CN115453369A - A fuel cell consistency prediction and fault diagnosis method - Google Patents

Abstract

The invention belongs to the technical field of fuel cells, and particularly relates to a method for consistency prediction and fault diagnosis of a fuel cell, which comprises the following steps: firstly, presetting a fuel cell performance prediction model; and then, finding out operation parameters meeting the output performance characteristics of the fuel cell according to the fuel cell performance prediction model, using the operation parameters as standard output characteristic values of the fuel cell engine system, and comparing the real-time output characteristic values in the operation process of the fuel cell engine to perform fault diagnosis. The invention can solve the problems that the output performance of the fuel cell is predicted to be one-sided and the fault diagnosis is also one-sided in the prior art.

Description

A fuel cell consistency prediction and fault diagnosis method

technical field

The invention belongs to the technical field of fuel cells, in particular to a method for fuel cell consistency prediction and fault diagnosis.

Background technique

A fuel cell is a power generation device that directly converts the chemical energy present in fuel and oxidant into electrical energy. It is often used in fuel cell engine systems. Fuel and air are fed into the fuel cell separately to quickly generate electrical energy as a power drive for the engine. , and will not produce sulfides that pollute the air, so fuel cells have the advantages of high conversion efficiency, clean and pollution-free, and quick start at room temperature. Fuel cell engine systems have been widely used in aerospace, transportation and other fields.

In the process of the increasing development of fuel cell engine systems, the performance, life and cost of fuel cells have become the focus of increasing attention. The performance of fuel cells can directly affect the life and cost of fuel cells. This is because the operation of fuel cells is accompanied by With a series of complex multi-parameter highly coupled electrochemical reactions, the output performance of fuel cells will vary under different operating parameters. Therefore, when testing the performance of fuel cells, it is necessary to set appropriate operating parameters according to the characteristics of fuel cells. , so as to ensure the stable performance of the fuel cell. However, the process of finding suitable operating parameters is very complicated and requires a large number of experimental tests, and it is easy to cause irreversible fuel cell performance degradation under extreme conditions, thereby affecting the life of the fuel cell system and increasing maintenance. and cost of use.

In a large number of current studies, the fuel cell model is chosen to predict the output performance of the fuel cell under different operating parameters, and the fault diagnosis of the fuel cell system is performed based on the established fuel cell model, which avoids the waste of resources caused by the experimental test, but for the fuel cell Most of the research on the model focuses on the average voltage of a single-cell fuel cell or a multi-cell fuel cell stack, and the output performance of a single-cell fuel cell and the consistency between multiple fuel cells can affect the entire output of a fuel cell stack performance, and the factors affecting the output performance of fuel cells include steady-state characteristics and dynamic characteristics in addition to consistency, so only the average voltage between single-cell or multi-cell batteries or the consistency between cells is studied. The prediction of the output performance of the fuel cell is relatively one-sided, and the fault diagnosis of the fuel cell system is not comprehensive enough.

Contents of the invention

The technical problem to be solved by the present invention is to provide a method for fuel cell consistency prediction and fault diagnosis to solve the problems in the prior art by studying the average voltage between a single battery or multiple cells or the consistency between cells. To predict the output performance of the fuel cell, the prediction result is relatively one-sided, and at the same time, the fault diagnosis of the fuel cell system is not comprehensive enough.

The basic solution provided by the present invention: a method for fuel cell consistency prediction and fault diagnosis, including:

S1: preset fuel cell performance prediction model;

S2: Input the set different fuel cell operating parameters into the fuel cell performance prediction model, find the expected operating parameters that meet the fuel cell performance prediction model, and conduct fuel cell test experiments on the expected operating parameters to obtain fuel cell performance requirements that meet the requirements The standard output eigenvalues at different operating points of ;

S3: During the operation of the fuel cell engine system, the expected operating parameters are used as input, and the standard output eigenvalue is used as the standard, and the actual output eigenvalues and standard output eigenvalues of the fuel cell engine system at different operating points are calculated in real time according to the preset error The threshold value is compared to generate a comparison result;

S4: If the comparison result of the actual output of the fuel cell engine system and the characteristic value of the node pressure in the comparison result exceeds a preset error threshold, perform fault diagnosis.

The principle and advantages of the present invention are: the fuel cell performance prediction model preset in this application is used to establish a prediction model based on the characteristics of the fuel cell, and through the fuel cell performance prediction model, different operating parameters set are input, through Continuously input and verify to find the operating parameters that meet the expectations, and define them as expected operating parameters. There are more than one set of expected operating parameters. The expected operating parameters are used to characterize the operating parameters that can show the output performance of the fuel cell. Therefore, it is also necessary to The expected operating parameters are tested and tested to verify whether the expected operating parameters can also meet the output performance requirements of the fuel cell voltage in the actual application process, so that the expected operating parameters can not only meet the theoretical requirements, It can also meet the requirements of practical applications, and the output results of the determined expected operating parameters at different operating points in the fuel cell performance prediction model can be used as the standard output characteristic values of the fuel cell.

Then, during the operation of the fuel cell engine system, the standard output characteristic value is used as the standard, and the actual output characteristic value at different operating points of the fuel cell engine system is detected in real time, and compared with the standard output characteristic value. The error between the actual output eigenvalue at the current operating point and the standard output eigenvalue exceeds the preset error threshold, which means that there is a fault problem at the current fuel cell operating point, so that fault detection can be performed in advance before a fault occurs to avoid causing Fuel cell engine system down.

Therefore, the advantage of the present application is that, by establishing a fuel cell performance prediction model and experimental tests to find out the standard output characteristic value that can satisfy the fuel cell output performance, the standard output characteristic value can be used as the evaluation of the output result in the entire fuel cell engine system standard, and the standard output characteristic value is used to characterize the output performance of the fuel cell, so it covers more characteristics of the fuel cell. More accurate, more comprehensive and accurate for fault diagnosis.

Further, the S1 includes:

S1-1: Obtain the dynamic characteristics and steady-state characteristics of the fuel cell output current in a step, and establish the performance evaluation index of the fuel cell cell;

S1-2: Establish the fuel cell voltage consistency evaluation index according to the standard deviation and range of the cell voltage of multiple cells in the fuel cell stack;

S1-3: Establish a fuel cell performance prediction model based on the performance evaluation index of the fuel cell cell and the consistency evaluation index of the fuel cell voltage.

Beneficial effects: the characteristics of the fuel cell are divided into steady-state characteristics, dynamic characteristics and voltage-saving consistency, the performance of the fuel cell can be predicted and evaluated through the steady-state characteristics and dynamic characteristics, and the fuel cell can be predicted and evaluated through the consistency of the voltage saving The output performance of the fuel cell can be more comprehensively predicted and evaluated by combining the two and making a comprehensive judgment.

Further, said S2 includes:

S2-1: Set multiple sets of fuel cell operating parameters, and input the fuel cell operating parameters as boundary conditions into the fuel cell performance prediction model;

S2-2: According to the performance evaluation index of the fuel cell cell and the consistency evaluation index of the fuel cell voltage in the fuel cell performance prediction model, the steady-state characteristics, dynamic characteristics and node voltage consistency of the fuel cell at different operating points are obtained, and the generated output result;

S2-3: Comparing the output result with the preset expected value, if the comparison result is within the preset expected value error threshold, execute S2-4, otherwise, repeat S2-1 to S2-3;

S2-4: Carry out a fuel cell test experiment on the fuel cell operating parameters that meet the expected value error threshold, and judge whether the experimental results meet the performance requirements of the fuel cell. If not, repeat S2-1 to S2-3. If they are satisfied, the output is satisfied. Standard output eigenvalues for fuel cell performance requirements.

Beneficial effects: According to the fuel cell performance prediction model, the steady-state characteristics, dynamic characteristics, and voltage-saving consistency of the fuel cell can be effectively simulated, and the output results can be used to determine whether the steady-state characteristics, dynamic characteristics, and voltage-saving consistency meet the output performance of the fuel cell Expectation, get the expected operating parameters, and carry out experiments to verify whether the expected operating parameters meet the output performance of the fuel cell, and the model output results under the satisfied conditions represent the standard output characteristic value of the fuel cell, so through continuous testing and verification Operating parameters that meet fuel cell output performance requirements can be obtained.

Further, the operating parameters of the fuel cell include the working density of the fuel cell, the working pressure of the fuel cell, the working temperature of the fuel cell and the flow rate of the reaction gas.

Beneficial effects: taking the working density of the fuel cell, the working pressure of the fuel cell, the working temperature of the fuel cell and the flow rate of the reaction gas as operating parameters, the difference in the output performance of the fuel cell under the condition of the parameters can be obtained, and it is convenient to obtain the best output performance of the fuel cell.

Further, the S3 includes:

S3-1: Through the fuel cell performance prediction model and the fuel cell test experiment, the standard output characteristic value meeting the fuel cell performance requirements is obtained;

S3-2: Apply desired operating parameters to the fuel cell engine system;

S3-3: When the fuel cell engine system is running, compare the real-time output characteristic value with the standard output characteristic value;

S3-4: If the comparison error between the real-time output characteristic value and the standard output characteristic value exceeds the preset error threshold, it is determined that the fuel cell engine system is faulty.

Beneficial effects: the fuel cell performance prediction model can be used to obtain the operating parameters that meet the expected output performance of the fuel cell. The error difference of the characteristic value will not exceed the preset error threshold. If it exceeds, it indicates that there is a fault in the fuel cell engine system. Therefore, the fault of the fuel cell engine system can be detected and diagnosed in advance to avoid faults during actual operation. cause system downtime.

Description of drawings

Fig. 1 is a block flow diagram of Embodiment 1 of the present invention;

Fig. 2 is a schematic diagram of the fuel cell output current step process in Embodiment 1 of the present invention;

Fig. 3 is the electrochemical model diagram of the fuel cell of Embodiment 1 of the present invention;

FIG. 4 is a schematic diagram of the phenomenon of inconsistent voltages of the fuel cells in Embodiment 1 of the present invention;

Fig. 5 is a flowchart of fuel cell performance prediction and fault diagnosis according to Embodiment 1 of the present invention;

Fig. 6 is a block diagram of the fuel cell failure solution according to the second embodiment of the present invention.

detailed description

The following is further described in detail through specific implementation methods:

In the actual work of fuel cells, the output performance of fuel cells will have certain differences due to different external conditions. When operating under different operating parameters, the output performance of fuel cells will show different characteristics. Therefore, in order to better compare For the output performance of the fuel cell under different conditions, a set of performance evaluation indicators that can reflect the characteristics of the fuel cell are needed to evaluate the pros and cons of the output performance of the fuel cell. It is used to predict and diagnose the failure of the fuel cell system.

Therefore, this application provides a method for fuel cell consistency prediction and fault diagnosis, specifically:

Embodiment one:

Embodiment 1 is basically shown in Figure 1 and Figure 5: a method for fuel cell consistency prediction and fault diagnosis, including:

S1: preset fuel cell performance prediction model;

Among them, S1 includes:

S1-1: Obtain the dynamic characteristics and steady-state characteristics of the fuel cell output current during the transition of the cell voltage, and establish the performance evaluation index of the fuel cell cell;

S1-2: Establish the fuel cell voltage consistency evaluation index according to the standard deviation and range of the cell voltage of multiple cells in the fuel cell stack;

S1-3: Establish a fuel cell performance prediction model based on the performance evaluation index of the fuel cell cell and the consistency evaluation index of the fuel cell voltage.

In the research of the prior art, the output performance characteristics of the fuel cell are usually characterized by the output voltage of the fuel cell under a given current output. Therefore, the fuel cell performance prediction model established in this application is mainly aimed at the output voltage of the fuel cell. Establish; as shown in Figure 2, in the present embodiment, when the output current of fuel cell increases from I ₀ to I ₁ in a stepwise manner by researching, the node voltage of fuel cell can appear undershoot phenomenon, so can find , when the output current is I ₀ , the amplitude of the node voltage is V ₀ ; when the output current increases stepwise to I ₁ , the node voltage appears an undershoot phenomenon, first the node voltage drops to V ₁ instantaneously, and then gradually increases Therefore, in the whole process, the difference of the node voltage from V ₀ to V ₁ is defined as _{ΔV 1} , which represents the activation loss of the fuel cell DC source when the current steps from I ₀ to I ₁ , The remaining voltage after ohmic loss and concentration loss can be characterized by ΔV ₁ to characterize the steady-state characteristics of the fuel cell under current conditions; the process of the node voltage gradually recovering from V ₁ to V _∞ is called the recovery process of the node voltage undershoot, defined as ΔV ₂ represents the process of the fuel cell gradually recovering to a steady state through capacitance, inductance and internal resistance after loss, so ΔV ₂ is used to characterize the dynamic characteristics of the fuel cell under current conditions.

Among them, the electrochemical model of the steady-state characteristic ΔV ₁ and the dynamic characteristic ΔV ₂ of the fuel cell is shown in Figure 3, and the calculation formula of the steady-state characteristic ΔV ₁ of the fuel cell is specifically:

ΔV ₁ ＝E _cell -V _act -V _ohm -V _con

E _cell means Nernst voltage, V _act means activation loss voltage, V _ohm means ohmic loss voltage, V _con means concentration loss voltage;

in:

Among them, c1 is _a constant, and i represents the output current density of the fuel cell;

表示阳极氢气分压，

表示阴极氧气分压，P_ca表示燃料电池阴极压力，P_sat表示燃料电池饱和蒸气压；Among them, T _fc represents the operating temperature of the fuel cell,

is the anode hydrogen partial pressure,

Indicates the cathode oxygen partial pressure, P _ca indicates the cathode pressure of the fuel cell, and P _sat indicates the saturated vapor pressure of the fuel cell;

b ₂ =b ₁₁ λ _m -b ₁₂

Among them, t _m represents the thickness of the proton exchange membrane of the battery, λ _m represents the water content of the proton exchange membrane, and b ₁ , b ₁₁ , b ₁₂ represent constants;

Among them, i _max represents the current density when the performance of the fuel cell drops sharply, c ₃ is a constant, the resistance R _act represents the activation loss, the resistance R _o h _m represents the ohmic loss, and the resistance R _con represents the concentration loss.

The calculation formula of the steady-state characteristic ΔV ₂ of the fuel cell is specifically:

ΔV ₂ =I×R _{L_para}

Among them, _{RL_para} represents the internal resistance,:

Among them, k, a ₂ , r, and a ₃ are all constants.

Therefore, the above-mentioned ΔV ₁ and ΔV ₂ are used in this embodiment to characterize the output performance characteristics of the fuel cell, as the performance evaluation index of a single cell.

As shown in Figure 4, Figure 4 shows the phenomenon that the cell voltage of the fuel cell is inconsistent during the experimental test, and the consistency of the cell voltage is characterized by selecting the standard deviation and range of multiple cells, specifically,

The standard deviation Std _cell of the fuel cell voltage is obtained by the following formula:

Among them, n is the number of fuel cells in the fuel cell stack, and V _cell is the voltage of each fuel cell obtained through inspection of the fuel cell voltage collection;

The fuel cell voltage extreme difference R _cell is obtained by the following formula:

R _cell ＝Max(V _cell )-Min(V _cell )

Through the comprehensive analysis of the standard deviation and range of fuel cell power saving, it is used to analyze the consistency of fuel cell stack voltage.

Therefore, the ΔV ₁ used to characterize the steady-state characteristics of the fuel cell, the ΔV ₂ used to characterize the dynamic characteristics of the fuel cell, and the standard deviation and range of the cell voltage used to characterize the consistency of the fuel cell stack voltage can be obtained through the above-mentioned calculation model fuel cell performance prediction model.

S2: Input the set different fuel cell operating parameters into the fuel cell performance prediction model, find the expected operating parameters that meet the fuel cell performance prediction model, and conduct fuel cell test experiments on the expected operating parameters to obtain fuel cell performance requirements that meet the requirements The standard output eigenvalues at different operating points of ;

Among them, S2 includes:

S2-1: Set multiple sets of fuel cell operating parameters, and input the fuel cell operating parameters as boundary conditions into the fuel cell performance prediction model;

S2-2: According to the performance evaluation index of the fuel cell cell and the consistency evaluation index of the fuel cell voltage in the fuel cell performance prediction model, the steady-state characteristics, dynamic characteristics and node voltage consistency of the fuel cell at different operating points are obtained, and the generated output result;

S2-3: Comparing the output result with the preset expected value, if the comparison result is within the preset expected value error threshold, execute S2-4, otherwise, repeat S2-1 to S2-3;

S2-4: Carry out a fuel cell test experiment on the fuel cell operating parameters that meet the expected value error threshold, and judge whether the experimental results meet the performance requirements of the fuel cell. If not, repeat S2-1 to S2-3. If they are satisfied, the output is satisfied. Standard output eigenvalues for fuel cell performance requirements.

In this embodiment, the specific implementation of S2 is to first select a set of fuel cell operating parameters, including fuel cell operating density, fuel cell operating pressure, fuel cell operating temperature, fuel cell reaction gas flow rate, etc., and use the operating parameters as the boundary The conditions are input into the fuel cell performance prediction model. The fuel cell performance prediction model obtains the output performance of the fuel cell under the current conditions according to the operating parameters. According to the output results of the model, combined with the performance evaluation index, in this embodiment, the performance evaluation index is based on the experimental Then determine the output characteristic value under the operating parameters, that is, the steady-state characteristics, dynamic characteristics and node pressure consistency of the fuel cell, and compare it with the expected value. If the error between the model output result and the expected value is within the preset expected value error threshold In this embodiment, it is ±5%, then it is considered that the output performance of the fuel cell corresponding to the current operating parameter is better, and it can be used in the fuel cell system. If the error between the model output result and the expected value exceeds 5%, it indicates that the current operating parameter The output performance of the fuel cell cannot meet the requirements, and the operating parameters need to be tested again until the output performance meets the conditions, and the fuel cell experiment is used to test and verify, and the operating parameters and standard output characteristic values that meet the actual output performance requirements of the fuel cell are obtained. .

S3: During the operation of the fuel cell engine system, the expected operating parameters are used as input, and the standard output eigenvalue is used as the standard, and the actual output eigenvalues and standard output eigenvalues of the fuel cell engine system at different operating points are calculated in real time according to the preset error The threshold value is compared to generate a comparison result;

Among them, S3 includes:

S3-1: Through the fuel cell performance prediction model and the fuel cell test experiment, the standard output characteristic value meeting the fuel cell performance requirements is obtained;

S3-2: Apply desired operating parameters to the fuel cell engine system;

S3-3: When the fuel cell engine system is running, compare the real-time output characteristic value with the standard output characteristic value;

S3-4: If the comparison error between the real-time output characteristic value and the standard output characteristic value exceeds the preset error threshold, it is determined that the fuel cell engine system is faulty.

In this embodiment, various faults will inevitably be encountered due to complex working conditions during actual operation, so how to quickly detect faults is of great significance to the reliability of the fuel cell engine system. Most of the traditional fault detection uses the lowest node voltage as the fault detection standard, that is, when the lowest node voltage is detected to reach a certain set value, it is considered that there is a fault. This fault detection method is useful, but it cannot be realized. Prediction of faults, even if it is judged that a fault occurs, can only be debugged by stopping the system, which cannot improve the reliability of the system.

Therefore, according to the fuel cell performance prediction model preset in S1, the standard output eigenvalues of the fuel cell in the fuel cell engine system can be obtained, that is, the steady-state characteristics, dynamic characteristics, and voltage-saving consistency, and the standard output eigenvalues can be used as fuel cell The fuel cell output performance standard of the engine system, when the fuel cell engine system is running, the expected operating parameters are used as the input operating parameters of the fuel cell in the fuel cell engine system, and the real-time output characteristic value is compared with the standard output characteristic value. If the result exceeds the preset error threshold, which is 10% in this embodiment, it is determined that the fuel cell is faulty, and repair and maintenance are carried out immediately. Therefore, early detection is realized by inputting expected operating parameters that can be used for fault diagnosis in advance Faults, avoid fuel cell engine downtime due to faults and improve system reliability.

Embodiment two:

As shown in Figure 6, the difference between Embodiment 2 and Embodiment 1 is that in Embodiment 2, it also includes determining the fault level according to the fault diagnosis result, and executing a corresponding solution according to the fault level, specifically:

S4: When performing fault diagnosis, judge the fault level according to the comparison result of the real-time output characteristic value and the standard output characteristic value, and execute the fault solution according to the judgment of the fault level;

Among them, S4 includes:

S4-1: Preset the three-level fault error threshold, if the comparison result is within the preset three-level fault error threshold, increase the input of the operating pressure and gas flow in the fuel cell operating parameters, and at the same time, the fuel cell engine system give an early warning;

Specifically, in S4-1, the preset third-level failure error threshold is 10%-15%, and if the error of the comparison result is between 10%-15%, excluding 15%, it is judged as a third-level failure , at this time, by increasing the input of the operating pressure and gas flow in the operating parameters of the fuel cell to 120% of the original, therefore, the performance of the fuel cell can be improved by increasing the operating pressure and flow, and continuous deterioration of performance can be prevented; The battery engine system can issue an early warning.

S4-2: Preset the error threshold of the secondary fault. If the comparison result is within the preset error threshold of the secondary fault, the load reduction operation will be forcibly executed, the output power of the fuel cell will be reduced, and the fault will be fed back to the fuel cell engine system state;

Specifically, in this embodiment, the preset secondary fault error threshold is 15%-20%. If the error of the comparison result is 15%-20%, it is determined that the fuel cell has a secondary fault. The load reduction operation is to reduce the output power of the fuel cell to half of the original output power, so that the performance can be prevented from continuously deteriorating; at the same time, the fault status is fed back to the fuel cell engine system.

S4-3: Preset the first-level fault error threshold. If the comparison result is within the preset first-level fault error threshold, the load reduction operation will be completed immediately, and the fuel cell will be kept open. At the same time, the fuel cell engine system will be locked to wait for the fault Restart after the troubleshooting is complete.

Specifically, in this embodiment, the preset first-level fault error threshold is more than 20%. If the comparison result determines that the fuel cell belongs to the first-level fault, it indicates that there is a serious fault in the fuel cell, so the fuel cell needs to be checked immediately. The battery is deloaded and troubleshooting is carried out to avoid sudden downtime of the fuel cell engine system during operation in the morning.

The above is only an embodiment of the present invention, and the common knowledge such as the specific structure and characteristics known in the scheme is not described here too much. Those of ordinary skill in the art know all the common technical knowledge in the technical field to which the invention belongs before the filing date or the priority date , can know all the existing technologies in this field, and have the ability to apply conventional experimental methods before this date. Those of ordinary skill in the art can improve and implement this scheme based on their own abilities under the inspiration given by this application. Some typical The known structures or known methods should not be an obstacle for those of ordinary skill in the art to implement the present application. It should be pointed out that for those skilled in the art, under the premise of not departing from the structure of the present invention, several modifications and improvements can also be made, and these should also be regarded as the protection scope of the present invention, and these will not affect the implementation of the present invention. Effects and utility of patents. The scope of protection required by this application shall be based on the content of the claims, and the specific implementation methods and other records in the specification may be used to interpret the content of the claims.

Claims (5)

1. A method for fuel cell consistency prediction and fault diagnosis, characterized in that: comprising: S1: preset fuel cell performance prediction model; S2: Input the set different fuel cell operating parameters into the fuel cell performance prediction model, find the expected operating parameters that meet the fuel cell performance prediction model, and conduct fuel cell test experiments on the expected operating parameters to obtain fuel cell performance requirements that meet the requirements The standard output eigenvalues at different operating points of ; S3: During the operation of the fuel cell engine system, the expected operating parameters are used as input, and the standard output eigenvalue is used as the standard, and the actual output eigenvalues and standard output eigenvalues of the fuel cell engine system at different operating points are calculated in real time according to the preset error The threshold value is compared to generate a comparison result; S4: If the comparison result of the actual output of the fuel cell engine system and the characteristic value of the node pressure in the comparison result exceeds a preset error threshold, perform fault diagnosis. 2. A fuel cell consistency prediction and fault diagnosis method according to claim 1, characterized in that: said S1 includes: S1-1: Obtain the dynamic characteristics and steady-state characteristics of the fuel cell output current in a step, and establish the performance evaluation index of the fuel cell cell; S1-2: Establish the fuel cell voltage consistency evaluation index according to the standard deviation and range of the cell voltage of multiple cells in the fuel cell stack; S1-3: Establish a fuel cell performance prediction model based on the performance evaluation index of the fuel cell cell and the consistency evaluation index of the fuel cell voltage. 3. A method for fuel cell consistency prediction and fault diagnosis according to claim 2, characterized in that: said S2 includes: S2-1: Set multiple sets of fuel cell operating parameters, and input the fuel cell operating parameters as boundary conditions into the fuel cell performance prediction model; S2-2: According to the performance evaluation index of the fuel cell cell and the consistency evaluation index of the fuel cell voltage in the fuel cell performance prediction model, the steady-state characteristics, dynamic characteristics and node voltage consistency of the fuel cell at different operating points are obtained, and the generated output result; S2-3: Comparing the output result with the preset expected value, if the comparison result is within the preset expected value error threshold, execute S2-4, otherwise, repeat S2-1 to S2-3; S2-4: Carry out a fuel cell test experiment on the fuel cell operating parameters that meet the expected value error threshold, and judge whether the experimental results meet the performance requirements of the fuel cell. If not, repeat S2-1 to S2-3. If they are satisfied, the output is satisfied. Standard output eigenvalues for fuel cell performance requirements. 4. A method for fuel cell consistency prediction and fault diagnosis according to claim 3, characterized in that: said fuel cell operating parameters include fuel cell operating density, fuel cell operating pressure, fuel cell operating temperature, and reaction gas flow. 5. A method for fuel cell consistency prediction and fault diagnosis according to claim 1, characterized in that: said S3 includes: S3-1: Through the fuel cell performance prediction model and the fuel cell test experiment, the standard output characteristic value meeting the fuel cell performance requirements is obtained; S3-2: Apply desired operating parameters to the fuel cell engine system; S3-3: When the fuel cell engine system is running, compare the real-time output characteristic value with the standard output characteristic value; S3-4: If the comparison error between the real-time output characteristic value and the standard output characteristic value exceeds the preset error threshold, it is determined that the fuel cell engine system is faulty.

Images