Multi-module collaborative fault detection and early warning method for hydrogen-electric vehicles

Abstract

The present invention discloses a multi-module coordinated fault detection and early warning method for hydrogen-electric electric vehicles, which relates to the technical field related to electric vehicle fault detection. The method includes: determining multiple functional modules of hydrogen-electric electric vehicles; collecting multiple functional modules through an on-board sensor network to obtain multiple sensor data sets; performing pattern recognition on multiple sensor data sets based on a pattern classification algorithm, and outputting a real-time matching working mode; constructing a module coordination relationship database; calling the module coordination relationship database to identify the module coordination relationship diagram corresponding to the real-time matching working mode; performing coordinated fault detection on multiple sensor data sets according to the module coordination relationship diagram, and outputting a fault early warning signal corresponding to the real-time matching working mode. The method solves the technical problem that the comprehensive fault detection means lacking the coordinated relationship of multiple functional modules in the prior art, which leads to untimely and incomplete fault identification of electric vehicles, and achieves the technical effect of improving the comprehensiveness and accuracy of fault identification.

Description

Technical Field

[0001] The present application relates to the technical field related to electric vehicle fault detection, and in particular to a multi-module collaborative fault detection and early warning method for hydrogen-electric electric vehicles. Background Art

[0002] With the rapid development of hydrogen fuel cell and electric vehicle technologies, hydrogen electric vehicles have been increasingly widely used in transportation due to their high efficiency and environmental protection. However, hydrogen electric vehicles contain multiple complex functional modules, such as power system, energy storage system, fuel cell system, intelligent control system, etc. These functional modules are tightly integrated and work together through the on-board sensor network. In order to ensure the safety and reliability of vehicle operation, how to collaboratively detect vehicle faults in real time has become a key issue. Traditional methods mainly monitor a single functional module independently, usually based on the collection of module operation data based on the on-board sensor network. However, due to the wide variety of data, the accuracy of pattern classification and fault identification is low, and it is impossible to fully evaluate the collaborative relationship between modules, thus affecting the working mode of the whole vehicle. For example, the collaborative efficiency of the fuel cell system and the energy storage system determines the vehicle energy management, and it is difficult to cope with the complex working conditions of high integration between modules, making it impossible to perform comprehensive and accurate fault detection.

[0003] At the current stage, relevant technologies lack comprehensive fault detection methods that coordinate multiple functional modules, resulting in technical problems such as untimely and incomplete identification of electric vehicle faults. Summary of the invention

[0004] The present application solves the technical problem of the lack of comprehensive fault detection means with collaborative relationships among multiple functional modules in the prior art, which leads to untimely and incomplete fault identification of electric vehicles, by providing a multi-module collaborative fault detection and early warning method for hydrogen-electric vehicles, thereby achieving the technical effect of improving the comprehensiveness and accuracy of fault identification.

[0005] The present application provides a multi-module collaborative fault detection and early warning method for a hydrogen-electric vehicle, comprising: determining multiple functional modules of a hydrogen-electric vehicle, wherein the multiple functional modules are connected to an on-board sensor network; collecting data from the multiple functional modules through the on-board sensor network to obtain multiple sensor data sets; performing pattern recognition on the multiple sensor data sets based on a pattern classification algorithm, and outputting a real-time matching working mode; constructing a module coordination relationship database, wherein the module coordination relationship database stores the coordination relationship of the multiple functional modules under each working mode; calling the module coordination relationship database to identify a module coordination relationship diagram corresponding to the real-time matching working mode; performing collaborative fault detection on the multiple sensor data sets according to the module coordination relationship diagram, and outputting a fault early warning signal corresponding to the real-time matching working mode.

[0006] In a possible implementation, the multi-module collaborative fault detection and early warning method for the hydrogen-electric vehicle also performs the following processing: extracting features from the multiple sensor data sets and outputting sensor feature vectors; inputting the sensor feature vectors into a trained random forest classification model, performing pattern recognition according to the random forest classification model, and obtaining a real-time matching working mode output by the random forest classification model; training the random forest classification model includes training multiple decision trees according to training data until convergence, wherein the training data includes obtaining historical sensor sample data sets and label data that identifies the mode type of the hydrogen-electric vehicle.

[0007] In a possible implementation, the multi-module collaborative fault detection and early warning method for the hydrogen-electric vehicle also performs the following processing: using a sliding window to analyze the multiple groups of sensor data sets to obtain a mode duration; obtaining a stability index based on the difference between the mode duration and a preset duration threshold; if the stability index is greater than or equal to the preset stability index, performing pattern recognition on the multiple groups of sensor data sets based on a pattern classification algorithm.

[0008] In a possible implementation, the multi-module collaborative fault detection and early warning method for the hydrogen-electric vehicle also performs the following processing: determining a first switching working mode based on the multiple mode switching probabilities, wherein the first switching working mode is the working mode with the highest probability among the multiple mode switching probabilities; calling the module coordination relationship database to identify the module coordination relationship diagram corresponding to the first switching working mode; and performing collaborative fault detection on multiple sets of continuously monitored sensor data sets according to the module coordination relationship diagram.

[0009] In a possible implementation, the multi-module collaborative fault detection and early warning method for the hydrogen-electric vehicle also performs the following processing: identifying the health sensor data sample corresponding to the module coordination relationship diagram; comparing the multiple sensor data sets according to the health sensor data sample to determine the first fault function module; obtaining the first fault indicator and multiple collaborative fault indicators corresponding to the first fault function module; performing weighted summation based on the first fault indicator and the multiple collaborative fault indicators to output the fault level, and outputting a fault early warning signal based on the fault level conversion.

[0010] In a possible implementation, the multi-module collaborative fault detection and early warning method for the hydrogen-electric vehicle also performs the following processing: combining the module coordination relationship diagram, and outputting a fault propagation probability matrix according to the connection relationship between the first fault function module and other function modules; and calculating multiple collaborative fault indicators according to the fault propagation probability matrix.

[0011] In a possible implementation, the multi-module collaborative fault detection and early warning method for the hydrogen-electric vehicle also performs the following processing: according to the module coordination relationship database, obtaining the mode switching combination of the real-time matching working mode; according to the fault early warning signal, identifying multiple switching risks corresponding to the mode switching combination; screening the identification mode switching combination greater than the preset switching risk from the multiple switching risks; when the received mode switching request belongs to the identification mode switching combination, generating a switching early warning signal.

[0012] In a possible implementation, the multi-module collaborative fault detection and early warning method of the hydrogen-electric vehicle also performs the following processing: based on the switching early warning signal, detecting the repair index of the real-time matching working mode; if the repair index does not meet the preset repair index, performing mode switching optimization in the module coordination relationship database with the preset switching risk, and outputting the optimal solution for the switching mode.

[0013] Through the multi-module collaborative fault detection and early warning method for hydrogen-electric electric vehicles proposed in this application, multiple functional modules of hydrogen-electric electric vehicles are determined; multiple functional modules are collected through the on-board sensor network to obtain multiple sensor data sets; multiple sensor data sets are pattern recognized based on the pattern classification algorithm, and real-time matching working modes are output; a module coordination relationship database is constructed; the module coordination relationship database is called to identify the module coordination relationship diagram corresponding to the real-time matching working mode; collaborative fault detection is performed on multiple sensor data sets according to the module coordination relationship diagram, and fault early warning signals corresponding to the real-time matching working mode are output. This solves the technical problem of the lack of comprehensive fault detection means of multiple functional module coordination relationships in the prior art, which leads to untimely and incomplete fault identification of electric vehicles, and achieves the technical effect of improving the comprehensiveness and accuracy of fault identification. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0015] Figure 1 A schematic flow chart of a multi-module coordinated fault detection and early warning method for a hydrogen-electric vehicle provided in an embodiment of the present application; Figure 2 A schematic diagram of a flow chart for outputting a real-time matching working mode in a multi-module collaborative fault detection and early warning method for a hydrogen-electric vehicle provided in an embodiment of the present application. DETAILED DESCRIPTION

[0016] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0017] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0018] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of the objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, product, or server comprising a series of steps is not necessarily limited to those steps clearly listed, but may include other steps that are not clearly listed or inherent to these processes, methods, products, or devices, and unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0019] The present application embodiment provides a multi-module coordinated fault detection and early warning method for hydrogen electric vehicles, such as Figure 1 As shown, the method includes: Step S100, determining a plurality of functional modules of a hydrogen-electric vehicle, wherein the plurality of functional modules are connected to an on-board sensor network.

[0020] Preferably, multiple functional modules of the hydrogen-electric electric vehicle are determined, that is, multiple system modules with specific functions in the hydrogen-electric electric vehicle are obtained, and data exchange and communication are performed through the vehicle-mounted sensor network. Multiple functional modules are connected to the vehicle-mounted sensor network through various sensors, data buses and communication interfaces to form an integrated and interconnected network system, so that each module can collect sensor data in real time and transmit it to the vehicle-mounted control system or other modules. For example, through the vehicle-mounted sensor network, the fuel cell system module can transmit its status information to the control system, and the control system can adjust the operating mode of the motor and the energy storage system, so as to achieve collaborative work. The functional modules may include but are not limited to the power system module, including the motor, the control unit etc., which are related to the vehicle's driving ability and sports performance; the fuel cell system module is responsible for the storage and conversion of hydrogen into electrical energy, and supplies it to the electric motor and other modules; the energy storage system module, such as the battery pack, stores the electrical energy obtained from the fuel cell system or the energy recovered through regenerative braking and other methods; the thermal management system module regulates the temperature of the battery pack, fuel cell and other modules to ensure that the system operates at the optimal operating temperature; the on-board control system module is responsible for the overall control, monitoring and data processing of the vehicle, which may include the power control unit (ECU), vehicle status monitoring system, etc.; the safety monitoring system module, including sensors and monitoring systems, is responsible for monitoring the safety of the vehicle, such as hydrogen leak detection and over-temperature alarm.

[0021] Step S200: collecting data from the multiple functional modules through the vehicle-mounted sensor network to obtain multiple sets of sensor data sets.

[0022] Preferably, various types of sensor data are collected and acquired from various functional modules of hydrogen-electric electric vehicles through the on-board sensor network to reflect the working status, performance indicators and possible fault characteristics of each module. Specifically, different types of sensors are installed on each functional module to monitor the operating status of each module, which may include temperature sensors (for monitoring the temperature of batteries, fuel cells and power systems), current and voltage sensors (for monitoring battery voltage, current and power output), hydrogen leakage sensors (for detecting whether there is leakage in the hydrogen system), pressure sensors (for monitoring the pressure of the gas system and fuel cell system), vibration sensors (for detecting abnormal vibrations in the mechanical system) and speed sensors (for monitoring the speed of the motor and wheels), etc. The on-board sensor The sensor network collects data from various functional modules in real time through sensors, generating multiple sets of sensor data sets, which reflect the operating status, performance changes and potential fault signs of each module in real time, and may include data under different time periods and different working conditions, such as power system data sets (such as motor output power, torque changes), energy storage system data sets (such as battery charging and discharging status, battery health status), fuel cell system data sets (such as hydrogen pressure, fuel cell current output), safety system data sets (such as temperature, hydrogen concentration, leakage alarm), etc. Through pattern recognition, the operating status and mutual relationship of different modules are analyzed, so as to fully understand the real-time operating status and synergistic efficiency of multiple functional modules of hydrogen-electric vehicles, and provide more accurate fault warnings for vehicles.

[0023] Step S300, performing pattern recognition on the plurality of sensor data sets based on a pattern classification algorithm, and outputting a real-time matching working mode.

[0024] Preferably, a pattern classification algorithm is used to analyze and process the sensor data sets collected from multiple functional modules, so as to identify the current working mode of the hydrogen electric vehicle and output a real-time working mode matching it. Specifically, multiple sensor data sets come from different functional modules (such as power system, fuel cell system, energy storage system, etc.), and there may be differences in timing, data type and feature dimension. The pattern classification algorithm analyzes and processes multiple sets of sensor data sets to extract effective feature information. For example, considering that the working environment of electric vehicles is dynamically changing, the pattern classification algorithm processes data with time series characteristics and extracts the changes in the working state of the modules at different time points; by analyzing the data of each sensor, the algorithm extracts the key features that affect the working mode (such as temperature, voltage, pressure, etc.), and fuses them to generate a feature vector suitable for classification; then, according to the input sensor data set, the current system The state is matched to a predefined working mode. The working mode is the possible operating state of the vehicle under different working conditions, which may include but is not limited to a normal working mode, in which all functional modules are in normal state and the data indicators are within the preset range; a high-load working mode, such as the motor power output reaches the maximum and the fuel cell system works in a high-pressure state; a fault warning mode, in which a functional module has an abnormality, resulting in a decrease in the performance of the entire vehicle, such as the battery temperature is too high or the hydrogen pressure of the fuel cell is abnormal; an energy recovery mode, when the electric vehicle is in a braking state, the energy storage system enters the energy recovery mode; through real-time processing of sensor data, the pattern classification algorithm can accurately determine the current working mode of the vehicle, and match it with the pre-set working mode, and output the working mode that matches the current sensor data set, that is, the current working state of the vehicle. For example, if the current motor and fuel cell are identified to be working in a high-load state, the algorithm will output a high-load working mode.

[0025] Preferably, the pattern classification algorithm is a technique in machine learning or data mining, the purpose of which is to identify the pattern or category represented by the data based on the characteristics of the input data set. It may include supervised learning algorithms, such as support vector machines (SVM), decision trees, random forests, neural networks, etc., which identify different working modes by training models. It usually requires labeled data, that is, the sensor data corresponding to known faults and normal working modes are used as training sets to train a classifier; unsupervised learning algorithms, such as clustering algorithms (such as K-means, DBSCAN, etc.), automatically discover potential patterns in the data through clustering analysis of sensor data, and are suitable for situations where data does not need to be labeled in advance; deep learning methods, such as convolutional neural networks (CNN) and recurrent neural networks (RNN), etc., these methods can process high-dimensional data and automatically extract features from it, and are particularly suitable for processing time series characteristics and nonlinear relationships in sensor data.

[0026] Further, such as Figure 2 As shown, step S300 also includes step S310, performing feature extraction on the multiple groups of sensor data sets and outputting sensor feature vectors; step S320, inputting the sensor feature vectors into a trained random forest classification model, performing pattern recognition according to the random forest classification model, and obtaining a real-time matching working mode output by the random forest classification model; step S330, training the random forest classification model includes training multiple decision trees according to training data until convergence, wherein the training data includes obtaining historical sensor sample data sets and label data identifying the mode type of hydrogen electric vehicles.

[0027] Preferably, feature extraction is performed on multiple groups of sensor data sets to determine multiple representative features that can describe the current vehicle state, namely, the state features of each functional module of the electric vehicle, and then a sensor feature vector is generated, which is a condensed representation of multiple sensor data and a data format used to input into a machine learning model. Training data is obtained, including a historical sensor sample data set and label data that identifies the mode type of hydrogen-electric electric vehicles, wherein the historical sensor sample data set is a historical sensor data set collected through an on-board sensor network, which contains multiple groups of sensor data collected in different time periods and under different working conditions, and the label data records the working mode label corresponding to each group of sensor data of the hydrogen-electric electric vehicle mode type, and then a random forest classification model is trained based on the training data. Specifically, during the training process, the random forest model constructs multiple decision trees, and each decision tree learns how to make decisions based on the input features by recursive splitting based on the historical sensor data and label data. Classification, the basis for splitting a decision tree is usually to select the features that can best distinguish different categories (for example, temperature changes, power output, vibration frequency, etc.). As the training progresses, each tree will gradually improve its classification ability until certain convergence conditions are met (such as tree depth limit, maximum number of splits, etc.), and finally generate a complete decision tree. When the tree is built, the random forest will determine the final classification result through the votes of all trees, and can accurately predict different working modes; finally, the sensor feature vector is input into the trained random forest classification model, and classified through the decision tree of the random forest to identify the real-time matching working mode. Specifically, the input sensor feature vector represents the current state of the vehicle. The random forest classification model will determine the current working mode of the vehicle based on these features (such as normal working mode, high load mode, fault warning mode, etc.), and the output result is the real-time matching working mode predicted by the model.

[0028] Furthermore, step S300 includes step A, analyzing the multiple groups of sensor data sets using a sliding window to obtain a pattern duration; step B, obtaining a stability index based on a difference between the pattern duration and a preset duration threshold; and step C, performing pattern recognition on the multiple groups of sensor data sets based on a pattern classification algorithm if the stability index is greater than or equal to a preset stability index.

[0029] Preferably, a sliding window is a data processing method for performing segmented analysis on time series data. The window moves on the data sequence, covering a certain number of continuous data points each time. The size of the sliding window (i.e., the time span) is usually determined by preset parameters. Specifically, a sliding window is used to divide multiple sets of sensor data (such as temperature, voltage, pressure, etc.) into several small segments according to the time series. The characteristics of the data are analyzed in each window to determine whether the working state of the vehicle in the current window belongs to a certain mode (such as normal mode, high load mode, etc.), thereby analyzing and obtaining the mode duration, that is, the continuous duration of a certain working mode in time; and then calculating and obtaining the stability index according to the difference between the mode duration and the preset duration threshold, wherein the preset The duration threshold defines the shortest time a certain mode needs to last. The stability index measures the relationship between the actual duration of a certain mode and the preset threshold. For example, if the stability index ≥ 0, it means that the duration of the mode has reached or exceeded the preset threshold, and the current mode can be considered stable. If the stability index ≤ 0, it means that the duration of the mode is insufficient, which may be an instantaneous change or anomaly, and pattern recognition is not performed for the time being. Finally, based on the stability index, it is decided whether to perform pattern recognition. Only when the stability index ≥ the preset stability index (such as 0 or a positive value), the current mode is considered worthy of further pattern recognition. Finally, pattern recognition is performed to determine the specific working mode of the vehicle, which serves as the basis for fault detection and early warning.

[0030] Furthermore, step C also includes step C1, if the stability index is less than the preset stability index, performing mode switching prediction based on the multiple groups of sensor data sets, and outputting multiple mode switching probabilities; step C2, determining a first switching working mode based on the multiple mode switching probabilities, wherein the first switching working mode is the working mode with the highest probability among the multiple mode switching probabilities; step C3, calling the module coordination relationship database to identify the module coordination relationship diagram corresponding to the first switching working mode; step C4, performing collaborative fault detection on the multiple groups of sensor data sets that are continuously monitored according to the module coordination relationship diagram.

[0031] Preferably, when the stability index is less than a preset threshold, it indicates that the duration of the current mode is insufficient to consider the system stable, which means that the working state of the vehicle is in dynamic change, such as switching from "normal mode" to "high load mode" or switching from "high load mode" to "fault warning mode". In an unstable state, by analyzing the dynamic change trend of the sensor data, the next working mode to which the current mode may switch is predicted. Specifically, multiple sets of sensor data sets are used as input data, including time series of parameters such as temperature, voltage, pressure, and vibration. Based on a model trained with historical data (such as a Markov chain, a neural network, a state machine, etc.), the probability of the current state switching to other states is calculated, and the probability of the current mode switching to each possible target mode is output. For example, the probability of switching to "high load mode" is 60%, the probability of switching to "fault warning mode" is 30%, and the probability of switching to "energy saving mode" is 10%.

[0032] Preferably, the one with the highest switching probability is selected from multiple switching working modes as the first switching working mode, that is, the next working mode that is most likely to be entered, and then the module coordination relationship database is called to extract the coordination relationship diagram of each functional module in the mode, wherein the coordination relationship diagram contains the coordination rules of each module in the current mode (such as energy flow, signal interaction, etc.) and the data dependency relationship between modules (such as energy distribution between batteries and fuel cells, temperature regulation relationship between temperature control systems and energy storage systems, etc.). By understanding the relationship between each module, it is possible to determine which modules may be affected by the abnormality, thereby locating the source of the fault; finally, according to the module coordination relationship diagram, collaborative fault detection is performed on multiple sets of sensor data sets that are continuously monitored. Specifically, in the first switching working mode, the module coordination relationship diagram is used to comprehensively analyze the sensor data of multiple functional modules to determine whether there is a fault or abnormality. For example, according to the module coordination rules defined in the coordination relationship diagram, the data of each module is analyzed to determine whether it meets the normal working state. If the abnormality of a module causes the data of other modules to exceed the normal range, it is determined to be a collaborative fault, which enhances the adaptability of the electric vehicle to the dynamic environment and improves the accuracy of fault detection, thereby improving the safety and reliability of vehicle operation.

[0033] Step S400: construct a module coordination relationship database, wherein the module coordination relationship database stores coordination relationships among the plurality of functional modules in each working mode.

[0034] Preferably, a module coordination relationship database is constructed to record the coordinated coordination relationship of multiple functional modules in hydrogen-electric vehicles under different working modes, that is, the coordination relationship of multiple functional modules in each working mode is stored, including the coordination mode and mutual influence of each module under different working conditions. Specifically, the database will store the coordination relationship between each module (such as power system, fuel cell system, energy storage system, etc.) in each working mode. For example, in normal working mode, each module such as power system, fuel cell system, energy storage system may need to maintain balanced operation and cooperate with each other to maintain optimal energy efficiency. For example, the fuel cell outputs electricity to supply the electric motor, and the battery provides additional power support when needed; in high load mode, the power system may To achieve greater power, the fuel cell system and energy storage system need to adjust their output and charging status according to the load conditions. In the fault warning mode, if a module fails, the database will record how other modules respond or adjust in this fault mode, and how to cooperate with the faulty module to ensure the safety of the vehicle. The module coordination relationship may also include complex interactive relationships, such as power sharing (how the power system and the energy storage system work together to provide power, or how to recover energy), temperature control (the fuel cell system and the energy storage system may need to share a temperature control system), and data sharing (modules share data in real time through a sensor network, such as battery voltage, fuel cell output current, power system speed, etc.). Through the module coordination relationship database, the vehicle can quickly query and match the coordination relationship of each module according to the current working mode during real-time operation, further enhancing the synergy of the various functional modules of the electric vehicle. If a module fails, the database can provide the coordination relationship between the module and other modules, thereby helping to determine the scope of the fault so that it can be quickly diagnosed and a warning signal can be issued when a fault occurs.

[0035] Step S500, calling the module coordination relationship database to identify the module coordination relationship diagram corresponding to the real-time matching working mode.

[0036] Preferably, in the process of fault detection of electric vehicles, the constructed module coordination relationship database is used to find and generate the corresponding module coordination relationship diagram according to the real-time identified working mode, so as to show the collaborative working relationship between the functional modules under the current working mode. Specifically, the module coordination relationship diagram is a graphical tool used to show the relationship and interaction mode between the functional modules of hydrogen electric vehicles under a specific working mode. It is usually presented in the form of a graph or a network. The modules are connected together by edges (relationships). The weight and connection mode of the edges represent the collaborative working rules between the modules. The nodes in the module coordination relationship diagram represent the functional modules (such as the power system, the energy storage system, the fuel cell system, etc.), and the edges represent the coordination relationship between these modules. Under different working modes, the coordination relationship between modules may change, that is, the connection mode and status between nodes in the diagram will also change with the change of working mode. Through the sensor network, the vehicle will detect the current working mode (such as normal working mode, high load mode, fault warning mode, etc.) in real time. According to the real-time matching working mode, the specific coordination relationship corresponding to each functional module in the mode is matched from the module coordination relationship database. By calling the real-time matching coordination relationship diagram, the working status and coordination between modules in a specific mode can be more clearly understood, so as to quickly diagnose faults through the coordination relationship diagram; it can also help analyze the synergy between different modules to ensure that the vehicle can operate efficiently and safely in various working modes.

[0037] Step S600: performing collaborative fault detection on the multiple sensor data sets according to the module coordination relationship diagram, and outputting a fault warning signal corresponding to the real-time matching working mode.

[0038] Preferably, based on the inter-module collaborative working mode shown in the module coordination relationship diagram, a comprehensive collaborative fault detection analysis is performed on multiple sensor data sets to discover potential module failures or abnormal behaviors, and a fault warning signal for the current working mode is generated based on the analysis results. Specifically, the sensor data sets (such as temperature, voltage, current, speed, etc.) from multiple modules are correlated and analyzed according to the definition of the module coordination relationship diagram to determine whether the data relationship between the modules conforms to the normal collaborative mode. For example, in high-load mode, the fuel cell and the battery should output higher power at the same time. If the sensor data shows that the fuel cell output is abnormally low and the battery is overloaded, it means that the collaborative cooperation is abnormal. The sensor data of each module is then analyzed separately to detect anomalies (such as excessive temperature, abnormal current fluctuations, etc.). Cross-module analysis is performed to see if there is a causal relationship between the anomalies of the modules. For example, if the fuel cell Insufficient power output, whether it causes the power output of the power system to drop, determine the fault module or fault mode based on the detection results, that is, quickly locate the module where the problem occurs, determine its impact on other modules and match the detected abnormal behavior with the predefined fault mode, and then output the fault warning signal corresponding to the real-time matching working mode, that is, the warning information generated according to the detection results, which is used to remind the driver or maintenance personnel to pay attention to the abnormal state of the current vehicle. The warning signal should indicate which module (such as fuel cell system, energy storage system, etc.) has a problem and describe the specific fault phenomenon, such as "insufficient power output", "overheated temperature", "abnormal pressure", etc., and indicate the working mode when the fault occurs, such as "abnormal fuel cell system under high load mode", which can be output in various forms, such as warning lights or sound alarms on the dashboard, and detailed fault reports displayed on the central control screen. By collaboratively analyzing the data of multiple modules, the module coordination relationship diagram can be used to reduce false positives and false negatives, and improve the accuracy and comprehensiveness of fault detection.

[0039] Furthermore, step S600 also includes step S610, identifying the health sensor data sample corresponding to the module coordination relationship diagram; step S620, comparing the multiple sensor data sets according to the health sensor data sample to determine the first fault function module; step S630, obtaining the first fault indicator and multiple collaborative fault indicators corresponding to the first fault function module; step S640, performing weighted summation based on the first fault indicator and the multiple collaborative fault indicators, outputting the fault level, and converting the output fault warning signal according to the fault level.

[0040] Preferably, the faulty module is determined, the degree of fault is evaluated, and a fault warning signal is generated by comparing the healthy data with the sensor data. Specifically, the healthy sensor data samples corresponding to the module coordination relationship diagram are identified, that is, for each working mode (such as normal mode, fault warning mode, etc.), the collaborative working relationship between the functional modules in these modes and the expected sensor data during normal operation are analyzed through the module coordination relationship diagram, including the sensor data of each functional module under normal vehicle operating conditions, which represents the standard behavior of the system in a healthy state, that is, the normal working data of each module in the absence of faults or abnormalities; the current multiple groups of sensor data sets (real-time data from different functional modules) are compared with the previously identified healthy sensor data samples, for example, to detect whether the sensor data exceeds a predetermined safety threshold, check whether the data trend deviates from the normal mode, or calculate the mean, variance, fluctuation, etc. of the data, to determine whether the current data has an abnormality, and to detect whether the current data matches the normal range in the healthy data sample, thereby determining the first faulty functional module.

[0041] Preferably, a first fault indicator and multiple coordinated fault indicators corresponding to the first fault function module are obtained, wherein the first fault indicator refers to an independent fault feature related to the first fault function module, which may include changes in parameters such as temperature, pressure, voltage, power, etc. of the function module; the coordinated fault indicator refers to a fault signal related to other modules, which may be caused by the synergy problem between the modules, for example, the coordinated fault indicator of the energy storage system and the fuel cell, the energy storage system may be overcharged or over-discharged due to unstable fuel cell output, resulting in performance degradation; the coordinated fault indicator of the temperature control system and the power system, failure of the temperature control system may cause the power system to overheat, thereby affecting the power performance of the vehicle; a weighted sum is performed according to the first fault indicator and the multiple coordinated fault indicators, that is, a certain weight is assigned according to the severity of the impact of each fault indicator on the system fault, and the weighted sum outputs a fault level, indicating the severity of the fault. The higher the fault level, the more serious the fault, and immediate measures may need to be taken; finally, a fault warning signal is output according to the fault level, for example, the fault level is low, the impact is small, and the vehicle can continue to run; the fault level is medium, and it is recommended to monitor or take preventive measures; the fault level is high, an emergency warning is issued, which may cause the system to shut down or require immediate maintenance.

[0042] Furthermore, step S630 also includes step S631, combining the module coordination relationship diagram, and outputting a fault propagation probability matrix according to the connection relationship between the first fault function module and other function modules; step S632, calculating multiple collaborative fault indicators according to the fault propagation probability matrix.

[0043] Preferably, by analyzing the connection relationship and fault propagation path between modules, a fault propagation probability matrix is ​​constructed, and the collaborative fault index between each module is calculated based on the matrix. Specifically, according to the connection relationship between the first faulty functional module (the module with fault is determined by comparing the sensor data with the healthy sample) and other functional modules (the mutual influence and dependence between functional modules), based on historical data, the connection strength between modules and the fault propagation path, the probability of fault propagation from one module to another is calculated, that is, a fault propagation probability matrix is ​​established, which describes the probability that the fault may propagate to other modules starting from the first faulty functional module. Each element in the matrix represents the probability that another module is affected after the fault of one functional module occurs. Probability: The fault propagation probability matrix can quantitatively describe the fault propagation risk between different modules and help understand the potential impact range of the fault. Finally, based on the fault propagation probability matrix, multiple collaborative fault indicators are calculated, that is, the probability of collaborative faults between multiple modules is evaluated through the fault propagation probability matrix (the collaborative fault indicator is calculated by weighted summation). For example, the collaborative fault indicator of the energy storage system. If the battery fails, the probability of the energy storage system being affected is high. The collaborative fault indicator is calculated based on the probability of the battery fault propagating to the energy storage system. It reflects the fault linkage between modules and can help the system identify potential fault chains and risks in advance, thereby providing more accurate fault warning, diagnosis and optimization measures, and improving the reliability and safety of the system.

[0044] Furthermore, step S600 also includes step S650, obtaining the mode switching combination of the real-time matching working mode according to the module coordination relationship database. Step S660, identifying multiple switching risks corresponding to the mode switching combination according to the fault warning signal. Step S670, screening out the identification mode switching combination greater than the preset switching risk from the multiple switching risks. Step S680, generating a switching warning signal when the received mode switching request belongs to the identification mode switching combination.

[0045] Preferably, a mode switching combination matching the working mode in real time is obtained from the module coordination relationship database, that is, a combination of all target modes that the vehicle may switch from the current working mode to, and the feasibility and conditions of each switching are considered, and then according to the fault warning signal, multiple switching risks corresponding to the mode switching combination are identified. The switching risk refers to the operating risk that the system may face when the current working mode is switched to the target mode, including aggravated module failure, expanded coordination problems or reduced energy efficiency. For example, if the current working mode is "high load mode", switching to "energy saving mode" may cause the power system load to drop rapidly, thereby aggravating the power balance problem between the battery and the fuel cell, and the switching risk may be high; screening is greater than the predicted A mode switching combination with a switching risk identification is set, wherein the preset switching risk is a threshold for distinguishing between low-risk switching and high-risk switching. Among all the mode switching combinations, the mode switching with a risk value greater than the preset switching risk is screened out according to the risk assessment result; the mode switching request can come from the driver's operating instruction (such as switching to a certain mode) or the vehicle's automatic adjustment system (such as automatically switching to energy-saving mode). When the switching request received by the system belongs to the identified high-risk mode switching combination, a switching warning signal is generated, a high-risk switching warning is displayed on the instrument panel, and it is recommended to avoid switching, or to take buffering measures (such as delayed switching, gradual switching, etc.), thereby avoiding high-risk operations and improving safety and reliability.

[0046] Furthermore, step S680 also includes step S681, detecting the repair index of the real-time matching working mode according to the switching warning signal; step S682, if the repair index does not meet the preset repair index, performing mode switching optimization in the module coordination relationship database with the preset switching risk, and outputting the optimal solution for the switching mode.

[0047] Preferably, according to the switching warning signal (indicating that the current mode switching may have a high risk, for example, the status of some modules may not be suitable for performing the switching operation), the repair index of the real-time matching working mode is detected. The repair index is a set of key parameters to measure the health status of the current working mode, which indicates the minimum performance or status standard that the system needs to achieve before the switching operation. For example, the temperature of the fuel cell must fall back to a certain range, the state of charge (SOC) of the energy storage system needs to reach a certain level, and the load fluctuation of the power system needs to be stabilized within a safe range; if the repair index does not meet the preset repair index, that is, it is detected that the repair index of the current working mode does not meet the preset requirements, it means that the state of the system is not sufficient to safely complete the switching of the target mode. Operation, based on the principle of risk minimization while ensuring safety, takes the current working mode (real-time matching mode), target working mode (the mode to be switched to) and the mode switching risks and conditions recorded in the module coordination relational database as input parameters, uses optimization algorithms (such as dynamic programming, shortest path algorithm, genetic algorithm, etc.) to calculate the best switching path, evaluates all possible intermediate mode combinations (such as from "normal mode" to "energy-saving mode" and then to "high load mode"), and performs weighted summation of the switching risks of each path, outputs the switching path with the lowest risk, marks it as the optimal solution for switching mode and outputs it, that is, when the current repair indicators are not met, the mode switching solution with the lowest risk determined after optimization calculation. It not only improves the reliability of vehicle operation, but also reduces the risk of failure caused by unsafe mode switching, and improves the ability of vehicle intelligent control.

[0048] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A multi-module coordinated fault detection and early warning method for hydrogen-electric vehicles, characterized in that: The method comprises: Determining a plurality of functional modules of a hydrogen-electric vehicle, wherein the plurality of functional modules are connected to an onboard sensor network; The plurality of functional modules are collected through the vehicle-mounted sensor network to obtain a plurality of sensor data sets; Performing pattern recognition on the plurality of sensor data sets based on a pattern classification algorithm, and outputting a real-time matching working mode; Constructing a module coordination relationship database, wherein the module coordination relationship database stores coordination relationships of the plurality of functional modules in each working mode; Calling the module coordination relationship database to identify the module coordination relationship diagram corresponding to the real-time matching working mode; The plurality of sensor data sets are subjected to collaborative fault detection according to the module coordination relationship diagram, and a fault warning signal corresponding to the real-time matching working mode is output.

2. The multi-module coordinated fault detection and early warning method for a hydrogen-electric vehicle as claimed in claim 1, characterized in that: Performing pattern recognition on the plurality of sensor data sets based on a pattern classification algorithm and outputting a real-time matching working mode, the method comprising: Performing feature extraction on the multiple sets of sensor data sets and outputting sensor feature vectors; Inputting the sensor feature vector into a trained random forest classification model, performing pattern recognition according to the random forest classification model, and obtaining a real-time matching working mode output by the random forest classification model; Training the random forest classification model includes training multiple decision trees until convergence based on training data, wherein the training data includes obtaining a historical sensor sample data set and label data identifying the hydrogen-electric vehicle mode type.

3. The multi-module coordinated fault detection and early warning method for a hydrogen-electric vehicle as claimed in claim 1, characterized in that: Before performing pattern recognition on the plurality of sensor data sets based on a pattern classification algorithm, the method further comprises: Analyzing the plurality of sensor data sets using a sliding window to obtain a pattern duration; Obtaining a stability index according to a difference between the mode duration and a preset duration threshold; If the stability index is greater than or equal to a preset stability index, pattern recognition is performed on the multiple sets of sensor data sets based on a pattern classification algorithm.

4. The multi-module coordinated fault detection and early warning method for a hydrogen-electric vehicle as claimed in claim 3, characterized in that: If the stability index is less than the preset stability index, performing mode switching prediction according to the multiple sets of sensor data sets, and outputting multiple mode switching probabilities; Determining a first switching working mode according to the multiple mode switching probabilities, wherein the first switching working mode is the working mode with the highest probability among the multiple mode switching probabilities; Calling the module coordination relationship database to identify the module coordination relationship diagram corresponding to the first switching working mode; According to the module coordination relationship diagram, collaborative fault detection is performed on multiple sets of sensor data sets that are continuously monitored.

5. The multi-module coordinated fault detection and early warning method for a hydrogen-electric vehicle as claimed in claim 1, characterized in that: According to the module coordination relationship diagram, collaborative fault detection is performed on the multiple sensor data sets, and a fault warning signal corresponding to the real-time matching working mode is output, the method comprising: Identify the health sensor data samples corresponding to the module coordination relationship diagram; Comparing the plurality of sensor data sets according to the healthy sensor data samples to determine a first faulty functional module; Obtaining a first fault indicator and a plurality of coordinated fault indicators corresponding to the first fault function module; A weighted sum is taken according to the first fault indicator and the multiple coordinated fault indicators to output a fault level, and a fault warning signal is output according to the conversion of the fault level.

6. The multi-module coordinated fault detection and early warning method for a hydrogen-electric vehicle as claimed in claim 5, characterized in that: Methods for obtaining multiple coordinated fault indicators include: Combined with the module coordination relationship diagram, output a fault propagation probability matrix according to the connection relationship between the first fault function module and other function modules; A plurality of coordinated fault indicators are calculated according to the fault propagation probability matrix.

7. The multi-module coordinated fault detection and early warning method for a hydrogen-electric vehicle as claimed in claim 1, characterized in that: After outputting the fault warning signal corresponding to the real-time matching working mode, the method further includes: According to the module coordination relationship database, a mode switching combination of the real-time matching working mode is obtained; identifying, according to the fault warning signal, a plurality of switching risks corresponding to the mode switching combination; Selecting a marking mode switching combination having a greater than a preset switching risk from the plurality of switching risks; When the received mode switching request belongs to the identified mode switching combination, a switching warning signal is generated.

8. The multi-module coordinated fault detection and early warning method for a hydrogen-electric vehicle as claimed in claim 7, characterized in that: When the received mode switching request belongs to the identified mode switching combination, after generating the switching warning signal, the method further includes: According to the switching warning signal, detecting a repair index of the real-time matching working mode; If the repair index does not meet the preset repair index, the preset switching risk is used to perform mode switching optimization in the module coordination relationship database, and an optimal switching mode solution is output.

Images