, in step S12, the current operation data is analyzed for fault prediction to obtain a fault prediction result, including the following steps:

[0067] The target diagnosis model is trained based on the operation data samples, and the operation data samples include normal operation data samples and fault operation data samples. The fault operation data samples include multiple preset fault categories, and the multiple preset fault categories include refrigerant charge abnormality, condenser blockage, cooling fan failure, compressor wear, compressor failure, compressor oil return failure, expansion valve failure, temperature sensor abnormality, and vehicle working condition abnormality.

[0068] In the embodiment of the present application, the target diagnosis model can be understood as a model trained by machine learning, such as a deep learning algorithm (such as a CNN-LSTM neural network), for analyzing the current operation data of the compressor system and predicting possible fault categories. The model is trained on a large number of historical operation data samples and can identify and distinguish between normal and abnormal operating states, as well as the characteristics of specific fault categories.

[0069] The operation data sample can be understood as a collection of historical data of the compressor system under different operating states, including data during normal operation and data under various fault states. The operation data sample is used to train and optimize the target diagnosis model so that it can accurately predict faults.

[0070] The normal operation data sample can be understood as the operation data of the compressor system under normal working conditions without faults. The normal operation data sample reflects the performance indicators of the system under normal conditions, including but not limited to the discharge temperature, suction temperature, discharge pressure, suction pressure, condenser temperature, electronic expansion valve opening, compressor speed, and ambient temperature of the compressor.

[0071] The fault operation data sample can be understood as the operation data of the compressor system under multiple preset fault categories, which is used to train the model to identify the characteristics of multiple preset fault states. The multiple preset fault categories include refrigerant charge abnormality, condenser blockage, cooling fan failure, compressor wear, compressor failure, compressor oil return failure, expansion valve failure, temperature sensor abnormality, and vehicle working condition abnormality.

[0072] The refrigerant charge abnormality can be understood as the refrigerant charge exceeding the normal range, and both excessive or insufficient charge can be classified as this type of fault.

[0073] The condenser blockage can be understood as the presence of blockage in the heat exchanger (condenser), which reduces the heat dissipation efficiency of the system and causes the compressor discharge temperature to rise.

[0074] The cooling fan failure can be understood as the fan for heat dissipation stopping working or efficiency decreasing, which cannot effectively reduce the operating temperature of the compressor.

[0075] The compressor wear can be understood as the wear of the internal parts of the compressor due to long-time operation, which affects the efficiency of the compressor.

[0076] The compressor failure can be understood as including but not limited to the compressor failure to start, unstable operation, and other serious conditions, which directly affects the normal operation of the system.

[0077] The compressor oil return failure can be understood as the poor oil return of the compressor, which leads to insufficient lubrication of the compressor and increases the wear and failure probability.

[0078] The expansion valve failure can be understood as the expansion valve controlling the refrigerant flow in the refrigeration cycle, and its failure will directly affect the refrigeration effect and the load of the compressor.

[0079] The temperature sensor anomaly can be understood as inaccurate readings of the temperature sensor, which can lead to incorrect judgment of the operating state of the compressor by the system and affect the accuracy of fault diagnosis.

[0080] The vehicle working condition anomaly can be understood as non-standard or harsh conditions encountered by the vehicle during operation, such as long-time high-load operation, extreme temperature environment, etc., which may indirectly cause the failure of the compressor system. Exemplarily, the vehicle working condition anomaly includes an environment temperature of -7℃, 30℃, and a vehicle speed of 50-80 km / h, which is not limited herein.

[0081] In the embodiment of the present application, the fault prediction analysis based on the target diagnosis model can significantly improve the stability, safety and economy of the operation of the compressor of the heat pump system.

[0082] Further, before the fault prediction analysis based on the target diagnosis model on the current operation data, the method further comprises the following steps:

[0083] Obtaining the operation data sample of the compressor system within a preset time period;

[0084] Training the initial diagnosis model based on the operation data sample to obtain the fault prediction probability of a plurality of preset fault categories in the operation data sample;

[0085] Adjusting the training parameters of the initial diagnosis model based on the real fault probability and the fault prediction probability corresponding to the operation data sample to obtain the target diagnosis model.

[0086] In the embodiment of the present application, the preset time period can be understood as a specific time range set for collecting the operation data sample of the compressor system, for example, the preset time period can be the past one month, which is not limited herein.

[0087] Acquiring operating data samples from the compressor system within a preset time period can be understood as collecting various system operating parameter information, such as temperature, pressure, speed, and environmental conditions, over a specific period of time using sensors, monitoring equipment, and other data acquisition tools installed on the compressor system. These operating data samples include data from normal operating conditions and abnormal data from operations under preset fault categories.

[0088] The initial diagnosis model is trained based on the operating data samples to obtain the fault prediction probabilities of multiple preset fault categories in the operating data samples. It can be understood that the initial diagnosis model establishes the correlation between operating data and fault categories by learning the features in normal and abnormal data, so that it can predict the possible fault types and fault prediction probabilities of the system under the current operating data.

[0089] Adjusting the training parameters of the initial diagnosis model based on the actual failure probability and the predicted failure probability corresponding to the operating data samples to obtain the target diagnosis model can be understood as the model adjusting its internal parameters (such as weights, biases, etc.) according to the difference between the actual failure probability and the predicted failure probability corresponding to the operating data samples to minimize the prediction error. Finally, the fully trained and optimized model becomes the target diagnosis model.

[0090] In the embodiment of the present invention, by continuously training and optimizing the model, the model can accurately identify the operating status of the compressor system and predict potential faults, thereby providing strong support for preventive maintenance and fault diagnosis.

[0091] Furthermore, obtaining operation data samples of the compressor system within a preset time period includes the following steps:

[0092] Acquire a first operating data sample of the compressor system within a preset time period;

[0093] Performing feature extraction on the first running data sample to obtain a feature data sample;

[0094] Performing dimensionality reduction processing on the feature data sample to obtain a second running data sample;

[0095] Dividing the second operation data sample to obtain a normal operation data sample and a fault operation data sample, wherein the normal operation data sample carries a normal label, and the fault operation data sample carries a fault label corresponding to any preset fault category;

[0096] An operation data sample is determined based on the normal operation data sample and the fault operation data sample.

[0097] In the embodiments of the present application, the first operation data sample can be understood as the original data collected directly from the compressor system. Exemplarily, the first operation data sample includes but is not limited to temperature, pressure, compressor speed, electronic expansion valve opening, condenser temperature, and any vehicle operating condition information that can affect the performance of the compressor. The first operation data sample is a set of data points recorded continuously or intermittently within a preset time period, without any processing or conversion.

[0098] The feature data sample can be understood as a data set obtained by feature extraction processing on the first operation data sample. Feature extraction is a process of screening or calculating more meaningful feature parameters from original data. For example, average temperature, pressure fluctuation amplitude, speed change rate, etc. can be calculated, and the above feature data sample can more clearly reflect the change trend of the system operation state and the signal of potential failure.

[0099] The second operation data sample can be understood as a data sample after feature extraction and dimension reduction processing. Dimension reduction processing is to remove data redundancy and reduce computational complexity, so that the model is easier to learn and predict. Dimension reduction can be achieved by principal component analysis, t-distributed neighborhood embedding, etc., to ensure that while reducing the dimension of the data, the information that best distinguishes normal and abnormal operation states is retained.

[0100] The normal label can be understood as an identification or label attached to the normal operation data sample, indicating that the data sample represents the operation state of the system under the condition of no failure and normal work.

[0101] The fault label can be understood as an identification or label corresponding to a preset fault category and attached to the fault operation data sample, indicating that the data sample represents the operation state under a specific fault category.

[0102] Obtaining the first operation data sample of the compressor system within a preset time period can be understood as collecting the original operation data within the preset time period from the real-time monitoring device of the compressor system, including but not limited to the discharge temperature, suction temperature, discharge pressure, suction pressure, condenser temperature, electronic expansion valve opening, compressor speed, and ambient temperature of the compressor.

[0103] Feature extraction on the first operation data sample to obtain the feature data sample can be understood as screening feature parameters from the first operation data sample that can effectively describe the system state and distinguish different fault modes to obtain the feature data sample. For example, the difference between the discharge temperature and the suction temperature, the rate of pressure change, the heat dissipation efficiency of the condenser, etc. are not limited here.

[0104] The dimensionality reduction processing of the feature data sample to obtain the second running data sample can be understood as that, by dimensionality reduction processing of the feature data sample, the high-dimensional feature data sample can be converted into the low-dimensional second running data sample, which is easier for model processing and learning.

[0105] The dividing of the second running data sample to obtain the normal running data sample and the fault running data sample can be understood as that, according to the label carried by the data sample, the data sample is divided into the normal running data sample and the fault running data sample. The normal running data sample represents the running state of the system under the fault-free condition, and the fault running data sample reflects the running state of the system when various preset fault categories occur.

[0106] The determining of the running data sample based on the normal running data sample and the fault running data sample can be understood as that, the divided normal running data sample and the fault running data sample constitute the running data sample set finally used for model training. The sample set contains the running features of the system under the normal and fault conditions, and is the basis for model learning and prediction.

[0107] In the embodiment of the application, through the above steps, from the data collection, through the feature extraction, the dimensionality reduction processing, to the data classification and the final determination, a data preprocessing process from the original data to the data that can be used for machine learning model training is constituted, so that the model can learn as much useful information as possible from the data, while reducing unnecessary calculation burden, improving the training efficiency and prediction accuracy of the model.

[0108] Further, in step S10, the current running data of the compressor system in the vehicle is obtained, including the following steps:

[0109] In step S101, perception data is obtained based on the vehicle-mounted sensor of the vehicle, wherein the perception data includes at least one kind of perception data collected by a sensor;

[0110] In step S102, the perception data is preprocessed to obtain initial current running data;

[0111] In step S103, data fusion is performed on the initial current running data to obtain the current running data.

[0112] In the embodiments of the present application, obtaining perception data based on vehicle-mounted sensors of a vehicle can be understood as using various sensors equipped on the vehicle (such as temperature sensors, pressure sensors, accelerometers, GPS, etc.) to collect information related to the state of the vehicle and the environment. The above-mentioned sensors can monitor a plurality of key parameters of the vehicle in real time, such as engine temperature, tire pressure, vehicle position, driving speed, acceleration, etc., as well as external environment such as weather conditions, road conditions, etc. The perception data directly reflects the state of the vehicle at a specific moment or time period, and is the basis for fault diagnosis, performance analysis or automatic driving decision-making.

[0113] Preprocessing the perception data to obtain initial current running data can be understood as cleaning and preparing the data to make it more suitable for subsequent analysis and modeling. Preprocessing can include data cleaning (removing erroneous or incomplete data), data transformation (such as converting temperature units from Fahrenheit to Celsius), data standardization or normalization (ensuring that data is compared on the same scale), missing value handling (filling or deleting missing data), and outlier detection and handling. The initial current running data obtained after preprocessing is a cleaned and uniformly formatted data set that can more accurately reflect the actual running state of the vehicle.

[0114] Fusing the initial current running data to obtain current running data can be understood as integrating the initial current running data from multiple sensors together to form a more comprehensive and consistent data view. Data fusion can eliminate redundancy, solve inconsistency problems, reduce noise, and possibly synthesize higher-level features through algorithms, such as combining position data and acceleration data to estimate the driving style of the vehicle (such as smooth driving, aggressive driving). The current running data is a fused data set that contains richer information and more accurate state descriptions, providing a solid data foundation for subsequent fault diagnosis, vehicle state monitoring or driving behavior analysis.

[0115] In the embodiments of the present application, through the above steps, from the original perception data to the preprocessed initial current running data, and then to the fused current running data, the data quality input into the vehicle diagnostic system or intelligent control algorithm is ensured, thereby improving the reliability, accuracy and reaction speed of the prediction model.

[0116] As a specific embodiment, the present application includes a data acquisition module, a model construction module, a model training module, and a fault diagnosis module.

[0117] The data acquisition module is used to set a plurality of sensors in the automobile compressor system, including temperature sensors, pressure sensors, expansion valve opening degree sensors, compressor speed sensors, etc., to collect data such as the exhaust temperature, suction temperature, exhaust pressure, suction pressure, condenser temperature, expansion valve opening degree, compressor speed, and ambient temperature of the compressor in real time. At the same time, faults are set respectively, including excessive refrigerant charge, insufficient refrigerant charge, condenser blockage, cooling fan failure, compressor wear, compressor oil return failure, and operation under abnormal environmental conditions (for example, the ambient temperature is-7℃, 30℃, and the vehicle speed is 50-80km / h). The collected data is preprocessed, including data cleaning, normalization, etc., and converted into a format suitable for processing by the CNN-LSTM (Convolutional Neural Network-Long Short-Term Memory) neural network model.

[0118] The model construction module is used to construct a CNN-LSTM neural network model, which includes an input layer, a training layer, and an output layer. The input layer is used to complete the data sample set through data preprocessing, normalization, and feature parameter extraction of the original operation data of the heat pump system, and divide the training set and the test set in proportion, and then divide and complete the label making through the sliding window, construct the data set that meets the model training, and finally input into the training layer of the model; the training layer is used to find the mapping relationship between the fault feature parameters and the label values after the model receives the input data, the convolutional layer of CNN performs preliminary feature extraction on the time series data, then the pooling layer further processes the extracted features to realize data dimension reduction, simplifies the calculation and reduces the number of parameters, while retaining important feature information, so as to find the mapping relationship between the fault feature parameters and the label values. After the pooling layer of CNN, a bidirectional LSTM network is connected, which fits the feature information in time series through the internal gate structure, thereby establishing the relationship model between the input data and the predicted label value, and finally the fully connected layer outputs the predicted data of the model to complete the prediction of the target problem. The output layer is used to output the calculation value after the data set is calculated and predicted by the CNN-LSTM neural network model, and then the original format information is restored through the inverse normalization processing, and then it is judged whether a fault occurs. At the same time, program codes for evaluating the effect of the model are added in the output layer, and the results of the evaluation indexes are calculated and output, which are used as the basis for model effect evaluation and optimization improvement. The network parameter design of the CNN-LSTM neural network model is shown in Table 1:

[0119] Table 1

[0120]

[0121]

[0122] In addition to the CNN-LSTM neural network model, other neural network structures with time series processing capabilities, such as the Gated Recurrent Unit neural network model, can be used to replace the CNN-LSTM neural network. The Gated Recurrent Unit neural network model structure is relatively simple and has higher computational efficiency, and in some scenarios it can also effectively identify the causes of the compressor discharge temperature being too high. The CNN-LSTM neural network model can also be combined with other machine learning models (such as support vector machines, random forests, etc.) to take advantage of the strengths of different models and improve the accuracy and robustness of fault diagnosis. For example, first use the CNN-LSTM neural network model to perform preliminary feature extraction on the time series data, and then input the extracted features into the support vector machine for classification and judgment.

[0123] At the same time, according to the actual needs and system characteristics, adjust the types and quantities of data collection parameters. For example, in some cases, the number of vibration sensors collecting compressor vibration data can be increased, or some parameters that have less impact on fault diagnosis can be reduced to optimize the data collection and processing process and improve the diagnosis efficiency.

[0124] The model training module is used to collect a large amount of compressor operation data, including normal operation data and data under various fault conditions, to form a training data set. The CNN-LSTM neural network model is trained using the training data set, and the backpropagation algorithm and optimizer (such as the Adam optimizer) are used to adjust the network parameters to minimize the error between the predicted results and the actual fault causes, so that the model can accurately identify the feature patterns corresponding to different fault causes.

[0125] The fault diagnosis module is used to input the real-time collected and preprocessed data into the trained CNN-LSTM neural network model, and the model outputs the probability values of each fault cause. By setting a threshold (such as a probability value greater than 0.6 to determine that the corresponding fault cause has occurred), the specific cause of the compressor discharge temperature being too high is determined.

[0126] The present application provides accurate and effective input data for the CNN-LSTM neural network model by setting multiple sensors to collect multi-dimensional data of the compressor operation and performing preprocessing, ensuring the accuracy of the diagnosis. The ability of the CNN-LSTM neural network to process time series data is used to comprehensively analyze various parameters during the operation of the automobile compressor, enabling the identification of the causes of the compressor discharge temperature being too high, thereby distinguishing from traditional single parameter or fixed threshold judgment methods. In addition, by explicitly dividing the causes of the compressor discharge temperature being too high into multiple types such as refrigerant problems, heat dissipation problems, and compressor itself problems, and outputting the probability values of each cause through the CNN-LSTM neural network model, combined with the threshold for fault cause judgment, the technical effect of accurately determining the real cause of the compressor discharge temperature being too high is achieved.

[0127] It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions, and provide corresponding operation portal for user to choose authorization or refusal.

[0128] According to an embodiment of the present application, an embodiment of a vehicle fault determination device is provided, and it should be noted that the device can be used to execute the vehicle fault determination method described above.

[0129] According to another aspect of the embodiment of the present application, a vehicle fault determination device is also provided, Figure 2 is a module schematic diagram of an optional vehicle fault determination device according to an embodiment of the present application, as Figure 2 shown, the vehicle fault determination device 200 comprises: an acquisition module 201, the acquisition module is used for acquiring current running data of a compressor system in a vehicle, wherein the current running data is used for recording running attributes of any component in the compressor system; an analysis module 202, the analysis module is used for performing fault prediction analysis on the current running data to obtain a fault prediction result, wherein the fault prediction result is used for indicating fault occurrence probabilities of a plurality of preset fault categories in the current running data; a determination module 203, the determination module is used for determining a first maintenance strategy based on any preset fault category in response to that the fault occurrence probability corresponding to the any preset fault category is greater than a preset probability threshold, wherein the first maintenance strategy is used for repairing a fault in the compressor system corresponding to the any preset fault category; and a maintenance module 204, the maintenance module is used for maintaining the compressor system based on at least one first maintenance strategy.

[0130] Further, the maintenance module 204 is also used for determining an execution priority of any first maintenance strategy based on a preset execution rule; determining a target maintenance strategy based on the first maintenance strategy and the execution priority, wherein the target maintenance strategy is used for executing any first maintenance strategy according to the execution priority; and maintaining the compressor system based on the target maintenance strategy.

[0131] Further, the analysis module 202 is further configured to perform fault prediction analysis on the current operation data based on a target diagnosis model to obtain a fault prediction result, wherein the target diagnosis model is trained based on operation data samples, the operation data samples include normal operation data samples and fault operation data samples, the fault operation data samples include a plurality of preset fault categories, and the plurality of preset fault categories include refrigerant charge abnormality, condenser blockage, cooling fan failure, compressor wear, compressor failure, compressor oil return failure, expansion valve failure, temperature sensor abnormality, and vehicle working condition abnormality.

[0132] Further, before performing the fault prediction analysis on the current operation data based on the target diagnosis model, the vehicle fault determination apparatus further includes a training module configured to: obtain operation data samples of the compressor system in a preset time period; train an initial diagnosis model based on the operation data samples to obtain fault prediction probabilities of the plurality of preset fault categories in the operation data samples; and adjust training parameters of the initial diagnosis model based on real fault probabilities corresponding to the operation data samples and the fault prediction probabilities to obtain the target diagnosis model.

[0133] Further, the training module is further configured to: obtain first operation data samples of the compressor system in the preset time period; perform feature extraction on the first operation data samples to obtain feature data samples; perform dimension reduction processing on the feature data samples to obtain second operation data samples; divide the second operation data samples to obtain normal operation data samples and fault operation data samples, wherein the normal operation data samples carry normal labels, and the fault operation data samples carry fault labels corresponding to any preset fault category; and determine the operation data samples based on the normal operation data samples and the fault operation data samples.

[0134] Further, the obtaining module 201 is further configured to: obtain perception data based on vehicle-mounted sensors of the vehicle, wherein the perception data includes perception data collected by at least one sensor; perform preprocessing on the perception data to obtain initial current operation data; and perform data fusion on the initial current operation data to obtain the current operation data.

[0135] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, and the storage medium stores a computer program, wherein the computer program is configured to execute the vehicle fault determination method in the various embodiments of the present application when running on a computer or a processor.

[0136] According to another aspect of the embodiments of the present application, an electronic device is also provided, which includes a memory and a processor, the memory stores a computer program, and the processor is configured to execute the computer program to perform the vehicle fault determination method in the various embodiments of the present application.

[0137] According to another aspect of the embodiments of the present application, a vehicle is also provided, comprising a memory and a processor, the memory storing a computer program, the computer program implementing the vehicle fault determination method in the various embodiments of the present application when executed by the processor.

[0138] According to another aspect of the embodiments of the present application, a computer program product is also provided, comprising a computer program, the computer program implementing the vehicle fault determination method in the various embodiments of the present application when executed by a processor.

[0139] In the above-described embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0140] In several embodiments provided in the present application, it should be understood that the disclosed technical contents can be implemented by other manners. Among them, the apparatus embodiment described above is only schematic, for example, the division of units can be a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the units or modules shown or discussed can be indirect coupling or communication connection through some interfaces, and can be electrical or other forms.

[0141] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed to multiple units. Part or all of the units can be selected according to actual needs to achieve the purpose of the present embodiment scheme.

[0142] In addition, each functional unit in the various embodiments of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware, or in the form of software functional unit.

[0143] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application, essentially or in other words, the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server or a network device, etc.) execute all or part of the steps of the methods described in various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0144] The above is only the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A vehicle fault determination method, characterized in that: include: Acquiring current operating data of a compressor system in a vehicle, wherein the current operating data is used to record operating properties of any component in the compressor system; Performing a fault prediction analysis on the current operating data to obtain a fault prediction result, wherein the fault prediction result is used to indicate the probability of occurrence of multiple preset fault categories in the current operating data; In response to the probability of occurrence of the fault corresponding to any preset fault category being greater than a preset probability threshold, determining a first maintenance strategy based on the any preset fault category, wherein the first maintenance strategy is used to repair the fault corresponding to the any preset fault category in the compressor system; The compressor system is maintained based on at least one of the first maintenance strategies.

2. The method according to claim 1, characterized in that The maintaining the compressor system based on at least one of the first maintenance strategies includes: Determining an execution priority of any one of the first maintenance strategies based on preset execution rules; determining a target maintenance strategy based on the first maintenance strategy and the execution priority, wherein the target maintenance strategy is used to execute any one of the first maintenance strategies according to the execution priority; The compressor system is maintained based on the target maintenance strategy.

3. The method according to claim 1 or 2, characterized in that The performing fault prediction analysis on the current operating data to obtain a fault prediction result includes: A fault prediction analysis is performed on the current operating data based on a target diagnostic model to obtain the fault prediction result, wherein the target diagnostic model is trained based on operating data samples, the operating data samples include normal operating data samples and faulty operating data samples, and the faulty operating data samples include the multiple preset fault categories, and the multiple preset fault categories include abnormal refrigerant charge, condenser blockage, cooling fan failure, compressor wear, compressor failure, compressor oil return failure, expansion valve failure, temperature sensor abnormality, and abnormal vehicle operating condition.

4. The method according to any one of claims 1 to 3, characterized in that Before performing fault prediction analysis on the current operating data based on the target diagnosis model, the method further includes: Obtaining operation data samples of the compressor system within a preset time period; Training an initial diagnostic model based on the operating data samples to obtain fault prediction probabilities of multiple preset fault categories in the operating data samples; The training parameters of the initial diagnosis model are adjusted based on the actual fault probability and the fault prediction probability corresponding to the operation data sample to obtain the target diagnosis model.

5. The method according to claim 4, characterized in that The obtaining of the operating data sample of the compressor system within a preset time period includes: Acquiring a first operating data sample of the compressor system within the preset time period; performing feature extraction on the first operation data sample to obtain a feature data sample; Performing dimensionality reduction processing on the feature data sample to obtain a second operation data sample; Dividing the second operation data sample to obtain a normal operation data sample and a fault operation data sample, wherein the normal operation data sample carries a normal label, and the fault operation data sample carries a fault label corresponding to any of the preset fault categories; The operation data sample is determined based on the normal operation data sample and the fault operation data sample.

6. The method according to any one of claims 1 to 3, characterized in that The obtaining of current operating data of the compressor system in the vehicle includes: Acquiring perception data based on an onboard sensor of the vehicle, wherein the perception data includes perception data collected by at least one sensor; Preprocessing the sensing data to obtain initial current operation data; Perform data fusion on the initial current operation data to obtain the current operation data.

7. A vehicle fault determination device, characterized in that: The device comprises: an acquisition module, the acquisition module being configured to acquire current operating data of a compressor system in a vehicle, wherein the current operating data is used to record operating properties of any component in the compressor system; an analysis module, the analysis module being configured to perform a fault prediction analysis on the current operating data to obtain a fault prediction result, wherein the fault prediction result is configured to represent the probability of occurrence of a plurality of preset fault categories in the current operating data; a determination module, the determination module being configured to determine, in response to a probability of occurrence of the fault corresponding to any preset fault category being greater than a preset probability threshold, a first maintenance strategy based on the any preset fault category, wherein the first maintenance strategy is configured to repair the fault corresponding to the any preset fault category in the compressor system; A maintenance module is configured to perform maintenance on the compressor system based on at least one of the first maintenance strategies.

8. A computer-readable storage medium, characterized in that The storage medium stores a computer program, wherein the computer program is configured to execute the vehicle fault determination method according to any one of claims 1 to 6 when running on a computer or a processor.

9. An electronic device comprising a memory and a processor, characterized in that: The memory stores a computer program, and the processor is configured to run the computer program to execute the vehicle fault determination method according to any one of claims 1 to 6.

10. A vehicle comprising a memory and a processor, characterized in that: The memory stores a computer program, which, when executed by the processor, implements the vehicle fault determination method according to any one of claims 1 to 6.

Images