Fuel cell system fault processing method and device

Abstract

The embodiment of the invention discloses a fuel cell system fault processing method and device, and the method comprises the steps: carrying out the AC impedance spectrum test of a fuel cell, obtaining an AC impedance spectrum, building an equivalent circuit model for the reaction process of the fuel cell, carrying out the fitting of the equivalent circuit model according to the AC impedance spectrum, and obtaining the fault of the fuel cell system. Obtaining impedance data corresponding to each reaction process of the fuel cell; determining residual data between the impedance data corresponding to each reaction process of the fuel cell and the corresponding theoretical data; determining a data change trend of the impedance data according to the residual data; and performing fault diagnosis according to the data change trend to obtain a fault diagnosis result of the fuel cell. According to the fuel cell system fault processing method provided by the invention, the fault of the fuel cell can be diagnosed timely, accurately and comprehensively, the reliability and durability of the fuel cell system are improved, and the service life of the fuel cell is prolonged.

Description

Technical Field

[0001] The present invention relates to the technical field of hydrogen fuel cells, and in particular to a method and device for handling a fuel cell system fault. Background Art

[0002] Proton exchange membrane fuel cells are the core components of automotive fuel cell power systems. Maintaining the internal water balance of proton exchange membrane fuel cells is an important prerequisite for improving fuel cell output performance and extending the life of fuel cells and systems. The water management status of fuel cells can be divided into three types: normal, flooded, and membrane dry. Water management failures include flooding failure and membrane dry failure. Air starvation will reduce the electrochemical reaction rate, causing oxygen to be produced at the anode and hydrogen to be produced at the cathode, affecting the service life of the fuel cell and system. In addition, air starvation caused by flooding or air supply system failure will cause irreversible damage to the battery, and in severe cases, there is a possibility of explosion.

[0003] The commonly used fuel cell diagnosis methods currently include two categories: model-based fault diagnosis and data-driven fault diagnosis. The model-based fault diagnosis method first establishes a mathematical model of the fuel cell system, and then detects faults by analyzing the deviation between the actual system output and the model output. Due to the complexity of the fuel cell system, it is very difficult to establish an accurate and reliable model with this method, which makes the fault diagnosis lack accuracy. The data-driven fault diagnosis method uses historical data information from monitoring to detect faults. Common algorithms include machine learning and deep learning. This method requires a large amount of fault data to train the diagnosis model. In actual applications, fault data is difficult to collect, and the data-driven method may have delays when processing large amounts of data, affecting the effect of real-time fault diagnosis.

[0004] Therefore, it is particularly important to develop a fuel cell system fault handling method that can accurately and comprehensively diagnose fuel cell faults. Summary of the invention

[0005] In order to solve the above technical problems, the present application provides a fuel cell system fault handling method and device, which uses electrochemical AC impedance testing and equivalent circuit fitting, and determines the respective data change trends according to the residual data between the impedance values ​​obtained by fitting and the corresponding theoretical data to realize fuel cell fault diagnosis. Different from the prior art that diagnoses faults by directly comparing the size relationship between the impedance values ​​obtained by fitting and the theoretical values; or uses a fault diagnosis algorithm based on a binary tree support vector machine to classify proton exchange membrane fuel cells, the fuel cell system fault handling method provided by the present application can solve the problem of the current lack of accurate and comprehensive fuel cell fault handling methods.

[0006] The technical solutions provided by this application are as follows:

[0007] In one aspect, the present application provides a fuel cell system fault processing method, the fuel cell system fault processing method comprising:

[0008] Performing an AC impedance spectrum test on the fuel cell to obtain an AC impedance spectrum; establishing an equivalent circuit model for the reaction process of the fuel cell, fitting the equivalent circuit model according to the AC impedance spectrum, and obtaining impedance data corresponding to each reaction process of the fuel cell;

[0009] Determine the impedance data corresponding to each reaction process of the fuel cell and the residual data between the impedance data and the corresponding theoretical data;

[0010] Determine the data change trend of the impedance data corresponding to each reaction process of the fuel cell according to the residual data;

[0011] Fault diagnosis is performed according to the data change trend to obtain a fault diagnosis result of the fuel cell.

[0012] In some optional embodiments, the AC impedance spectrum test of the fuel cell is performed to obtain an AC impedance spectrum, an equivalent circuit model is established for the reaction process of the fuel cell, and the equivalent circuit model is fitted according to the AC impedance spectrum to obtain impedance data corresponding to each reaction process of the fuel cell, including:

[0013] Obtaining measured voltage data and theoretical voltage data of the fuel cell;

[0014] Acquire a preset first residual threshold corresponding to the measured voltage data based on first preset mapping information; the first preset mapping information represents a mapping relationship between the measured voltage data and the first residual threshold;

[0015] Determining a first residual between the measured voltage data and the theoretical voltage data;

[0016] When the first residual is greater than the first residual threshold, performing an AC impedance spectrum test on the fuel cell to obtain an AC impedance spectrum;

[0017] An equivalent circuit model is established for the reaction process of the fuel cell, and the equivalent circuit model is fitted according to the AC impedance spectrum to obtain impedance data corresponding to each reaction process of the fuel cell.

[0018] In some optional embodiments, each reaction process of the fuel cell includes a proton transmembrane transport reaction process, a charge transport reaction process, and a gas diffusion reaction process; establishing an equivalent circuit model for the reaction process of the fuel cell, and fitting the equivalent circuit model according to the AC impedance spectrum, comprises:

[0019] Obtaining an equivalent circuit model;

[0020] Fitting the equivalent circuit model according to the AC impedance spectrum to obtain first impedance data, second impedance data, and third impedance data in the equivalent circuit model;

[0021] The first impedance data is the high-frequency ohmic impedance data corresponding to the proton transmembrane transport reaction; the second impedance data is the cathode activation and charge transfer impedance data corresponding to the charge transfer reaction; and the third impedance data is the mass transfer impedance data corresponding to the gas diffusion reaction.

[0022] In some optional embodiments, the determining of residual data between impedance data corresponding to each reaction process of the fuel cell and respective corresponding theoretical data includes:

[0023] Acquire first theoretical impedance data corresponding to the first impedance data, second theoretical impedance data corresponding to the second impedance data, and third theoretical impedance data corresponding to the third impedance data;

[0024] A second residual is determined based on the first impedance data and the first theoretical impedance data; a third residual is determined based on the second impedance data and the second theoretical impedance data; and a fourth residual is determined based on the third impedance data and the third theoretical impedance data.

[0025] In some optional implementations, determining the data change trend of the impedance data corresponding to each reaction process of the fuel cell according to the residual data includes:

[0026] The data change trend of the first impedance data is determined according to the second residual, the data change trend of the second impedance data is determined according to the third residual; and the data change trend of the first impedance data is determined according to the fourth residual.

[0027] In some optional implementations, determining the data change trend of the first impedance data according to the second residual includes:

[0028] Acquire a preset second residual threshold corresponding to the first impedance data based on second preset mapping information; the second preset mapping information represents a mapping relationship between the first impedance data and the second residual threshold;

[0029] When the second residual is less than or equal to the second residual threshold, the data change trend of the first impedance data is determined to be a stable state; when the second residual is greater than the second residual threshold and the first impedance data is greater than the first theoretical impedance data, the data change trend of the first impedance data is determined to be an increasing state; when the second residual is greater than the second residual threshold and the first impedance data is less than the first theoretical impedance data, the data change trend of the first impedance data is determined to be a decreasing state.

[0030] In some optional implementations, determining the data change trend of the second impedance data according to the third residual includes:

[0031] Acquire a preset third residual threshold corresponding to the second impedance data based on third preset mapping information; the third preset mapping information represents a mapping relationship between the second impedance data and the third residual threshold;

[0032] When the third residual is less than or equal to the third residual threshold, the data change trend of the second impedance data is determined to be a stable state; when the third residual is greater than the third residual threshold and the second impedance data is greater than the theoretical second impedance data, the data change trend of the second impedance data is determined to be an increasing state; when the third residual is greater than the third residual threshold and the second impedance data is less than the theoretical second impedance data, the data change trend of the second impedance data is determined to be a decreasing state.

[0033] In some optional implementations, determining the data change trend of the first impedance data according to the fourth residual includes:

[0034] Acquire a preset fourth residual threshold corresponding to the third impedance data based on fourth preset mapping information; the fourth preset mapping information represents a mapping relationship between the third impedance data and the fourth residual threshold;

[0035] When the fourth residual is less than or equal to the fourth residual threshold, the data change trend of the third impedance data is determined to be a stable state; when the fourth residual is greater than the fourth residual threshold and the third impedance data is greater than the theoretical third impedance data, the data change trend of the third impedance data is determined to be an increasing state; when the fourth residual is greater than the fourth residual threshold and the third impedance data is less than the theoretical third impedance data, the data change trend of the third impedance data is determined to be a decreasing state.

[0036] In some optional implementations, performing fault diagnosis according to the data change trend to obtain the fuel cell fault diagnosis result includes:

[0037] Under the condition that a first preset condition is met, determining that the fault diagnosis result of the fuel cell is a membrane dry fault; the first preset condition is that the first impedance data is in the increasing state, the second impedance data is in the stable state, and the third impedance data is in the stable state;

[0038] In the case where a second preset condition is met, determining that the fault diagnosis result of the fuel cell is a flooding fault; the second preset condition is that the first impedance data is in the decreasing state, the second impedance data is in the stable state, and the third impedance data is in the increasing state;

[0039] When a third preset condition is met, it is determined that the fault diagnosis result of the fuel cell is an air starvation fault; the third preset condition is that the first impedance data is in the decreasing state, the second impedance data is in the increasing state, and the third impedance data is in the increasing state.

[0040] In some optional implementations, after performing fault diagnosis according to the data change trend to obtain the fault diagnosis result of the fuel cell, the method further includes:

[0041] Based on the fault diagnosis results of the fuel cell, executing recovery strategies corresponding to the fault diagnosis results;

[0042] The executing of the recovery strategies corresponding to the respective fault diagnosis results based on the fault diagnosis results of the fuel cell comprises:

[0043] When the fault diagnosis result of the fuel cell is the membrane dry fault, executing a membrane dry recovery strategy;

[0044] When the fault diagnosis result of the fuel cell is the flooding fault, executing a flooding recovery strategy;

[0045] In a case where the fault diagnosis result of the fuel cell is the air starvation fault, an air starvation recovery strategy is executed.

[0046] On the other hand, the present application proposes an electronic device for a fuel cell system fault handling method, the electronic device comprising a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or at least one program being loaded and executed by the processor to implement the fuel cell system fault handling method as described above.

[0047] On the other hand, the present application proposes a computer-readable storage medium, which stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the fuel cell system fault handling method as described above.

[0048] On the other hand, the present application proposes a computer program product, including a computer program, which implements the fuel cell system fault handling method as described above when executed by a processor.

[0049] The fuel cell system fault handling method provided by the present application obtains the measured voltage data and theoretical voltage data of the fuel cell; when the residual between the measured voltage data and the theoretical voltage data meets the preset conditions, the fuel cell is tested for AC impedance spectrum to obtain the AC impedance spectrum; the AC impedance spectrum is fitted with an equivalent circuit to obtain the impedance data corresponding to each reaction process of the fuel cell; the fault diagnosis is performed according to the impedance data corresponding to each reaction process of the fuel cell to obtain the fault diagnosis result of the fuel cell; based on the fault diagnosis result of the fuel cell, the corresponding recovery strategy is executed. By performing AC impedance spectrum testing and equivalent circuit fitting according to a preset equivalent circuit model, the accuracy and comprehensiveness of fault diagnosis are improved, and the fault diagnosis of the fuel cell is realized according to the change trend of the impedance value obtained by fitting, and the corresponding recovery strategy of the fault diagnosis result is executed, the fault of the fuel cell can be diagnosed in a timely, accurate and comprehensive manner, the reliability, durability and output performance of the fuel cell system are improved, and the operating life of the fuel cell system is extended. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0051] Figure 1 is a schematic flow chart of a method for handling a fuel cell system fault according to an embodiment of the present invention;

[0052] Figure 2 is a schematic diagram of an equivalent circuit model proposed according to an embodiment of the present invention;

[0053] Figure 3 It is a schematic diagram of the operation flow of a battery system fault processing method proposed according to an embodiment of the present invention. DETAILED DESCRIPTION

[0054] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0055] The term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure or characteristic that may be included in at least one implementation of the present application. In the description of the present application, it should be understood that the orientation or positional relationship indicated by the terms "upper", "lower", "top", "bottom", etc. is based on the orientation or positional relationship shown in the accompanying drawings, which is only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as a limitation on the present application. In addition, the terms "first" and "second" are used only for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, the features defined as "first" and "second" may include one or more of the features explicitly or implicitly. Moreover, the terms "first", "second", etc. are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0056] When a numerical range is disclosed herein, the above range is deemed to be continuous and includes the minimum and maximum values ​​of the range, as well as each value between such minimum and maximum values. Further, when a range refers to an integer, each integer between the minimum and maximum values ​​of the range is included. In addition, when multiple ranges are provided to describe features or characteristics, the ranges can be merged. In other words, unless otherwise indicated, all ranges disclosed herein should be understood to include any and all sub-ranges included therein. For example, a specified range from "1 to 10" should be deemed to include any and all sub-ranges between a minimum of 1 and a maximum of 10. Exemplary sub-ranges of ranges 1 to 10 include, but are not limited to, 1 to 6.1, 3.5 to 7.8, 5.5 to 10, etc.

[0057] Since there is currently a lack of a fuel cell fault handling method that is timely, accurate, and comprehensive and can provide a recovery strategy, in order to timely, accurately, and comprehensively diagnose fuel cell faults, provide corresponding recovery strategies, improve the reliability, durability, and output performance of the fuel cell system, and extend the operating life of the fuel cell, the present application provides a fuel cell system fault handling method and device.

[0058] See also Figure 1 , Figure 1 1 is a flow chart of a method for handling a fuel cell system fault according to an embodiment of the present invention; the present application provides a method for handling a fuel cell system fault, the method for handling a fuel cell system fault comprising:

[0059] S101. Perform an AC impedance spectrum test on a fuel cell to obtain an AC impedance spectrum; establish an equivalent circuit model for the reaction process of the fuel cell, and fit the equivalent circuit model according to the AC impedance spectrum to obtain impedance data corresponding to each reaction process of the fuel cell.

[0060] Optionally, the fuel cell may be a proton exchange membrane fuel cell; the fuel cell may be composed of a plurality of fuel cell units connected in series or in parallel.

[0061] In an optional embodiment, the AC impedance spectrum test is performed on the fuel cell to obtain an AC impedance spectrum; an equivalent circuit model is established for the reaction process of the fuel cell, and the equivalent circuit model is fitted according to the AC impedance spectrum to obtain impedance data corresponding to each reaction process of the fuel cell, including:

[0062] Obtaining measured voltage data and theoretical voltage data of the fuel cell;

[0063] Acquire a preset first residual threshold corresponding to the measured voltage data based on first preset mapping information; the first preset mapping information represents a mapping relationship between the measured voltage data and the first residual threshold;

[0064] Determining a first residual between the measured voltage data and the theoretical voltage data;

[0065] When the first residual is greater than the first residual threshold, performing an AC impedance spectrum test on the fuel cell to obtain an AC impedance spectrum;

[0066] The equivalent circuit model is fitted according to the AC impedance spectrum to obtain impedance data corresponding to each reaction process of the fuel cell.

[0067] Optionally, the measured voltage data is obtained based on a battery voltage monitor, and the battery voltage monitor is provided in the fuel cell system.

[0068] Optionally, the theoretical voltage data can be measured by a battery voltage monitor. After the fuel cell system is calibrated at the factory, it will output an operating parameter table based on the actual operating conditions of the system, including parameters such as voltage, current and impedance values ​​when the system is operating at a fixed power point. When the fuel cell system operates normally when leaving the factory, the voltage of the fuel cell is measured as the theoretical voltage data.

[0069] Optionally, the theoretical voltage data may also be obtained by theoretical calculation, and the calculation method is as follows:

[0070] According to the Nernst formula, the theoretical output voltage of a single battery can be obtained, and the calculation formula is as follows:

[0071]

[0072] It should be noted that, among them, E n is the thermodynamic electromotive force; a=8.5×10 -4 ; b = 4.3085 × 10 -5 ; T st is the fuel cell operating temperature; is the effective partial pressure of hydrogen at the interface between the catalyst and the gas; is the effective partial pressure of oxygen at the interface between the catalyst and the gas.

[0073] Furthermore, activation loss is mainly due to the slow reaction rate at the electrode surface, and part of the voltage will be consumed when driving the chemical reaction of electrons to or from the electrode. act The calculation formula is as follows:

[0074]

[0075] It should be noted that, among them, T st is the operating temperature of the fuel cell; i is the current of the fuel cell; ε1, ε2, ε3, ε4 are all model coefficients; ε1 = -0.9514; ε3=7.4×10 -5 ; ε4=-1.87×10 -4 ; A is the proton exchange membrane activation area; is the dissolved concentration of hydrogen at the gas-liquid interface; is the dissolved oxygen concentration at the gas-liquid interface.

[0076] It should be noted that and The value of can be obtained from Henry's law, and the calculation formula is as follows:

[0077]

[0078] It should be noted that, is the effective partial pressure of hydrogen at the interface between the catalyst and the gas; is the effective partial pressure of oxygen at the interface between the catalyst and the gas; T st is the fuel cell operating temperature.

[0079] Furthermore, the ohmic polarization overpotential is mainly generated by the equivalent membrane impedance of the proton exchange membrane and the impedance that prevents protons from passing through the proton exchange membrane, and its calculation formula is as follows:

[0080]

[0081] It should be noted that, among them, R ohm is the measured value of high-frequency ohmic impedance; A is the activation area of ​​the proton exchange membrane.

[0082] Furthermore, concentration loss is caused by the change in the concentration of reactants on the electrode surface when the fuel is used. This loss is also called mass transfer loss. Concentration polarization overpotential V con The calculation formula is as follows:

[0083] V con =m·exp(n·i)

[0084] It should be noted that, n is an empirical value; i is the current of the fuel cell; and it is usually taken as 8×10 -3 ; in T st >312.15, m=1.1×10 -4 -1.2×10 -6 (T st -273.15); in T st When <312.15, m=3.3×10 -3 -8.2×10 -5 (T st -273.15).

[0085] Furthermore, the calculation formula for the theoretical voltage of a single cell of a fuel cell is as follows:

[0086] Vc=E n -V act -V ohm -V con

[0087] It should be noted that, among them, E n is the thermodynamic electromotive force; V act is the activation polarization overpotential; V ohm is the ohmic polarization overpotential; V con is the concentration polarization overpotential.

[0088] Furthermore, if the fuel cell is composed of N single cells connected in series, the theoretical voltage Vst of the fuel cell is:

[0089] Vst=N·Vc

[0090] It should be noted that, N is the number of single cells; Vc is the theoretical voltage of a single cell of the fuel cell.

[0091] The theoretical voltage data provides a benchmark data, which can be used as a standard for normal system operation. When the fuel cell system is operating normally, the theoretical voltage is calculated and subsequent diagnosis and recovery strategies are carried out accordingly. When the system performance begins to decline, problems can be discovered in time, ensuring that the system operates at the highest efficiency and reducing energy waste and equipment loss.

[0092] Optionally, the residual is the difference between the measured voltage data and the theoretical voltage data.

[0093] Optionally, the preset condition may be set according to actual business needs, and is not limited thereto. Exemplarily, the preset condition may be that the residual is greater than a preset residual threshold.

[0094] Optionally, the first preset mapping information represents a mapping relationship between the measured voltage data and the first residual threshold. Exemplarily, the first preset mapping information may be a mapping curve, and the mapping curve includes the first residual threshold corresponding to different measured voltage data conditions.

[0095] Optionally, the first residual threshold may be set according to actual business requirements, and is not limited thereto. Exemplarily, the first residual threshold may be 10% of the measured voltage data.

[0096] Optionally, a difference between the measured voltage data and the theoretical voltage data is calculated to obtain a first residual.

[0097] Optionally, the AC impedance spectroscopy test is based on the response of the fuel cell system to an AC signal, and the result of the AC impedance spectroscopy test may be a curve.

[0098] Optionally, when the residual between the measured voltage data and the theoretical voltage data is less than or equal to a first residual threshold, it indicates that the fuel cell is in a normal state and there is no need to perform AC impedance spectrum testing and equivalent circuit fitting for fault diagnosis.

[0099] Optionally, when the residual between the measured voltage data and the theoretical voltage data is greater than a first residual threshold, it indicates that the fuel cell is in an abnormal state and fault diagnosis is required, so an AC impedance spectrum test is performed on the fuel cell to obtain an AC impedance spectrum.

[0100] The AC impedance test is performed when the fuel cell is abnormal. If the AC impedance spectrum continuous test will increase the extra power consumption of the system, the extra power consumption of the system can be reduced to maintain the stable operation of the fuel cell system.

[0101] In an optional embodiment, the fuel cell system fault processing method further includes:

[0102] When the first residual is less than or equal to the first residual threshold, it is determined that the residual between the measured voltage data and the theoretical voltage data does not meet the preset conditions, and the rapid AC impedance spectrum test is not performed; new measured voltage data of the fuel cell is reacquired; and when the residual between the new measured voltage data and the theoretical voltage data meets the preset conditions, an AC impedance spectrum test is performed on the fuel cell to obtain an AC impedance spectrum.

[0103] The residual between the measured voltage data and the theoretical voltage data is used to determine whether to perform the AC impedance spectrum test. The residual between the measured voltage data and the theoretical voltage data is used to determine whether the fuel cell is in an abnormal state, thereby determining whether an AC impedance spectrum test is needed. Since the easiest way to determine an abnormality is to monitor the voltage fluctuation range, a residual value is set to determine whether to execute the next command. Since the system error is usually constant or trending, whether the fuel cell is abnormal based on the constant or trending voltage residual can eliminate the influence of the system error on the measured voltage data to a certain extent, simplify the data analysis process, and make it easier to identify anomalies.

[0104] In an optional embodiment, each reaction process of the fuel cell includes a proton transmembrane transport reaction process, a charge transport reaction process, and a gas diffusion reaction process; establishing an equivalent circuit model for the reaction process of the fuel cell, and fitting the equivalent circuit model according to the AC impedance spectrum, comprises:

[0105] Obtaining an equivalent circuit model;

[0106] Fitting the equivalent circuit model according to the AC impedance spectrum to obtain first impedance data, second impedance data, and third impedance data in the equivalent circuit model;

[0107] The first impedance data is the high-frequency ohmic impedance data corresponding to the proton transmembrane transport reaction; the second impedance data is the cathode activation and charge transfer impedance data corresponding to the charge transfer reaction; and the third impedance data is the mass transfer impedance data corresponding to the gas diffusion reaction.

[0108] Optionally, the AC impedance spectrum is a continuous spectrum, which represents the real and imaginary parts of the impedance of the fuel cell at various frequencies. After fitting the equivalent circuit model, the impedance data corresponding to each reaction process of the fuel cell can be decomposed and obtained.

[0109] Optionally, after the AC impedance spectrum test is completed, an AC impedance spectrum test is performed on the fuel cell to obtain an AC impedance spectrum; an equivalent circuit model is established for the reaction process of the fuel cell, and the equivalent circuit model is fitted according to the AC impedance spectrum. It should be noted that the criterion for judging whether the AC impedance spectrum test is completed is whether the AC impedance spectrum test for all frequency values ​​is completed. Exemplarily, if the frequency of the AC impedance setting is 1000Hz~1Hz, then after the AC impedance spectrum test is completed at a frequency value of 1Hz, the AC impedance spectrum test for all frequency values ​​is completed, and then an equivalent circuit model is established for the reaction process of the fuel cell, and the equivalent circuit model is fitted according to the AC impedance spectrum, and the impedance data corresponding to each reaction process of the fuel cell is calculated.

[0110] Optionally, the equivalent circuit model can be set according to actual business needs. Optionally, the preset equivalent circuit model is determined by a large amount of experimental data, see Figure 2 , Figure 2 is a schematic diagram of an equivalent circuit model proposed according to an embodiment of the present invention. In the equivalent circuit model, the impedance corresponding to each reaction process during the operation of the fuel cell system can be most accurately characterized. The equivalent circuit model includes a first impedance R corresponding to the charge transfer reaction. ohm , the second impedance R corresponding to the charge transfer reaction ct1 , the third impedance R corresponding to the gas diffusion reaction ct2 , the second impedance R ct1 The corresponding capacitance C d1 , the third impedance R ct2 The corresponding capacitance C d2 The first impedance R ohm , the second impedance R ct1 , the third impedance R ct2 In series, due to the double charge layer phenomenon in the fuel cell, that is, the charge layer formed at the contact interface between the electrode and the electrolyte, one layer is the charge layer formed on the electrode surface due to charge adsorption, and the other layer is the opposite charge layer formed in the electrolyte due to charge repulsion. In order to simulate this phenomenon, the second impedance R ct1 and the third impedance R ct2 A capacitor is connected in parallel to each of the two circuits, and the resulting equivalent circuit model can more accurately correspond to the characteristics of the fuel cell.

[0111] Optionally, the first impedance R is calculated based on the equivalent circuit model fitting ohm The corresponding first impedance data, R ct1 The corresponding second impedance data, R ct2The corresponding third impedance data. The input of the equivalent circuit model fitting is an AC impedance spectrum, which contains the real and imaginary parts of the fuel cell impedance at each frequency. The equivalent circuit model is fitted through algorithms or software to calculate the impedance data of each reaction process of the fuel cell.

[0112] Alternatively, the equivalent circuit model can be fitted by a nonlinear least squares method, using an iterative calculation using a selected optimization algorithm, such as the Levenberg-Marquardt algorithm, Newton's method, or gradient descent, and then adjusting the parameter values ​​to reduce the difference between the experimental data and the model prediction data, usually using the root mean square error or χ 2 The statistic is used as an error function to evaluate the model fit. According to the error size and direction, the optimization algorithm is used to update the impedance values ​​in the equivalent circuit model. The above process is repeated until the change in the error function is less than the preset threshold or the maximum number of iterations is reached, and the impedance value corresponding to each reaction of the final output is determined. The preset threshold and maximum number of iterations of the error function can be set according to the actual business needs of the algorithm, and are not limited here.

[0113] It should be noted that, in the embodiment of the present scheme, according to the residual data between the impedance data of each reaction process of the fuel cell and the corresponding theoretical data, the data change trend of the impedance data corresponding to each reaction process of the fuel cell is determined according to the residual data, so as to obtain the fault diagnosis result of the fuel cell, and the output capacitor C is not required. d1 and capacitor C d2 The capacitance value, capacitance C d1 and capacitor C d2 This is to make the obtained equivalent circuit model correspond to the characteristics of the fuel cell more accurately.

[0114] Impedance data is obtained by fitting and calculating the equivalent circuit model. Circuit fitting can decompose the complex impedance spectrum into several simple circuit elements, making it easier to understand the behavior of the system. At the same time, circuit fitting provides an objective and standardized process for the analysis of AC impedance spectrum, and fitting the equivalent circuit model can provide more accurate impedance data, thereby improving the accuracy and efficiency of fault diagnosis.

[0115] S102. Determine residual data between impedance data corresponding to each reaction process of the fuel cell and respective corresponding theoretical data.

[0116] In an optional embodiment, the determining of residual data between impedance data corresponding to each reaction process of the fuel cell and respective corresponding theoretical data includes:

[0117] Acquire first theoretical impedance data corresponding to the first impedance data, second theoretical impedance data corresponding to the second impedance data, and third theoretical impedance data corresponding to the third impedance data;

[0118] A second residual is determined based on the first impedance data and the first theoretical impedance data; a third residual is determined based on the second impedance data and the second theoretical impedance data; and a fourth residual is determined based on the third impedance data and the third theoretical impedance data.

[0119] Optionally, the first theoretical impedance data, the second theoretical impedance data, and the third theoretical impedance data can be obtained by measuring impedance data corresponding to each reaction in the equivalent circuit model when the fuel cell system operates normally, as the theoretical impedance data.

[0120] Optionally, the normal operation of the fuel cell system means that the fuel cell system will output the optimal initial value or standard value of the impedance corresponding to each reaction of the fuel cell after the factory calibration is completed. Therefore, the impedance data corresponding to each reaction in the equivalent circuit model measured when the fuel cell system leaves the factory is used as the theoretical impedance data.

[0121] Optionally, the difference between the first impedance data and the first theoretical impedance data is calculated to obtain a second residual; the difference between the second impedance data and the second theoretical impedance data is calculated to obtain a third residual; the difference between the third impedance data and the third theoretical impedance data is calculated to obtain a fourth residual.

[0122] S103. Determine the data change trend of the impedance data corresponding to each reaction process of the fuel cell according to the residual data.

[0123] In an optional embodiment, determining the data change trend of the impedance data corresponding to each reaction process of the fuel cell according to the residual data includes:

[0124] The data change trend of the first impedance data is determined according to the second residual, the data change trend of the second impedance data is determined according to the third residual; and the data change trend of the third impedance data is determined according to the fourth residual.

[0125] In an optional embodiment, determining the data change trend of the first impedance data according to the second residual includes:

[0126] When the second residual is less than or equal to the second residual threshold, the data change trend of the first impedance data is determined to be a stable state; when the second residual is greater than the second residual threshold and the first impedance data is greater than the first theoretical impedance data, the data change trend of the first impedance data is determined to be an increasing state; when the second residual is greater than the second residual threshold and the first impedance data is less than the first theoretical impedance data, the data change trend of the first impedance data is determined to be a decreasing state.

[0127] Optionally, the second preset mapping information represents a mapping relationship between the first impedance data and the second residual threshold. Exemplarily, the second preset mapping information may be a mapping curve, and the mapping curve includes the second residual threshold corresponding to different first impedance data conditions.

[0128] Optionally, the second residual threshold may be set according to actual business requirements, and is not limited thereto. Exemplarily, the second residual threshold may be 10% of the first impedance data.

[0129] Optionally, the increasing state of the first impedance data means that the first impedance data is greater than the first theoretical impedance data and exceeds the range of the second residual threshold; the decreasing state of the first impedance data means that the first impedance data is less than the first theoretical impedance data and exceeds the range of the second residual threshold.

[0130] Optionally, the first impedance data is high-frequency ohmic impedance data corresponding to a proton transmembrane transport reaction, representing the proton conduction capacity of the proton exchange membrane. The proton conduction rate is related to the water content of the proton exchange membrane. If the proton exchange membrane is too dry, the proton conduction rate will decrease. Therefore, if the first impedance data increases, it indicates that proton conduction is obstructed and a membrane dry failure occurs.

[0131] In an optional embodiment, determining the data change trend of the second impedance data according to the third residual includes:

[0132] Acquire a preset third residual threshold corresponding to the second impedance data based on third preset mapping information; the third preset mapping information represents a mapping relationship between the second impedance data and the third residual threshold;

[0133] When the third residual is less than or equal to the third residual threshold, the data change trend of the second impedance data is determined to be a stable state; when the third residual is greater than the third residual threshold and the second impedance data is greater than the theoretical second impedance data, the data change trend of the second impedance data is determined to be an increasing state; when the third residual is greater than the third residual threshold and the second impedance data is less than the theoretical second impedance data, the data change trend of the second impedance data is determined to be a decreasing state.

[0134] Optionally, the third preset mapping information represents a mapping relationship between the second impedance data and the third residual threshold. Exemplarily, the third preset mapping information may be a mapping curve, and the mapping curve includes the third residual threshold corresponding to different second impedance data conditions.

[0135] Optionally, the third residual threshold may be set according to actual business requirements, and is not limited thereto. Exemplarily, the third residual threshold may be 10% of the second impedance data.

[0136] Optionally, the increasing state of the second impedance data means that the second impedance data is greater than the second theoretical impedance data and exceeds the range of the second residual threshold; the decreasing state of the second impedance data means that the second impedance data is less than the second theoretical impedance data and exceeds the range of the second residual threshold.

[0137] Optionally, the second impedance data is the cathode activation and charge transfer impedance data corresponding to the charge transfer reaction, and is related to the transmission of gas in the proton exchange membrane electrode. Therefore, if the first impedance data decreases and the second impedance data increases, it means that the water content is too high, the catalyst layer is flooded, the active area is reduced, and a flooding failure occurs.

[0138] In an optional embodiment, determining the data change trend of the third impedance data according to the fourth residual includes:

[0139] Acquire a preset fourth residual threshold corresponding to the third impedance data based on fourth preset mapping information; the fourth preset mapping information represents a mapping relationship between the third impedance data and the fourth residual threshold;

[0140] When the fourth residual is less than or equal to the fourth residual threshold, the data change trend of the third impedance data is determined to be a stable state; when the fourth residual is greater than the fourth residual threshold and the third impedance data is greater than the theoretical third impedance data, the data change trend of the third impedance data is determined to be an increasing state; when the fourth residual is greater than the fourth residual threshold and the third impedance data is less than the theoretical third impedance data, the data change trend of the third impedance data is determined to be a decreasing state.

[0141] Optionally, the fourth preset mapping information represents a mapping relationship between the third impedance data and the fourth residual threshold. Exemplarily, the fourth preset mapping information may be a mapping curve, and the mapping curve includes the fourth residual threshold corresponding to different third impedance data conditions.

[0142] Optionally, the fourth residual threshold may be set according to actual business requirements, and is not limited thereto. Exemplarily, the fourth residual threshold may be 10% of the third impedance data.

[0143] Optionally, the increasing state of the third impedance data means that the third impedance data is greater than the third theoretical impedance data and exceeds the range of the fourth residual threshold; the decreasing state of the third impedance data means that the third impedance data is less than the third theoretical impedance data and exceeds the range of the fourth residual threshold.

[0144] Optionally, the third impedance data is mass transfer impedance data corresponding to the gas diffusion reaction, which is related to the activity of the catalyst in the reaction gas. Therefore, if the first impedance data and the second impedance data increase synchronously, it indicates that the reaction gas is insufficient and an air starvation fault occurs.

[0145] S104. Perform fault diagnosis according to the data change trend to obtain a fault diagnosis result of the fuel cell.

[0146] In an optional embodiment, performing fault diagnosis according to the data change trend to obtain the fuel cell fault diagnosis result includes:

[0147] Under the condition that a first preset condition is met, determining that the fault diagnosis result of the fuel cell is a membrane dry fault; the first preset condition is that the first impedance data is in the increasing state, the second impedance data is in the stable state, and the third impedance data is in the stable state;

[0148] Optionally, when the first impedance data increases, the second impedance data is stable, and the third impedance data is stable, it is determined that the fault diagnosis result of the fuel cell is a membrane dry fault.

[0149] In the case where a second preset condition is met, determining that the fault diagnosis result of the fuel cell is a flooding fault; the second preset condition is that the first impedance data is in the decreasing state, the second impedance data is in the stable state, and the third impedance data is in the increasing state;

[0150] Optionally, when the first impedance data decreases, the second impedance data is stable, and the third impedance data increases, it is determined that the fault diagnosis result of the fuel cell is a flooding fault.

[0151] When a third preset condition is met, it is determined that the fault diagnosis result of the fuel cell is an air starvation fault; the third preset condition is that the first impedance data is in the decreasing state, the second impedance data is in the increasing state, and the third impedance data is in the increasing state.

[0152] Optionally, when the first impedance data decreases, the second impedance data increases, and the third impedance data increases, it is determined that the fault diagnosis result of the fuel cell is an air starvation fault.

[0153] By first determining the data change trend of the first impedance data, the data change trend of the second impedance data, and the data change trend of the third impedance data, and then performing fault diagnosis, by preliminarily determining the data change trend of the measured value, it is possible to quickly screen out which impedance data may have problems, thereby narrowing the scope of fault diagnosis and improving the efficiency and accuracy of fault diagnosis.

[0154] In an optional embodiment, after performing fault diagnosis according to the data change trend to obtain the fault diagnosis result of the fuel cell, the method further includes:

[0155] Based on the fault diagnosis results of the fuel cell, recovery strategies corresponding to the fault diagnosis results are executed.

[0156] Optionally, the recovery strategy is executed based on a program pre-set in the controller.

[0157] In an optional embodiment, based on the fault diagnosis result of the fuel cell, executing the recovery strategy corresponding to each fault diagnosis result includes:

[0158] When the fault diagnosis result of the fuel cell is the membrane dry fault, executing a membrane dry recovery strategy;

[0159] When the fault diagnosis result of the fuel cell is the flooding fault, executing a flooding recovery strategy;

[0160] In a case where the fault diagnosis result of the fuel cell is the air starvation fault, an air starvation recovery strategy is executed.

[0161] Optionally, the membrane dry recovery strategy may include: (1) rapidly loading the fuel cell to a high-power operating state; (2) lowering the air intake temperature to reduce the fuel cell temperature; (3) lowering the operating water temperature of the fuel cell system; (4) increasing the air intake pressure; It should be noted that the methods included in the above membrane dry recovery strategy are in a parallel relationship, and the membrane dry recovery strategy can be executed according to actual business needs, combined with the degree of fault and the power demand during system operation.

[0162] Optionally, the flooding recovery strategy may include: (1) reducing the operating power of the fuel cell; (2) increasing the operating water temperature of the fuel cell system; (3) reducing the air intake pressure; It should be noted that the methods included in the above flooding recovery strategy are in a parallel relationship, and the flooding recovery strategy can be executed according to actual business needs, combined with the degree of fault and the power demand during system operation.

[0163] Optionally, the air starvation recovery strategy may be: increasing the rotation speed of the air compressor to increase the air intake flow rate.

[0164] Designing corresponding recovery strategies for different fault diagnosis results can locate and solve problems more quickly, reduce the trial and error process, improve the efficiency of fault handling, and ensure that the system can recover to a stable state as soon as possible after a fault occurs, thereby improving the reliability of the system. The fuel cell system can automatically diagnose faults and take recovery measures, reducing manual intervention, shortening fault handling time, and reducing downtime caused by faults; the system can continuously monitor and ensure the normal operation of the equipment, improving the reliability and stability of the entire system and increasing the system life.

[0165] See also Figure 3 , Figure 3 The figure is a schematic diagram of the operation flow of a battery system fault handling method proposed according to an embodiment of the present invention. The following is an overall description of a fuel cell system fault handling method provided in an embodiment of the present application:

[0166] 1) Perform status monitoring on the fuel cell system to obtain the measured voltage data and theoretical voltage data of the fuel cell.

[0167] 2) determining a first residual between the measured voltage data and the theoretical voltage data, and judging a relationship between the first residual and a first residual threshold;

[0168] When the first residual is greater than the first residual threshold, an AC impedance spectrum test is performed to obtain an AC impedance spectrum; when the first residual is less than or equal to the first residual threshold, the rapid AC impedance spectrum test is not performed, and state monitoring is performed again to reacquire new measured voltage data of the fuel cell; when the first residual between the new measured voltage data and the theoretical voltage data is greater than the first residual threshold, an AC impedance spectrum test is performed to obtain an AC impedance spectrum.

[0169] 3) performing an AC impedance spectrum test on the fuel cell to obtain an AC impedance spectrum; establishing an equivalent circuit model for the reaction process of the fuel cell, fitting the equivalent circuit model according to the AC impedance spectrum, and obtaining impedance data corresponding to each reaction process of the fuel cell;

[0170] 4) determining the residual data between the impedance data corresponding to each reaction process of the fuel cell and the corresponding theoretical data;

[0171] 5) determining the data change trend of the impedance data corresponding to each reaction process of the fuel cell according to the residual data;

[0172] 6) performing fault diagnosis according to the data change trend to obtain a fault diagnosis result of the fuel cell;

[0173] 7) Based on the fault diagnosis results of the fuel cell, the recovery strategies corresponding to the fault diagnosis results are executed.

[0174] 8) After executing the recovery strategies corresponding to the fault diagnosis results, perform state monitoring, obtain the measured voltage data and theoretical voltage data of the fuel cell, determine the first residual between the measured voltage data and the theoretical voltage data, and judge the relationship between the first residual and the first residual threshold; when the first residual is less than or equal to the first residual threshold, terminate the execution of the recovery strategy; when the first residual is greater than the first residual threshold, continue to execute the recovery strategy corresponding to the fault diagnosis result, and perform state monitoring until the first residual is less than or equal to the first residual threshold, and then terminate the execution of the recovery strategy.

[0175] The fuel cell system fault handling method provided by the present application obtains the measured voltage data and theoretical voltage data of the fuel cell; when the residual between the measured voltage data and the theoretical voltage data meets the preset conditions, the fuel cell is tested for AC impedance spectrum to obtain the AC impedance spectrum; the AC impedance spectrum is fitted with an equivalent circuit to obtain the impedance data corresponding to each reaction process of the fuel cell; the fault diagnosis is performed according to the impedance data corresponding to each reaction process of the fuel cell to obtain the fault diagnosis result of the fuel cell; based on the fault diagnosis result of the fuel cell, the corresponding recovery strategy is executed. By performing AC impedance spectrum testing and equivalent circuit fitting according to a preset equivalent circuit model, the accuracy and comprehensiveness of fault diagnosis are improved, and the fault diagnosis of the fuel cell is realized according to the change trend of the impedance value obtained by fitting, and the corresponding recovery strategy of the fault diagnosis result is executed, the fault of the fuel cell can be diagnosed in a timely, accurate and comprehensive manner, the reliability, durability and output performance of the fuel cell system are improved, and the operating life of the fuel cell system is extended.

[0176] In an optional embodiment, the present application proposes an electronic device for a fuel cell system fault handling method, the electronic device comprising a processor and a memory, the memory storing at least one instruction or at least one program, the at least one instruction or at least one program being loaded and executed by the processor to implement the fuel cell system fault handling method as described above.

[0177] In an optional embodiment, the present application proposes a computer-readable storage medium, which stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by a processor to implement the fuel cell system fault handling method as described above.

[0178] In an optional embodiment, the present application proposes a computer program product, including a computer program, which implements the fuel cell system fault handling method as described above when executed by a processor.

[0179] The above description is only an optional embodiment of the present application and is not intended to limit the present application. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present application should be included in the protection scope of the present application.

Claims

1. A method for handling a fuel cell system fault, characterized in that: The fuel cell system fault processing method comprises: Performing an AC impedance spectrum test on the fuel cell to obtain an AC impedance spectrum; establishing an equivalent circuit model for the reaction process of the fuel cell, fitting the equivalent circuit model according to the AC impedance spectrum, and obtaining impedance data corresponding to each reaction process of the fuel cell; Determine the impedance data corresponding to each reaction process of the fuel cell and the residual data between the impedance data and the corresponding theoretical data; Determine the data change trend of the impedance data corresponding to each reaction process of the fuel cell according to the residual data; Fault diagnosis is performed according to the data change trend to obtain a fault diagnosis result of the fuel cell.

2. The method for handling a fuel cell system failure according to claim 1, characterized in that: The method of performing an AC impedance spectrum test on the fuel cell to obtain an AC impedance spectrum, establishing an equivalent circuit model for the reaction process of the fuel cell, and fitting the equivalent circuit model according to the AC impedance spectrum to obtain impedance data corresponding to each reaction process of the fuel cell includes: Obtaining measured voltage data and theoretical voltage data of the fuel cell; Acquire a preset first residual threshold corresponding to the measured voltage data based on first preset mapping information; the first preset mapping information represents a mapping relationship between the measured voltage data and the first residual threshold; Determining a first residual between the measured voltage data and the theoretical voltage data; When the first residual is greater than the first residual threshold, performing an AC impedance spectrum test on the fuel cell to obtain an AC impedance spectrum; An equivalent circuit model is established for the reaction process of the fuel cell, and the equivalent circuit model is fitted according to the AC impedance spectrum to obtain impedance data corresponding to each reaction process of the fuel cell.

3. The method for handling a fuel cell system failure according to claim 1, characterized in that: Each reaction process of the fuel cell includes a proton transmembrane transport reaction process, a charge transport reaction process, and a gas diffusion reaction process; establishing an equivalent circuit model for the reaction process of the fuel cell, fitting the equivalent circuit model according to the AC impedance spectrum, and obtaining impedance data corresponding to each reaction process of the fuel cell, including: Obtaining an equivalent circuit model; Fitting the equivalent circuit model according to the AC impedance spectrum to obtain first impedance data, second impedance data, and third impedance data in the equivalent circuit model; The first impedance data is the high-frequency ohmic impedance data corresponding to the proton transmembrane transport reaction; the second impedance data is the cathode activation and charge transfer impedance data corresponding to the charge transfer reaction; and the third impedance data is the mass transfer impedance data corresponding to the gas diffusion reaction.

4. The method for handling a fuel cell system failure according to claim 3, characterized in that: The determining of residual data between impedance data corresponding to each reaction process of the fuel cell and respective corresponding theoretical data includes: Acquire first theoretical impedance data corresponding to the first impedance data, second theoretical impedance data corresponding to the second impedance data, and third theoretical impedance data corresponding to the third impedance data; A second residual is determined based on the first impedance data and the first theoretical impedance data; a third residual is determined based on the second impedance data and the second theoretical impedance data; and a fourth residual is determined based on the third impedance data and the third theoretical impedance data.

5. The method for handling a fuel cell system failure according to claim 4, characterized in that: The step of determining the data change trend of the impedance data corresponding to each reaction process of the fuel cell according to the residual data includes: The data change trend of the first impedance data is determined according to the second residual, the data change trend of the second impedance data is determined according to the third residual; and the data change trend of the first impedance data is determined according to the fourth residual.

6. The method for handling a fuel cell system failure according to claim 5, characterized in that: The determining the data change trend of the first impedance data according to the second residual includes: Acquire a preset second residual threshold corresponding to the first impedance data based on second preset mapping information; the second preset mapping information represents a mapping relationship between the first impedance data and the second residual threshold; When the second residual is less than or equal to the second residual threshold, the data change trend of the first impedance data is determined to be a stable state; when the second residual is greater than the second residual threshold and the first impedance data is greater than the first theoretical impedance data, the data change trend of the first impedance data is determined to be an increasing state; when the second residual is greater than the second residual threshold and the first impedance data is less than the first theoretical impedance data, the data change trend of the first impedance data is determined to be a decreasing state.

7. The method for handling a fuel cell system failure according to claim 5, characterized in that: The step of determining the data change trend of the second impedance data according to the third residual includes: Acquire a preset third residual threshold corresponding to the second impedance data based on third preset mapping information; the third preset mapping information represents a mapping relationship between the second impedance data and the third residual threshold; When the third residual is less than or equal to the third residual threshold, the data change trend of the second impedance data is determined to be a stable state; when the third residual is greater than the third residual threshold and the second impedance data is greater than the theoretical second impedance data, the data change trend of the second impedance data is determined to be an increasing state; when the third residual is greater than the third residual threshold and the second impedance data is less than the theoretical second impedance data, the data change trend of the second impedance data is determined to be a decreasing state.

8. The method for handling a fuel cell system failure according to claim 5, characterized in that: The determining the data change trend of the first impedance data according to the fourth residual includes: Acquire a preset fourth residual threshold corresponding to the third impedance data based on fourth preset mapping information; the fourth preset mapping information represents a mapping relationship between the third impedance data and the fourth residual threshold; When the fourth residual is less than or equal to the fourth residual threshold, the data change trend of the third impedance data is determined to be a stable state; when the fourth residual is greater than the fourth residual threshold and the third impedance data is greater than the theoretical third impedance data, the data change trend of the third impedance data is determined to be an increasing state; when the fourth residual is greater than the fourth residual threshold and the third impedance data is less than the theoretical third impedance data, the data change trend of the third impedance data is determined to be a decreasing state.

9. The method for handling a fuel cell system failure according to claim 8, characterized in that: The performing fault diagnosis according to the data change trend to obtain the fault diagnosis result of the fuel cell includes: Under the condition that a first preset condition is met, determining that the fault diagnosis result of the fuel cell is a membrane dry fault; the first preset condition is that the first impedance data is in the increasing state, the second impedance data is in the stable state, and the third impedance data is in the stable state; In the case where a second preset condition is met, determining that the fault diagnosis result of the fuel cell is a flooding fault; the second preset condition is that the first impedance data is in the decreasing state, the second impedance data is in the stable state, and the third impedance data is in the increasing state; When a third preset condition is met, it is determined that the fault diagnosis result of the fuel cell is an air starvation fault; the third preset condition is that the first impedance data is in the decreasing state, the second impedance data is in the increasing state, and the third impedance data is in the increasing state.

10. The method for handling a fuel cell system failure according to claim 9, characterized in that: After performing fault diagnosis according to the data change trend to obtain the fault diagnosis result of the fuel cell, the method further includes: Based on the fault diagnosis results of the fuel cell, executing recovery strategies corresponding to the fault diagnosis results; The executing of the recovery strategies corresponding to the respective fault diagnosis results based on the fault diagnosis results of the fuel cell comprises: When the fault diagnosis result of the fuel cell is the membrane dry fault, executing a membrane dry recovery strategy; When the fault diagnosis result of the fuel cell is the flooding fault, executing a flooding recovery strategy; In a case where the fault diagnosis result of the fuel cell is the air starvation fault, an air starvation recovery strategy is executed.

Images