Fault diagnosis method and device of fuel cell, electronic equipment and program product

Abstract

The invention relates to a fault diagnosis method and device for a fuel cell, electronic equipment and a program product, and the method comprises the steps: determining the operation time of the fuel cell, inputting the operation time into a preset average monomer voltage self-adaptive model, a preset monomer voltage standard deviation self-adaptive model and a preset impedance self-adaptive model to obtain an average monomer voltage reference value, a monomer voltage standard deviation reference value, a high-frequency impedance reference value and an intermediate-frequency impedance reference value; calculating a first difference value between the actual average monomer voltage and the average monomer voltage reference value, a second difference value between the actual monomer voltage standard difference value and the monomer voltage standard difference reference value, a third difference value between the actual high-frequency impedance and the high-frequency impedance reference value, and a fourth difference value between the actual intermediate-frequency impedance and the intermediate-frequency impedance reference value; a fifth difference value between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value; and diagnosing the current state of the fuel cell based on the first difference value, the second difference value, the third difference value, the fourth difference value and the fifth difference value.

Description

Technical Field

[0001] The present application relates to the technical field of fuel cell diagnosis, and in particular to a fuel cell fault diagnosis method, device, electronic equipment and program product. Background Art

[0002] The durability of fuel cells is an important indicator that affects the commercial application of fuel cells. Under real vehicle dynamic conditions, fuel cells are easily affected by start-stop, load changes, and improper strategies, resulting in failure and aging. Fuel cell internal failures are difficult to observe and diagnose directly through sensors. At the same time, the internal state of fuel cells changes due to the aging of the stack and components, which increases the difficulty of fault diagnosis.

[0003] Most existing methods achieve online diagnosis based on diagnostic quantities such as fuel cell voltage and impedance, but do not consider changes in the internal state of the fuel cell. The diagnostic accuracy will decrease after the vehicle has been running for a long time, further affecting the vehicle control decision. At the same time, due to the influence of the computing power of the vehicle controller, it is difficult to integrate complex adaptive algorithms for diagnosis. Summary of the invention

[0004] The present application provides a fuel cell fault diagnosis method, device, electronic device and program product to solve the problem that most existing methods realize online diagnosis based on diagnostic quantities such as fuel cell voltage and impedance, but do not consider the changes caused by internal state changes when formulating strategies and diagnostic boundaries. As the vehicle runs for a long time, the accuracy of the diagnostic strategy decreases, further affecting the control decision of the vehicle.

[0005] In a first aspect, an embodiment of the present application provides a fuel cell fault diagnosis method, comprising the following steps: collecting an actual average cell voltage, an actual cell voltage standard deviation, an actual high-frequency impedance, an actual medium-frequency impedance, and an actual anode inlet and outlet pressure difference of the fuel cell; determining the operation time of the fuel cell, and inputting the operation time into a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model, and a preset impedance adaptive model to obtain an average cell voltage reference value, a cell voltage standard deviation reference value, a high-frequency impedance reference value, and an medium-frequency impedance reference value; calculating a first difference between the actual average cell voltage and the average cell voltage reference value, a second difference between the actual cell voltage standard deviation value and the cell voltage standard deviation reference value, a third difference between the actual high-frequency impedance and the high-frequency impedance reference value, a fourth difference between the actual medium-frequency impedance and the medium-frequency impedance reference value, and a fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value; and diagnosing the current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference, and the fifth difference.

[0006] Optionally, the diagnosis of the current state of the fuel cell stack based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference includes: if the second difference is greater than the first single cell voltage standard deviation mild threshold and less than the first single cell voltage standard deviation severe threshold or the fourth difference is greater than the first intermediate frequency impedance mild threshold and less than the first intermediate frequency impedance severe threshold, then when the first difference is greater than the first average single cell voltage mild threshold and the third difference is greater than the first high frequency impedance mild threshold and less than the first high frequency impedance severe threshold, it is determined that the current state is a first membrane dry state; if the fourth difference is greater than the first intermediate frequency impedance severe threshold or the second difference is greater than the first single cell voltage standard deviation severe threshold, then when the first difference is greater than the first average single cell voltage severe threshold and the third difference is greater than the first high frequency impedance severe threshold, it is determined that the current state is a second membrane dry state. , wherein the membrane dryness degree of the first membrane dry state is lower than the membrane dryness degree of the second membrane dry state; if the fourth difference is greater than the second intermediate frequency impedance mild threshold and less than the second intermediate frequency impedance severe threshold or the second difference is greater than the second cell voltage standard deviation mild threshold and less than the second cell voltage standard deviation severe threshold, then when the first difference is greater than the second average cell voltage mild threshold and the fifth difference is greater than the anode pressure difference mild threshold and less than the anode pressure difference severe threshold, it is determined that the current state is the first flooded state; if the fourth difference is greater than the second intermediate frequency impedance severe threshold or the second difference is greater than the second cell voltage standard deviation severe threshold, then when the first difference is greater than the second average cell voltage severe threshold and the fifth difference is greater than the anode pressure difference severe threshold, it is determined that the current state is the second flooded state, wherein the flooding degree of the first flooded state is lower than the flooding degree of the second flooded state.

[0007] Optionally, after diagnosing the current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference, the method includes: based on a preset time interval, obtaining historical operating time data, historical cell voltage data, historical cell voltage standard deviation data, historical high-frequency impedance data, and historical medium-frequency impedance data, and recalibrating model parameters of the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model, and the preset impedance adaptive model, so as to utilize the updated average cell voltage adaptive model, the cell voltage standard deviation adaptive model, and the impedance adaptive model to perform fuel cell fault diagnosis.

[0008] Optionally, the preset cell voltage standard deviation adaptive model is:

[0009] σ r =σ0+αt

[0010]

[0011] Among them, σ r is the standard deviation of the fuel cell single voltage reference state, σ0 is the initial consistency of the fuel cell, The fuel cell passes through T d time is the standard deviation of the cell voltage after the test, α is the fitting coefficient of the cell voltage adaptive model, and t is the cumulative operating time of the fuel cell.

[0012] Optionally, the preset average cell voltage adaptive model is:

[0013]

[0014] in, is the average voltage reference state of the fuel cell unit, V nernst is the Nernst voltage, V act is the activation loss voltage, V ohm is the aging voltage of ohmic loss, V conc is the concentration loss aging voltage value.

[0015] Optionally, the preset impedance adaptive model is:

[0016]

[0017] in, is the high frequency impedance, is the intermediate frequency impedance, Re is the real part of the impedance spectrum, is the impedance value at the high frequency point of impedance, is the impedance value at the mid-frequency point.

[0018] In a second aspect, an embodiment of the present application provides a fuel cell fault diagnosis device, comprising: an acquisition module, used to collect the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual medium-frequency impedance and the actual anode inlet and outlet pressure difference of the fuel cell; an acquisition module, used to determine the operation time of the fuel cell, and input the operation time into a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model and a preset impedance adaptive model to obtain an average cell voltage reference value, a cell voltage standard deviation reference value, a high-frequency impedance reference value and an medium-frequency impedance reference value; a calculation module, used to calculate a first difference between the actual average cell voltage and the average cell voltage reference value, a second difference between the actual cell voltage standard deviation and the cell voltage standard deviation reference value, a third difference between the actual high-frequency impedance and the high-frequency impedance reference value, a fourth difference between the actual medium-frequency impedance and the medium-frequency impedance reference value, and a fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value; a diagnosis module, used to diagnose the current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference.

[0019] Optionally, the diagnostic module is also used for: if the second difference is greater than the first monomer voltage standard deviation mild threshold and less than the first monomer voltage standard deviation severe threshold or the fourth difference is greater than the first intermediate frequency impedance mild threshold and less than the first intermediate frequency impedance severe threshold, then when the first difference is greater than the first average monomer voltage mild threshold and the third difference is greater than the first high frequency impedance mild threshold and less than the first high frequency impedance severe threshold, determining that the current state is a first membrane dry state; if the fourth difference is greater than the first intermediate frequency impedance severe threshold or the second difference is greater than the first monomer voltage standard deviation severe threshold, then when the first difference is greater than the first average monomer voltage severe threshold and the third difference is greater than the first high frequency impedance severe threshold, determining that the current state is a second membrane dry state, wherein the membrane dryness of the first membrane dry state is lower than that of the second membrane dry state. The degree of membrane dryness in the membrane dry state; if the fourth difference is greater than the second intermediate frequency impedance mild threshold and less than the second intermediate frequency impedance severe threshold or the second difference is greater than the second monomer voltage standard deviation mild threshold and less than the second monomer voltage standard deviation severe threshold, then when the first difference is greater than the second average monomer voltage mild threshold and the fifth difference is greater than the anode pressure difference mild threshold and less than the anode pressure difference severe threshold, it is determined that the current state is the first flooded state; if the fourth difference is greater than the second intermediate frequency impedance severe threshold or the second difference is greater than the second monomer voltage standard deviation severe threshold, then when the first difference is greater than the second average monomer voltage severe threshold and the fifth difference is greater than the anode pressure difference severe threshold, it is determined that the current state is the second flooded state, wherein the flooding degree of the first flooded state is lower than the flooding degree of the second flooded state.

[0020] Optionally, after diagnosing the current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference, the diagnostic module is further used to: based on a preset time interval, obtain historical operating time data, historical cell voltage data, historical cell voltage standard deviation data, historical high-frequency impedance data, and historical medium-frequency impedance data, and recalibrate model parameters of the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model, and the preset impedance adaptive model, so as to use the updated average cell voltage adaptive model, the cell voltage standard deviation adaptive model, and the impedance adaptive model to perform fuel cell fault diagnosis.

[0021] Optionally, the preset cell voltage standard deviation adaptive model is:

[0022]

[0023] Among them, σ r is the standard deviation of the fuel cell single voltage reference state, σ0 is the initial consistency of the fuel cell, The fuel cell passes through T d time is the standard deviation of the cell voltage after the test, α is the fitting coefficient of the cell voltage adaptive model, and t is the cumulative operating time of the fuel cell.

[0024] Optionally, the preset average cell voltage adaptive model is:

[0025]

[0026] in, is the average voltage reference state of the fuel cell unit, V nernst is the Nernst voltage, V act is the activation loss voltage, V ohm is the aging voltage of ohmic loss, V conc is the concentration loss aging voltage value.

[0027] Optionally, the preset impedance adaptive model is:

[0028]

[0029] in, is the high frequency impedance, is the intermediate frequency impedance, Re is the real part of the impedance spectrum, is the impedance value at the high frequency point of impedance, is the impedance value at the mid-frequency point.

[0030] A third aspect of the present application provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the fuel cell fault diagnosis method as described in the above embodiment.

[0031] A fourth aspect of the present application provides a computer program product having a computer program stored thereon, the program being executed by a processor to implement the fuel cell fault diagnosis method as described in the above embodiment.

[0032] In the above embodiment, the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual medium-frequency impedance and the actual anode inlet and outlet pressure difference of the fuel cell are collected to determine the operation time of the fuel cell, and the operation time is input into a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model and a preset impedance adaptive model to obtain an average cell voltage reference value, a cell voltage standard deviation reference value, a high-frequency impedance reference value and a medium-frequency impedance reference value, and a first difference between the actual average cell voltage and the average cell voltage reference value, a second difference between the actual cell voltage standard deviation and the cell voltage standard deviation reference value, a third difference between the actual high-frequency impedance and the high-frequency impedance reference value, a fourth difference between the actual medium-frequency impedance and the medium-frequency impedance reference value, and a fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value are calculated, and the current state of the fuel cell is diagnosed based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference. This solves the problem that most existing methods realize online diagnosis based on diagnostic quantities such as fuel cell voltage and impedance, but do not consider the changes caused by internal state changes when formulating strategies and diagnostic boundaries. As the vehicle runs for a long time, the accuracy of the diagnostic strategy decreases, further affecting the control decision of the vehicle. This effectively improves the accuracy of fault diagnosis under long-term operation of fuel cells. At the same time, combined with big data technology, the adaptive model parameter correction function is deployed in the cloud, and the adaptive model parameters are corrected based on the user's actual historical data to ensure the accuracy of the adaptive model and realize online monitoring of the vehicle and cloud.

[0033] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0035] Figure 1 A flowchart of a fuel cell fault diagnosis method provided according to an embodiment of the present application;

[0036] Figure 2is a flow chart of a fuel cell fault diagnosis method according to one embodiment of the present application;

[0037] Figure 3 is an exemplary diagram of a fuel cell fault diagnosis device according to an embodiment of the present application;

[0038] Figure 4 Schematic diagram of the structure of an electronic device according to an embodiment of the present application. Description of the drawings:

[0040] 10 - fuel cell fault diagnosis device; 100 - acquisition module; 200 - acquisition module; 300 - calculation module; 400 - diagnosis module; 401 - memory; 402 - processor and 403 - communication interface. DETAILED DESCRIPTION

[0041] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0042] The following describes the fuel cell fault diagnosis method, device, electronic device and program product of the embodiment of the present application with reference to the accompanying drawings. In view of the problem that most of the existing methods mentioned in the above background technology realize online diagnosis based on diagnostic quantities such as fuel cell voltage and impedance, but do not consider the changes caused by internal state changes when formulating strategies and diagnostic boundaries, and the accuracy of the diagnostic strategy decreases after the whole vehicle has been running for a long time, further affecting the control decision of the whole vehicle, the present application provides a fuel cell fault diagnosis method, in which the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual medium-frequency impedance and the actual anode inlet and outlet pressure difference of the fuel cell are collected to determine the operating time of the fuel cell, and the operating time is input into the preset average cell voltage adaptive model, the preset cell voltage standard deviation, the actual high-frequency impedance, the actual medium-frequency impedance and the actual anode inlet and outlet pressure difference. The body voltage standard deviation adaptive model and the preset impedance adaptive model obtain the average cell voltage reference value, the cell voltage standard deviation reference value, the high-frequency impedance reference value and the intermediate-frequency impedance reference value, and calculate the first difference between the actual average cell voltage and the average cell voltage reference value, the second difference between the actual cell voltage standard deviation value and the cell voltage standard deviation reference value, the third difference between the actual high-frequency impedance and the high-frequency impedance reference value, the fourth difference between the actual intermediate-frequency impedance and the intermediate-frequency impedance reference value, and the fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value. The current state of the fuel cell is diagnosed based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference. Thus, the existing methods are mostly based on fuel cell voltage, impedance and other diagnostic quantities to achieve online diagnosis, but the changes caused by the change of the internal state are not considered when formulating the strategy and the diagnostic boundary. The accuracy of the diagnostic strategy decreases after the vehicle runs for a long time, which further affects the control decision of the vehicle. The problem is effectively improved. The accuracy of fault diagnosis under long-term operation of the fuel cell is effectively improved. At the same time, combined with big data technology, the adaptive model parameter correction function is deployed in the cloud, and the adaptive model parameters are corrected based on the actual historical data of the user to ensure the accuracy of the adaptive model and realize the online monitoring of the vehicle-cloud integration.

[0043] Specifically, Figure 1 A schematic flow chart of a fuel cell fault diagnosis method provided in an embodiment of the present application.

[0044] like Figure 1 As shown, the fuel cell fault diagnosis method includes the following steps:

[0045] In step S101, the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual medium-frequency impedance and the actual anode inlet and outlet pressure difference of the fuel cell are collected.

[0046] Specifically, the actual average cell voltage of the fuel cell is obtained based on the fuel cell engine onboard sensor. Actual single cell voltage standard deviation σ t , Actual high frequency impedance Intermediate frequency impedance Actual anode inlet and outlet pressure difference

[0047] In step S102, the operating time of the fuel cell is determined, and the operating time is input into a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model, and a preset impedance adaptive model to obtain an average cell voltage reference value, a cell voltage standard deviation reference value, a high-frequency impedance reference value, and a medium-frequency impedance reference value.

[0048] Optionally, in some embodiments, the preset cell voltage standard deviation adaptive model is:

[0049]

[0050] Among them, σ r is the standard deviation of the fuel cell single voltage reference state, σ0 is the initial consistency of the fuel cell, The fuel cell passes through T d time is the standard deviation of the cell voltage after the test, α is the fitting coefficient of the cell voltage adaptive model, and t is the cumulative operating time of the fuel cell.

[0051] Optionally, in some embodiments, the preset average cell voltage adaptive model is:

[0052]

[0053] in, is the average voltage reference state of the fuel cell unit, V nernst is the Nernst voltage, V act is the activation loss voltage, V ohm is the aging voltage of ohmic loss, V conc is the concentration loss aging voltage value.

[0054] Optionally, in some embodiments, the preset impedance adaptive model is:

[0055]

[0056] in, is the high frequency impedance, is the intermediate frequency impedance, Re is the real part of the impedance spectrum, is the impedance value at the high frequency point of impedance, is the impedance value at the mid-frequency point.

[0057] Specifically, the present application implements the establishment of an adaptive diagnostic model based on fuel cell aging test data, including a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model, and a preset impedance adaptive model.

[0058] First, the preset average cell voltage adaptive model is used to determine the average cell voltage reference state of the fuel cell. It can be expressed as formula (1):

[0059]

[0060] Among them, the activation loss model can be expressed as formula (2) and (3):

[0061]

[0062] Where b is the reaction constant calibrated based on the measured data of the fuel cell, is the initial effective reaction area of ​​the catalyst, b ECSA is the attenuation trend coefficient, and t is the cumulative operating time of the fuel cell.

[0063] The ohmic loss of a fuel cell is caused by the resistance during the directional transport of charged particles. The aging model of the ohmic loss can be expressed as formula (3):

[0064] V ohm =I·R0(1+b ohm ·t) (3)

[0065] Where I is the fuel cell current, R0 is the initial internal resistance, b ohm is the aging coefficient of internal resistance.

[0066] The concentration loss aging model of the fuel cell can be expressed as formula (4):

[0067]

[0068] Where R is the gas constant, F is the Faraday constant, T is the stack operating temperature, i is the current density, is the initial limiting current density of the fuel cell, b conc is the limiting current density aging coefficient, so the calibration parameter of the aging model is [R0b ohm b conc bb ESCA 】, b is the activation loss voltage fitting coefficient.

[0069] Furthermore, the consistency of fuel cell monomers changes approximately linearly with the aging of the fuel cell stack, so the preset monomer voltage standard deviation adaptive model is:

[0070]

[0071] The preset impedance adaptive model is based on the Fouquet model, where the fuel cell impedance can be expressed as:

[0072]

[0073] Where j is the imaginary part, ω is the angular frequency, Q and α are the capacitance and CPE component parameters respectively, and R d is the reactant diffusion resistance, D is the material diffusion coefficient, R1 represents the ohmic resistance in the circuit, τ d is the time constant.

[0074] Ohmic resistance R1, charge transfer resistance R2, reactant diffusion resistance R d , capacitance coefficient Q are related to the thickness of the membrane and the catalyst reaction area, so the parameter relationship of each component is established, and the formula fitting parameters in the initial impedance adaptive model [a1b1a2 b2 a d b d a Q b Q ατ d 】, and thus obtain the preset impedance adaptive model:

[0075]

[0076] In step S103, a first difference between the actual average cell voltage and the average cell voltage reference value, a second difference between the actual cell voltage standard deviation value and the cell voltage standard deviation reference value, a third difference between the actual high-frequency impedance and the high-frequency impedance reference value, a fourth difference between the actual intermediate-frequency impedance and the intermediate-frequency impedance reference value, and a fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value are calculated.

[0077] The reference value of the anode inlet and outlet pressure difference is the difference between the anode inlet pressure and the anode outlet pressure when the fuel cell is in a normal state (i.e., no flooding, membrane drying or other faults occur).

[0078] Specifically, the embodiment of the present application performs three groups of tests of the fuel cell reference state, the membrane dry state, and the flooded state under the initial state of the fuel cell engine (the stack is activated), and calculates the first difference between the actual average cell voltage and the average cell voltage reference value, the second difference between the actual cell voltage standard deviation and the cell voltage standard deviation reference value, the third difference between the actual high-frequency impedance and the high-frequency impedance reference value, the fourth difference between the actual intermediate frequency impedance and the intermediate frequency impedance reference value, the fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value, and the calculation formulas of the first difference, the second difference, the third difference, the fourth difference, and the fifth difference are as follows:

[0079]

[0080] Where, ΔV mean , Δσ, ΔR H , ΔR M With ΔPan-diff are the first difference, the second difference, the third difference, the fourth difference and the fifth difference respectively, σ t , and They are the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual intermediate-frequency impedance and the actual anode inlet and outlet pressure difference, σ r , and They respectively represent the average cell voltage reference value, the cell voltage standard deviation reference value, the high-frequency impedance reference value, the medium-frequency impedance reference value and the anode inlet and outlet pressure difference reference value.

[0081] In step S104 , the current state of the fuel cell is diagnosed based on the first difference, the second difference, the third difference, the fourth difference, and the fifth difference.

[0082] Optionally, in some embodiments, the current state of the fuel cell stack is diagnosed based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference, including: if the second difference is greater than the first single cell voltage standard deviation mild threshold and less than the first single cell voltage standard deviation severe threshold or the fourth difference is greater than the first intermediate frequency impedance mild threshold and less than the first intermediate frequency impedance severe threshold, then when the first difference is greater than the first average single cell voltage mild threshold and the third difference is greater than the first high frequency impedance mild threshold and less than the first high frequency impedance severe threshold, it is determined that the current state is the first membrane dry state; if the fourth difference is greater than the first intermediate frequency impedance severe threshold or the second difference is greater than the first single cell voltage standard deviation severe threshold, then when the first difference is greater than the first average single cell voltage severe threshold and the third difference is greater than the first high frequency impedance severe threshold, it is determined that the current state is the second membrane dry state. state, wherein the membrane dryness of the first membrane dry state is lower than the membrane dryness of the second membrane dry state; if the fourth difference is greater than the second intermediate frequency impedance mild threshold and less than the second intermediate frequency impedance severe threshold or the second difference is greater than the second monomer voltage standard deviation mild threshold and less than the second monomer voltage standard deviation severe threshold, then when the first difference is greater than the second average monomer voltage mild threshold and the fifth difference is greater than the anode pressure difference mild threshold and less than the anode pressure difference severe threshold, it is determined that the current state is the first flooded state; if the fourth difference is greater than the second intermediate frequency impedance severe threshold or the second difference is greater than the second monomer voltage standard deviation severe threshold, then when the first difference is greater than the second average monomer voltage severe threshold and the fifth difference is greater than the anode pressure difference severe threshold, it is determined that the current state is the second flooded state, wherein the flooding degree of the first flooded state is lower than the flooding degree of the second flooded state.

[0083] Specifically, the process of determining whether the fuel cell is in a membrane dry fault state or a flooded fault state is as follows:

[0084] like and and It is determined that the fuel cell is in the first membrane dry state, that is, the slightly membrane dry state;

[0085] like and and It is determined that the fuel cell is in the second membrane dry state, that is, the severe membrane dry state;

[0086] like and and It is determined that the fuel cell is in the first water flooding state, that is, the light water flooding state;

[0087] like and and It is determined that the fuel cell is in the second flooding state, ie, the severe flooding state.

[0088] in, They are respectively the first average single cell voltage mild threshold, the first average single cell voltage severe threshold, the first intermediate frequency impedance mild threshold, the first intermediate frequency impedance severe threshold, the first single cell voltage standard deviation mild threshold, the first single cell voltage standard deviation severe threshold, the first high frequency impedance mild threshold, and the first high frequency impedance severe threshold in membrane dryness diagnosis. They are respectively the second average cell voltage mild threshold, the second average cell voltage severe threshold, the second intermediate frequency impedance mild threshold, the second intermediate frequency impedance severe threshold, the second cell voltage standard deviation mild threshold, the second cell voltage standard deviation severe threshold, the anode pressure difference mild threshold, and the anode pressure difference severe threshold in flooding fault diagnosis.

[0089] Optionally, in some embodiments, after diagnosing the current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference, it includes: based on a preset time interval, obtaining historical operating time data, historical cell voltage data, historical cell voltage standard deviation data, historical high-frequency impedance data, historical medium-frequency impedance data, and recalibrating model parameters of a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model and a preset impedance adaptive model, so as to utilize the updated average cell voltage adaptive model, the cell voltage standard deviation adaptive model and the impedance adaptive model to perform fuel cell fault diagnosis.

[0090] Specifically, the cloud sends a message every preset time interval T L The parameters of the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model and the preset impedance adaptive model are recalibrated based on the historical operation time data t, the historical cell voltage data V mean, historical single-cell voltage standard deviation data σ, historical high-frequency impedance data R H 、Historical medium frequency impedance data R M Recalibrate the adaptive model parameters, including [R0 b ohm b conc bb ECSA 】, α, and

a1b1 a2 b2a d b d a Q b Q α τ d

R0 b ohm b conc bb ECSA

【a1 b1 a2 b2 a d b d a Q b Q ατ d The adaptive model parameters are deployed to the vehicle-side model, and the vehicle performs fuel cell fault diagnosis based on the updated average cell voltage adaptive model, cell voltage standard deviation adaptive model and impedance adaptive model.

[0091] In order to enable those skilled in the art to further understand the adaptive fault diagnosis method of the embodiment of the present application, the following is described in detail in conjunction with specific embodiments. Figure 2 shown.

[0092] (1) Offline calibration phase: the diagnostic logic and diagnostic threshold are determined through a pre-performed fault injection test;

[0093] (2) Based on the fuel cell stack aging data, the average cell voltage adaptive model, the cell voltage standard deviation adaptive model and the impedance adaptive model are established to determine the calibration parameters [R0 b ohm b conc bb ECSA 】, α, and

a1 b1 a2 b2 a d b d a Q b Q ατ d

[0094] (3) Considering the computing power limit of the vehicle-side controller, the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model and the preset impedance adaptive model are deployed to the vehicle-side controller, and the parameter calibration algorithms of the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model and the preset impedance adaptive model are deployed to the cloud;

[0095] (4) During the vehicle operation phase, the real-time average cell voltage of the fuel cell is obtained based on the fuel cell engine onboard sensor Single cell voltage consistencyσ t , high frequency impedance IF impedance Anode inlet and outlet pressure difference

[0096] (5) Every T s The effective operation time of the fuel cell stack is calculated, and the operation time is input into the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model and the preset impedance adaptive model to obtain the calculated average cell voltage reference value under the time. Single cell voltage standard deviation reference value σ r , high frequency impedance reference value Intermediate frequency impedance reference value

[0097] (6) Calculate the first difference ΔV based on the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual intermediate-frequency impedance and the actual anode inlet and outlet pressure difference obtained by monitoring. mean , the second difference Δσ, the third difference ΔR H , the fourth difference ΔR M and the fifth difference ΔP an-diff ;

[0098] (7) The first difference ΔV mean , the second difference Δσ, the third difference ΔR H , the fourth difference ΔR M and the fifth difference ΔP an-diff Input into a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model and a preset impedance adaptive model, and judge the fuel cell stack state according to the diagnostic logic of the diagnostic model;

[0099] (8) The fuel cell engine makes decisions based on the diagnostic results;

[0100] (9) The vehicle uploads the stored historical data to the cloud;

[0101] (10) Every T L The adaptive model parameters are recalibrated based on the operating time t and single cell voltage V in the historical data. mean , single cell voltage consistency σ, high frequency impedance R H 、Intermediate frequency impedance R M Recalibrate the adaptive model parameters, including [R0 b ohm bconc bb ECSA 】, α, and

a1b1 a2 b2 a d b d a Q b Q ατ d

[0102] (11) The updated [R0 b ohm b conc bb ECSA 】, α, and 【a1b1 a2 b2 a d b d a Q b Q ατ d Adaptive model parameters are deployed to the vehicle-side model:

[0103] (12) The entire vehicle performs fault diagnosis based on the updated adaptive model.

[0104] According to the fuel cell fault diagnosis method proposed in the embodiment of the present application, the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual medium-frequency impedance and the actual anode inlet and outlet pressure difference of the fuel cell are collected to determine the operation time of the fuel cell, and the operation time is input into a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model and a preset impedance adaptive model to obtain an average cell voltage reference value, a cell voltage standard deviation reference value, a high-frequency impedance reference value and a medium-frequency impedance reference value, and a first difference between the actual average cell voltage and the average cell voltage reference value, a second difference between the actual cell voltage standard deviation value and the cell voltage standard deviation reference value, a third difference between the actual high-frequency impedance and the high-frequency impedance reference value, a fourth difference between the actual medium-frequency impedance and the medium-frequency impedance reference value, and a fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value are calculated, and the current state of the fuel cell is diagnosed based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference. This solves the problem that most existing methods realize online diagnosis based on diagnostic quantities such as fuel cell voltage and impedance, but do not consider the changes caused by internal state changes when formulating strategies and diagnostic boundaries. As the vehicle runs for a long time, the accuracy of the diagnostic strategy decreases, further affecting the control decision of the vehicle. This effectively improves the accuracy of fault diagnosis under long-term operation of fuel cells. At the same time, combined with big data technology, the adaptive model parameter correction function is deployed in the cloud, and the adaptive model parameters are corrected based on the user's actual historical data to ensure the accuracy of the adaptive model and realize online monitoring of the vehicle and cloud.

[0105] Next, a fuel cell fault diagnosis device according to an embodiment of the present application will be described with reference to the accompanying drawings.

[0106] Figure 3 It is a block diagram of a fuel cell fault diagnosis device according to an embodiment of the present application.

[0107] like Figure 3 As shown, the fuel cell fault diagnosis device 10 includes: a collection module 100 , an acquisition module 200 , a calculation module 300 and a diagnosis module 400 .

[0108] Among them, the acquisition module 100 is used to collect the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual medium-frequency impedance and the actual anode inlet and outlet pressure difference of the fuel cell; the acquisition module 200 is used to determine the operation time of the fuel cell, and input the operation time into the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model and the preset impedance adaptive model to obtain the average cell voltage reference value, the cell voltage standard deviation reference value, the high-frequency impedance reference value and the medium-frequency impedance reference value; the calculation module 300 is used to calculate the first difference between the actual average cell voltage and the average cell voltage reference value, the second difference between the actual cell voltage standard deviation value and the cell voltage standard deviation reference value, the third difference between the actual high-frequency impedance and the high-frequency impedance reference value, the fourth difference between the actual medium-frequency impedance and the medium-frequency impedance reference value, and the fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value; the diagnosis module 400 is used to diagnose the current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference.

[0109] Optionally, in some embodiments, the diagnostic module 400 is further used for: if the second difference is greater than the first monomer voltage standard deviation mild threshold and less than the first monomer voltage standard deviation severe threshold or the fourth difference is greater than the first intermediate frequency impedance mild threshold and less than the first intermediate frequency impedance severe threshold, then when the first difference is greater than the first average monomer voltage mild threshold and the third difference is greater than the first high frequency impedance mild threshold and less than the first high frequency impedance severe threshold, it is determined that the current state is the first membrane dry state; if the fourth difference is greater than the first intermediate frequency impedance severe threshold or the second difference is greater than the first monomer voltage standard deviation severe threshold, then when the first difference is greater than the first average monomer voltage severe threshold and the third difference is greater than the first high frequency impedance severe threshold, it is determined that the current state is the second membrane dry state, wherein the membrane dry process of the first membrane dry state The degree of membrane dryness is lower than the second membrane dry state; if the fourth difference is greater than the second intermediate frequency impedance mild threshold and less than the second intermediate frequency impedance severe threshold or the second difference is greater than the second monomer voltage standard deviation mild threshold and less than the second monomer voltage standard deviation severe threshold, then when the first difference is greater than the second average monomer voltage mild threshold and the fifth difference is greater than the anode pressure difference mild threshold and less than the anode pressure difference severe threshold, it is determined that the current state is the first flooded state; if the fourth difference is greater than the second intermediate frequency impedance severe threshold or the second difference is greater than the second monomer voltage standard deviation severe threshold, then when the first difference is greater than the second average monomer voltage severe threshold and the fifth difference is greater than the anode pressure difference severe threshold, it is determined that the current state is the second flooded state, wherein the flooding degree of the first flooded state is lower than the flooding degree of the second flooded state.

[0110] Optionally, in some embodiments, after diagnosing the current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference, the diagnostic module 400 is further used to: based on a preset time interval, obtain historical operating time data, historical cell voltage data, historical cell voltage standard deviation data, historical high-frequency impedance data, historical medium-frequency impedance data, and recalibrate model parameters of a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model and a preset impedance adaptive model, so as to utilize the updated average cell voltage adaptive model, the cell voltage standard deviation adaptive model and the impedance adaptive model to perform fuel cell fault diagnosis.

[0111] Optionally, in some embodiments, the preset cell voltage standard deviation adaptive model is:

[0112]

[0113] Among them, σ r is the standard deviation of the fuel cell single voltage reference state, σ0 is the initial consistency of the fuel cell, The fuel cell passes through T dtime is the standard deviation of the cell voltage after the test, α is the fitting coefficient of the cell voltage adaptive model, and t is the cumulative operating time of the fuel cell.

[0114] Optionally, in some embodiments, the preset average cell voltage adaptive model is:

[0115]

[0116] in, is the average voltage reference state of the fuel cell unit, V nernst is the Nernst voltage, V act is the activation loss voltage, V ohm is the aging voltage of ohmic loss, V conc is the concentration loss aging voltage value.

[0117] Optionally, in some embodiments, the preset impedance adaptive model is:

[0118]

[0119] in, is the high frequency impedance, is the intermediate frequency impedance, Re is the real part of the impedance spectrum, is the impedance value at the high frequency point of impedance, is the impedance value at the mid-frequency point.

[0120] It should be noted that the above explanation of the fuel cell fault diagnosis method embodiment is also applicable to the fuel cell fault diagnosis device of this embodiment, and will not be repeated here.

[0121] According to the fuel cell fault diagnosis device proposed in the embodiment of the present application, the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual medium-frequency impedance and the actual anode inlet and outlet pressure difference of the fuel cell are collected to determine the operation time of the fuel cell, and the operation time is input into the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model and the preset impedance adaptive model to obtain the average cell voltage reference value, the cell voltage standard deviation reference value, the high-frequency impedance reference value and the medium-frequency impedance reference value, and a first difference between the actual average cell voltage and the average cell voltage reference value, a second difference between the actual cell voltage standard deviation value and the cell voltage standard deviation reference value, a third difference between the actual high-frequency impedance and the high-frequency impedance reference value, a fourth difference between the actual medium-frequency impedance and the medium-frequency impedance reference value, and a fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value are calculated, and the current state of the fuel cell is diagnosed based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference. This solves the problem that most existing methods realize online diagnosis based on diagnostic quantities such as fuel cell voltage and impedance, but do not consider the changes caused by internal state changes when formulating strategies and diagnostic boundaries. As the vehicle runs for a long time, the accuracy of the diagnostic strategy decreases, further affecting the control decision of the vehicle. This effectively improves the accuracy of fault diagnosis under long-term operation of fuel cells. At the same time, combined with big data technology, the adaptive model parameter correction function is deployed in the cloud, and the adaptive model parameters are corrected based on the user's actual historical data to ensure the accuracy of the adaptive model and realize online monitoring of the vehicle and cloud.

[0122] Figure 4 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device may include:

[0123] Memory 401 , processor 402 , and a computer program stored in the memory 401 and executable on the processor 402 .

[0124] When the processor 402 executes the program, the fuel cell fault diagnosis method provided in the above embodiment is implemented.

[0125] Furthermore, the electronic device further comprises:

[0126] The communication interface 403 is used for communication between the memory 401 and the processor 402 .

[0127] The memory 401 is used to store computer programs that can be executed on the processor 402 .

[0128] The memory 401 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory.

[0129] If the memory 401, the processor 402 and the communication interface 403 are implemented independently, the communication interface 403, the memory 401 and the processor 402 can be connected to each other through a bus and communicate with each other. The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 4 Only one thick line is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0130] Optionally, in a specific implementation, if the memory 401, the processor 402 and the communication interface 403 are integrated on a chip, the memory 401, the processor 402 and the communication interface 403 can communicate with each other through an internal interface.

[0131] The processor 402 may be a central processing unit (CPU), or an application specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of the present application.

[0132] The embodiment of the present application also provides a computer program product, on which a computer program is stored, and when the program is executed by a processor, the above-mentioned fuel cell fault diagnosis method is implemented.

[0133] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or N embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0134] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include at least one of the features. In the description of this application, "N" means at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0135] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0136] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer program product for use with an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purposes of this specification, a "computer program product" can be any device that can contain, store, communicate, propagate or transmit a program for use with an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer program products (a non-exhaustive list) include the following: an electrical connection with one or N wirings (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). Furthermore, the computer program product may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example by optically scanning the paper or other medium and then editing, interpreting or, if necessary, processing in another suitable manner, and then storing it in a computer memory.

[0137] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiment, the N steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0138] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer program product, which, when executed, includes one or a combination of the steps of the method embodiment.

[0139] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer program product.

[0140] The computer program product mentioned above may be a read-only memory, a disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A fuel cell fault diagnosis method, characterized in that: The following steps are involved: Collect the actual average cell voltage, actual cell voltage standard deviation, actual high-frequency impedance, actual intermediate-frequency impedance and actual anode inlet and outlet pressure difference of the fuel cell; Determine the operation time of the fuel cell, and input the operation time into a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model, and a preset impedance adaptive model to obtain an average cell voltage reference value, a cell voltage standard deviation reference value, a high frequency impedance reference value, and a medium frequency impedance reference value; Calculate a first difference between the actual average cell voltage and the average cell voltage reference value, a second difference between the actual cell voltage standard deviation and the cell voltage standard deviation reference value, a third difference between the actual high-frequency impedance and the high-frequency impedance reference value, a fourth difference between the actual intermediate-frequency impedance and the intermediate-frequency impedance reference value, and a fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value; A current state of the fuel cell is diagnosed based on the first difference, the second difference, the third difference, the fourth difference, and the fifth difference.

2. The method according to claim 1, characterized in that The diagnosing the current state of the fuel cell stack based on the first difference, the second difference, the third difference, the fourth difference and the fifth difference includes: If the second difference is greater than the first monomer voltage standard deviation mild threshold and less than the first monomer voltage standard deviation severe threshold or the fourth difference is greater than the first intermediate frequency impedance mild threshold and less than the first intermediate frequency impedance severe threshold, then when the first difference is greater than the first average monomer voltage mild threshold and the third difference is greater than the first high frequency impedance mild threshold and less than the first high frequency impedance severe threshold, it is determined that the current state is the first membrane dry state; If the fourth difference is greater than the first intermediate frequency impedance severe threshold or the second difference is greater than the first monomer voltage standard deviation severe threshold, then when the first difference is greater than the first average monomer voltage severe threshold and the third difference is greater than the first high frequency impedance severe threshold, it is determined that the current state is a second membrane dry state, wherein the membrane dryness of the first membrane dry state is lower than the membrane dryness of the second membrane dry state; If the fourth difference is greater than the second intermediate frequency impedance mild threshold and less than the second intermediate frequency impedance severe threshold or the second difference is greater than the second cell voltage standard deviation mild threshold and less than the second cell voltage standard deviation severe threshold, then when the first difference is greater than the second average cell voltage mild threshold and the fifth difference is greater than the anode pressure difference mild threshold and less than the anode pressure difference severe threshold, it is determined that the current state is the first flooding state; If the fourth difference is greater than the second intermediate frequency impedance severe threshold or the second difference is greater than the second cell voltage standard deviation severe threshold, then when the first difference is greater than the second average cell voltage severe threshold and the fifth difference is greater than the anode voltage difference severe threshold, it is determined that the current state is a second flooding state, wherein the flooding degree of the first flooding state is lower than the flooding degree of the second flooding state.

3. The method according to claim 1, characterized in that After diagnosing the current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference, and the fifth difference, the method further comprises: Based on a preset time interval, historical operating time data, historical cell voltage data, historical cell voltage standard deviation data, historical high-frequency impedance data, and historical medium-frequency impedance data are obtained, and model parameters of the preset average cell voltage adaptive model, the preset cell voltage standard deviation adaptive model, and the preset impedance adaptive model are recalibrated to utilize the updated average cell voltage adaptive model, the cell voltage standard deviation adaptive model, and the impedance adaptive model to perform fuel cell fault diagnosis.

4. The method according to claim 1, characterized in that: The preset single cell voltage standard deviation adaptive model is: Among them, σ r is the standard deviation of the fuel cell single voltage reference state, σ0 is the initial consistency of the fuel cell, The fuel cell passes through T d time is the standard deviation of the cell voltage after the test, α is the fitting coefficient of the cell voltage adaptive model, and t is the cumulative operating time of the fuel cell.

5. The method according to claim 1, characterized in that The preset average cell voltage adaptive model is: in, is the average voltage reference state of the fuel cell unit, V nernst is the Nernst voltage, V act is the activation loss voltage, V ohm is the aging voltage of ohmic loss, V conc is the concentration loss aging voltage value.

6. The method according to claim 1, characterized in that The preset impedance adaptive model is: in, is the high frequency impedance, is the intermediate frequency impedance, Re is the real part of the impedance spectrum, is the impedance value at the high frequency point of impedance, is the impedance value at the mid-frequency point.

7. A fuel cell fault diagnosis device, characterized in that: include: A collection module is used to collect the actual average cell voltage, the actual cell voltage standard deviation, the actual high-frequency impedance, the actual intermediate-frequency impedance and the actual anode inlet and outlet pressure difference of the fuel cell; An acquisition module, used for determining the operation time of the fuel cell, and inputting the operation time into a preset average cell voltage adaptive model, a preset cell voltage standard deviation adaptive model and a preset impedance adaptive model to obtain an average cell voltage reference value, a cell voltage standard deviation reference value, a high frequency impedance reference value and a medium frequency impedance reference value; a calculation module, configured to calculate a first difference between the actual average cell voltage and the average cell voltage reference value, a second difference between the actual cell voltage standard deviation value and the cell voltage standard deviation reference value, a third difference between the actual high-frequency impedance and the high-frequency impedance reference value, a fourth difference between the actual intermediate-frequency impedance and the intermediate-frequency impedance reference value, and a fifth difference between the actual anode inlet and outlet pressure difference and the anode inlet and outlet pressure difference reference value; A diagnosis module is configured to diagnose a current state of the fuel cell based on the first difference, the second difference, the third difference, the fourth difference, and the fifth difference.

8. The device according to claim 7, characterized in that The diagnostic module is further used for: If the second difference is greater than the first monomer voltage standard deviation mild threshold and less than the first monomer voltage standard deviation severe threshold or the fourth difference is greater than the first intermediate frequency impedance mild threshold and less than the first intermediate frequency impedance severe threshold, then when the first difference is greater than the first average monomer voltage mild threshold and the third difference is greater than the first high frequency impedance mild threshold and less than the first high frequency impedance severe threshold, it is determined that the current state is the first membrane dry state; If the fourth difference is greater than the first intermediate frequency impedance severe threshold or the second difference is greater than the first monomer voltage standard deviation severe threshold, then when the first difference is greater than the first average monomer voltage severe threshold and the third difference is greater than the first high frequency impedance severe threshold, it is determined that the current state is a second membrane dry state, wherein the membrane dryness of the first membrane dry state is lower than the membrane dryness of the second membrane dry state; If the fourth difference is greater than the second intermediate frequency impedance mild threshold and less than the second intermediate frequency impedance severe threshold or the second difference is greater than the second cell voltage standard deviation mild threshold and less than the second cell voltage standard deviation severe threshold, then when the first difference is greater than the second average cell voltage mild threshold and the fifth difference is greater than the anode pressure difference mild threshold and less than the anode pressure difference severe threshold, it is determined that the current state is the first flooding state; If the fourth difference is greater than the second intermediate frequency impedance severe threshold or the second difference is greater than the second cell voltage standard deviation severe threshold, then when the first difference is greater than the second average cell voltage severe threshold and the fifth difference is greater than the anode voltage difference severe threshold, it is determined that the current state is a second flooding state, wherein the flooding degree of the first flooding state is lower than the flooding degree of the second flooding state.

9. An electronic device, characterized in that: The invention comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the fuel cell fault diagnosis method as claimed in any one of claims 1 to 6.

10. A computer program product, wherein the computer program product stores a computer program, characterized in that: When the program is executed by a processor, the fuel cell fault diagnosis method as described in any one of claims 1 to 6 is implemented.

Images