A method and system for optimizing parameters of porous electrodes of fuel cells

Abstract

The present invention belongs to the field of parameter optimization, and provides a method and system for optimizing the parameters of porous electrodes of fuel cells, performs orthogonal experiments, obtains the test results of the coupling influence of the parameters of porous electrodes of fuel cells on the performance of fuel cells; performs regression analysis on the test results of the coupling influence, and constructs a regression equation for the performance of fuel cells; uses the cuckoo algorithm to improve the crown porcupine algorithm, obtains the crown porcupine-cuckoo algorithm, normalizes the regression equation for the performance of fuel cells, constructs a multi-objective optimization fitness function, uses the crown porcupine-cuckoo algorithm to optimize the multi-objective optimization fitness function, obtains the Pareto frontier, and selects the parameter combination of porous electrodes in the Pareto frontier according to the actual operation requirements of the fuel cell. The present invention can improve the overall performance of fuel cells under different operating conditions.

Description

Technical Field

[0001] The invention belongs to the field of parameter optimization, and in particular relates to a method and system for optimizing parameters of a porous electrode of a fuel cell. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] In recent years, proton exchange membrane fuel cells have become one of the new energy sources with potential due to their special advantages such as environmental friendliness, high efficiency and energy saving, stable operation, superior performance, and wide fuel sources. Their performance is comprehensively affected by external structures such as flow channel structure and membrane electrode assembly structure.

[0004] In a proton exchange membrane fuel cell, the catalyst layer and the diffusion layer act as porous electrodes, and changes in their structure can produce different performances in the overall performance of the battery. The catalyst layer is the site of the electrochemical reaction, and its efficient catalytic activity is the key to ensuring efficient and stable output of the fuel cell. The diffusion layer evenly transports the reaction gas to the catalyst layer, while discharging the reaction products to maintain the gas balance inside the fuel cell. Under cold start conditions, the catalyst layer needs to respond quickly to overcome the problem of reduced activity at low temperatures to ensure that the fuel cell can start quickly and operate stably. The diffusion layer needs to prevent moisture condensation from blocking the gas channel to ensure that the reaction gas can still be smoothly transmitted at low temperatures.

[0005] However, the current optimization research on porous electrodes of proton exchange membrane fuel cells is mostly focused on the adjustment of a single parameter, lacking a systematic study of the comprehensive impact of multiple key parameters. At the same time, the existing design and optimization methods of porous electrodes for fuel cells have limitations in dealing with complex multi-factor and multi-objective problems, and cannot meet the performance requirements of fuel cells under different operating conditions such as normal temperature and cold start. Summary of the invention

[0006] In order to solve the above problems, the present invention proposes a method and system for optimizing the parameters of a fuel cell porous electrode. The present invention comprehensively considers various performance indicators of the fuel cell under normal temperature conditions and low-temperature cold start conditions, optimizes the key parameters of the diffusion layer and the catalytic layer through a combination of orthogonal experiments and intelligent algorithms, and improves the overall performance of the fuel cell under different operating conditions.

[0007] According to some embodiments, the present invention adopts the following technical solutions:

[0008] A method for optimizing parameters of a porous electrode of a fuel cell comprises the following steps:

[0009] Conduct orthogonal experiments to obtain the test results of the coupling effect of fuel cell porous electrode parameters on fuel cell performance;

[0010] Performing regression analysis on the coupling impact test results to construct a fuel cell performance regression equation;

[0011] The crested porcupine algorithm is improved by using the cuckoo algorithm to obtain the crested porcupine-cuckoo algorithm, wherein the crested porcupine-cuckoo algorithm is obtained by integrating the second defense strategy of the crested porcupine by using the Levy flight global search mechanism and the host discovery probability mechanism of the cuckoo algorithm;

[0012] The fuel cell performance regression equation is normalized, and based on the normalized result, a multi-objective optimization fitness function is constructed, and the crested porcupine-cuckoo algorithm is used to optimize the multi-objective optimization fitness function to obtain the Pareto frontier. According to the actual operation requirements of the fuel cell, a parameter combination of the porous electrode is selected in the Pareto frontier.

[0013] As an optional embodiment, the fuel cell porous electrode parameters include the thickness of the gas diffusion layer, the porosity of the gas diffusion layer, the thickness of the catalyst layer, the porosity of the catalyst layer and the volume fraction of the ionomer in the catalyst layer.

[0014] As an optional embodiment, the orthogonal test is performed by a simulation experiment or a real test, and the coupling influence test result is obtained by conducting experiments on fuel cells with different porous electrode parameters.

[0015] As an optional implementation, the fuel cell performance includes current density under different operating conditions, heating rate of the fuel cell membrane electrode, and ice amount.

[0016] As an optional implementation, the fuel cell performance regression equation includes:

[0017] ;

[0018] ;

[0019] ;

[0020] in, is the fuel cell current density at room temperature, is the heating rate of the fuel cell membrane electrode under low temperature cold start conditions, is the volume fraction of ice in the fuel cell under low temperature cold start condition; is the thickness of the catalyst layer, is the porosity of the catalyst layer, is the volume fraction of ionomer in the catalyst layer, is the thickness of the diffusion layer, is the porosity of the diffusion layer.

[0021] As an optional implementation, the crested porcupine-cuckoo algorithm specifically adopts the crested porcupine second defense strategy to perform random search near and far from the current solution if the cuckoo egg is discovered by the host; if the cuckoo egg is not discovered by the host, Levy flight is used for global search.

[0022] As an optional embodiment, the mathematical description of the crested porcupine-cuckoo algorithm is:

[0023] ;

[0024] ;

[0025] in, It is in The iteration step A solution; It is the result of the host's awareness of the cuckoo's eggs; is the host discovery probability, which is a preset constant; yes The random number inside, and They are two solutions randomly selected from all solutions; is a randomly generated binary vector; is a random value between 0 and 1; represents the position of the predator, , is a solution randomly selected from all solutions, 𝛼 is the convergence speed factor, is a Levy flight random vector.

[0026] As an optional implementation, the fuel cell performance regression equation is normalized using a minimum-maximum normalization method.

[0027] As an optional implementation, the multi-objective optimization fitness function is characterized by the current density under normal temperature conditions, the temperature rise rate under low temperature cold start conditions, and the volume fraction of ice under low temperature cold start conditions, and five parameters, namely, the thickness of the catalytic layer, the porosity of the catalytic layer, the volume fraction of the ionomer in the catalytic layer, the thickness of the diffusion layer, and the porosity of the diffusion layer, are selected as optimization variables.

[0028] As an optional implementation method, according to the actual operation requirements of the fuel cell, the process of selecting a parameter combination of the porous electrode in the Pareto front includes: if the fuel cell is applied to a fixed power generation scenario and the start-stop frequency is less than a set value, a solution with better fuel cell performance under normal temperature conditions is selected; if the fuel cell is applied to a start-stop frequency exceeding the set value and the ambient temperature is lower than a predetermined value, a solution with better fuel cell performance under low temperature cold start conditions is selected.

[0029] A fuel cell porous electrode parameter optimization system, comprising:

[0030] Orthogonal test module, used to conduct orthogonal test and obtain the test results of the coupling effect of fuel cell porous electrode parameters on fuel cell performance;

[0031] A regression analysis module, used to perform regression analysis on the coupling impact test results and construct a fuel cell performance regression equation;

[0032] A model improvement module, used for improving the crested porcupine algorithm by using the cuckoo algorithm to obtain the crested porcupine-cuckoo algorithm, wherein the crested porcupine-cuckoo algorithm is obtained by integrating the second defense strategy of the crested porcupine by using the Levy flight global search mechanism and the host discovery probability mechanism of the cuckoo algorithm;

[0033] The multi-objective optimization module is used to normalize the fuel cell performance regression equation, construct a multi-objective optimization fitness function based on the normalized result, use the crested porcupine-cuckoo algorithm to optimize the multi-objective optimization fitness function to obtain the Pareto frontier, and select the parameter combination of the porous electrode in the Pareto frontier according to the actual operation requirements of the fuel cell.

[0034] Compared with the prior art, the present invention has the following beneficial effects:

[0035] The present invention proposes a fused crested porcupine-cuckoo algorithm, which integrates the Levy flight mechanism of the cuckoo algorithm into the second defense strategy of the crested porcupine. The characteristic of Levy flight with a large jump step length can be utilized to achieve a balance between local search and global search, improve the search diversity of the algorithm, and effectively avoid falling into the local optimal solution.

[0036] The optimization method provided by the present invention can balance and optimize the performance under normal temperature conditions and low temperature conditions, ensuring that the fuel cell can perform well under various conditions, and can flexibly select the porous electrode parameter combination according to the actual working conditions of the fuel cell to meet the different performance requirements of the fuel cell.

[0037] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings in the specification, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0039] Figure 1 The present invention is a flow chart of a method for optimizing parameters of porous electrodes of fuel cells based on an intelligent algorithm in one embodiment. DETAILED DESCRIPTION

[0040] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0041] It should be noted that the following detailed descriptions are all illustrative and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meanings as those commonly understood by those skilled in the art to which the present invention belongs.

[0042] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprising" and / or "including" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0043] In the absence of conflict, the embodiments in this application and the features in the embodiments may be combined with each other.

[0044] Embodiment 1

[0045] This embodiment is described by using the application scenario of proton exchange membrane fuel cells, but it does not mean that the method provided in this embodiment can only be used in this scenario.

[0046] A proton exchange membrane fuel cell includes four core components: a proton exchange membrane, an anode catalyst layer, an anode gas diffusion layer, and an anode bipolar plate. The bipolar plate is provided with flow channels. The fuel and the oxidant enter the fuel cell through the anode flow channel and the cathode flow channel respectively, and an electrochemical reaction occurs to realize the fuel cell electrical energy output. The fuel is hydrogen and the oxidant is air.

[0047] A method for optimizing parameters of porous electrodes of fuel cells, such as Figure 1 As shown, the following steps are included:

[0048] Step 1: Conduct an orthogonal test to obtain the test results of the coupling effect of fuel cell porous electrode parameters on fuel cell performance.

[0049] Under normal temperature conditions, five parameters are selected, namely, the thickness of the gas diffusion layer of the anode and cathode, the porosity of the gas diffusion layer, the thickness of the catalyst layer, the porosity of the catalyst layer, and the volume fraction of the ionomer in the catalyst layer. In this embodiment, the voltage of 0.5 V is selected as the basic condition to carry out the orthogonal experiment.

[0050] Under low temperature cold start conditions, the orthogonal test factors select the same five porous electrode parameters as those under normal temperature conditions. In this embodiment, the operating environment of -4°C and the initial battery temperature, 0.25A / cm 2The constant current density is used as the cold start condition. The evaluation indexes are the time required for the cathode catalyst layer temperature to rise to 0°C and the corresponding maximum ice volume fraction.

[0051] Of course, in other embodiments, other operating conditions may be selected as basic operating conditions to carry out orthogonal tests. Parameters of the orthogonal test may also be adjusted or changed.

[0052] The test results can also be obtained by running fuel cells with different porous electrode parameters in simulation or experimental manner.

[0053] In some embodiments, the fuel cell performance includes the current density under various operating conditions and the heating rate and ice amount of the fuel cell membrane electrode.

[0054] Step 2: Perform regression analysis on the test results of normal temperature and low temperature cold start conditions respectively, construct a fuel cell performance regression equation, and use the regression equation to predict the combination of optimal parameter values ​​of the porous electrode under different conditions.

[0055] In this embodiment, SPSS software is used to perform regression analysis to obtain the regression analysis results of current density under normal temperature conditions and the regression analysis results of battery temperature rise time and ice amount under low temperature cold start conditions.

[0056] Based on the coefficients obtained from the regression model results, the fuel cell performance regression prediction equation is:

[0057] ;

[0058] ;

[0059] ;

[0060] in, is the fuel cell current density at room temperature, is the heating rate of the fuel cell membrane electrode under low temperature cold start conditions, is the volume fraction of ice in the fuel cell under low temperature cold start condition; is the thickness of the catalyst layer, is the porosity of the catalyst layer, is the volume fraction of ionomer in the catalyst layer, is the thickness of the diffusion layer, is the porosity of the diffusion layer.

[0061] The optimal solution of the above three fuel cell performance regression prediction equations is obtained to obtain the maximum and minimum current density under normal temperature conditions. , , the longest and shortest temperature rise time under low temperature cold start conditions , , Maximum and minimum icing amount under low temperature cold start conditions , , and the porous electrode parameter values ​​for the corresponding working conditions .

[0062] Step 3: Use the cuckoo algorithm to improve the crested porcupine algorithm and obtain the crested porcupine-cuckoo algorithm.

[0063] The crested porcupine-cuckoo algorithm is obtained by integrating the Levy flight global search mechanism and the host discovery probability mechanism of the cuckoo algorithm into the second defense mechanism of the crested porcupine algorithm.

[0064] The mathematical description of the second defense strategy of the crested porcupine is:

[0065] ;

[0066] in, It is in The iteration step A solution, It is in The iteration step A solution; and They are two solutions randomly selected from all solutions; is a randomly generated binary vector; is a random value between 0 and 1; represents the location of the predator; Is in the current crested porcupine and crested porcupines randomly selected from the population The vector generated between is used to represent the position of the predator at iteration t.

[0067] The calculation method is as follows, where Here is a solution chosen randomly from among all possible solutions:

[0068] ;

[0069] The cuckoo algorithm simulates the parasitic laying of cuckoo eggs. The cuckoo uses a large range of Levy flights to search for a suitable host nest. This behavior represents the global search of the algorithm. The eggs in the nest are found to be cuckoo eggs. After being discovered, the cuckoo will look for a new host nest. The mathematical description of the global search mechanism of the cuckoo algorithm is:

[0070] ;

[0071] in, is the step size factor, is a Levy flight random vector:

[0072] ;

[0073] in, is the distribution index, and its value is ; is the gamma function; is a random step size; is the minimum step size.

[0074] The mathematical description of the crested porcupine-cuckoo algorithm is:

[0075] ;

[0076] ;

[0077] in, It is the result of the host's awareness of the cuckoo's eggs; is the host discovery probability, which is a preset constant; yes Random numbers within.

[0078] The improved crested porcupine-cuckoo algorithm uses the above formula to replace the original second defense strategy. When the host finds the cuckoo egg, , the last term of the above formula is 0, and the second defense strategy of the crested porcupine algorithm is used for search; when the host does not find the cuckoo egg, , the second term of the above formula is 0, and a global search is performed according to the cuckoo Levy flight.

[0079] Step 4: Normalize the regression equation obtained in step 2, then construct a multi-objective optimization fitness function, use the crested porcupine-cuckoo algorithm obtained in step 2 to find the optimal solution, obtain the Pareto frontier, and finally select the parameter combination of the porous electrode in the Pareto frontier according to the actual operation requirements of the fuel cell. Specifically:

[0080] Use the minimum and maximum method for normalization:

[0081] ;

[0082] ;

[0083] ;

[0084] Construct a multi-objective optimization fitness function:

[0085] ;

[0086] Will Substituting the definition of into the above formula, we get:

[0087] ;

[0088] The crested porcupine-cuckoo was used for parameter optimization. In this embodiment, the optimized input parameters were The objective function is The optimization result is the Pareto frontier of the input parameters. Different combinations of porous electrode parameters are selected according to the requirements of the fuel cell application scenario. If the fuel cell is used in a fixed power generation scenario and does not require frequent start and stop, the solution with better fuel cell performance under normal temperature conditions is selected; if the fuel cell is used in automobiles and other scenarios that require frequent start and stop and the ambient temperature is low, the solution with better performance under low temperature cold start conditions is selected.

[0089] Finally, a porous electrode design scheme for comprehensive fuel cell operating conditions is obtained.

[0090] Those skilled in the art should understand that the porous electrode parameters selected in the present invention can be the five parameters in the embodiment or other parameter combinations. The regression analysis software is not limited to SPSS, but can be any other mathematical software with regression analysis.

[0091] Embodiment 2

[0092] A fuel cell porous electrode parameter optimization system, comprising:

[0093] Orthogonal test module, used to conduct orthogonal test and obtain the test results of the coupling effect of fuel cell porous electrode parameters on fuel cell performance;

[0094] A regression analysis module, used to perform regression analysis on the coupling impact test results and construct a fuel cell performance regression equation;

[0095] A model improvement module, used for improving the crested porcupine algorithm by using the cuckoo algorithm to obtain the crested porcupine-cuckoo algorithm, wherein the crested porcupine-cuckoo algorithm is obtained by integrating the second defense strategy of the crested porcupine by using the Levy flight global search mechanism and the host discovery probability mechanism of the cuckoo algorithm;

[0096] The multi-objective optimization module is used to normalize the fuel cell performance regression equation, construct a multi-objective optimization fitness function based on the normalized result, use the crested porcupine-cuckoo algorithm to optimize the multi-objective optimization fitness function to obtain the Pareto frontier, and select the parameter combination of the porous electrode in the Pareto frontier according to the actual operation requirements of the fuel cell.

[0097] It should be understood by those skilled in the art that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of an all-hardware embodiment, an all-software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of one or more computer-usable storage media (including but not limited to disk storage, CD - ROM , optical storage, etc.).

[0098] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0099] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0100] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0101] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made by those skilled in the art within the spirit and principle of the present invention without creative labor shall be included in the protection scope of the present invention.

Claims

1. A method for optimizing parameters of a porous electrode of a fuel cell, characterized in that: The following steps are involved: Conduct orthogonal experiments to obtain the test results of the coupling effect of fuel cell porous electrode parameters on fuel cell performance; Performing regression analysis on the coupling impact test results to construct a fuel cell performance regression equation; The crested porcupine algorithm is improved by using the cuckoo algorithm to obtain the crested porcupine-cuckoo algorithm, wherein the crested porcupine-cuckoo algorithm is obtained by integrating the second defense strategy of the crested porcupine by using the Levy flight global search mechanism and the host discovery probability mechanism of the cuckoo algorithm; Specifically, the crested porcupine-cuckoo algorithm is obtained by integrating the Levy flight global search mechanism and the host discovery probability mechanism of the cuckoo algorithm into the second defense mechanism of the crested porcupine algorithm; The mathematical description of the second defense strategy of the crested porcupine is: ； in, It is in The iteration step A solution, It is in The iteration step A solution; and They are two solutions randomly selected from all solutions; is a randomly generated binary vector; is a random value between 0 and 1; represents the location of the predator; Is in the current crested porcupine and crested porcupines randomly selected from the population The vector generated between is used to represent the position of the predator at iteration t; The calculation method is as follows, where Here is a solution chosen randomly from among all possible solutions: ； The cuckoo algorithm simulates the parasitic laying of cuckoo eggs. When looking for a suitable host nest, the cuckoo uses a large-scale Levy flight. This behavior represents the global search of the algorithm. The host has a certain probability The eggs in the nest are found to be cuckoo eggs. After being discovered, the cuckoo will look for a new host nest; The mathematical description of the global search mechanism of the cuckoo algorithm is: ； in, is the step size factor, is a Levy flight random vector: ； in, is the distribution index, and its value is ; is the gamma function; is the random step size; is the minimum step size; The mathematical description of the crested porcupine-cuckoo algorithm is: ； ； in, It is the result of the host's awareness of the cuckoo's eggs; is the host discovery probability, which is a preset constant; yes Random numbers within The improved crested porcupine-cuckoo algorithm uses the above formula to replace the original second defense strategy; when the host finds the cuckoo egg, , the last term of the above formula is 0, and the second defense strategy of the crested porcupine algorithm is used for search; when the host does not find the cuckoo egg, , the second term of the above formula is 0, and a global search is performed according to the cuckoo Levy flight; The fuel cell performance regression equation is normalized, and based on the normalized result, a multi-objective optimization fitness function is constructed, and the crested porcupine-cuckoo algorithm is used to optimize the multi-objective optimization fitness function to obtain the Pareto frontier. According to the actual operation requirements of the fuel cell, a parameter combination of the porous electrode is selected in the Pareto frontier.

2. A method for optimizing parameters of a porous electrode of a fuel cell according to claim 1, characterized in that: The fuel cell porous electrode parameters include the thickness of the gas diffusion layer, the porosity of the gas diffusion layer, the thickness of the catalyst layer, the porosity of the catalyst layer and the volume fraction of the ionomer in the catalyst layer; The fuel cell performance includes current density under different working conditions, heating rate of the fuel cell membrane electrode and ice amount.

3. A method for optimizing parameters of a porous electrode of a fuel cell according to claim 1, characterized in that: The orthogonal test is performed through a simulation experiment or a real test, and the coupling influence test result is obtained by conducting experiments on fuel cells with different porous electrode parameters.

4. A method for optimizing parameters of a porous electrode of a fuel cell according to claim 1, characterized in that: The fuel cell performance regression equation includes: in, is the fuel cell current density at room temperature, is the heating rate of the fuel cell membrane electrode under low temperature cold start conditions, is the volume fraction of ice in the fuel cell under low temperature cold start condition; is the thickness of the catalyst layer, is the porosity of the catalyst layer, is the volume fraction of ionomer in the catalyst layer, is the thickness of the diffusion layer, is the porosity of the diffusion layer.

5. A method for optimizing parameters of a porous electrode of a fuel cell according to claim 1, characterized in that: The crested porcupine-cuckoo algorithm specifically adopts the second defense strategy of the crested porcupine to perform random searches near and far from the current solution if the cuckoo egg is discovered by the host; if the cuckoo egg is not discovered by the host, Levy flight is used to perform a global search.

6. A method for optimizing parameters of a porous electrode of a fuel cell as claimed in claim 5, characterized in that: The mathematical description of the crested porcupine-cuckoo algorithm is: ； ； in, It is in The iteration step A solution; It is the result of the host's awareness of the cuckoo's eggs; is the host discovery probability, which is a preset constant; yes The random number inside and They are two solutions randomly selected from all solutions; is a randomly generated binary vector; is a random value between 0 and 1; represents the position of the predator, , is a solution randomly selected from all solutions, 𝛼 is the convergence speed factor, is a Levy flight random vector.

7. A method for optimizing parameters of a porous electrode of a fuel cell according to claim 1, characterized in that: The fuel cell performance regression equation is normalized using a minimum-maximum normalization method.

8. A method for optimizing parameters of a porous electrode of a fuel cell as claimed in claim 1, characterized in that: The multi-objective optimization fitness function is characterized by the current density under normal temperature conditions, the temperature rise rate under low temperature cold start conditions, and the volume fraction of ice under low temperature cold start conditions. Five parameters, namely, the thickness of the catalytic layer, the porosity of the catalytic layer, the volume fraction of the ionomer in the catalytic layer, the thickness of the diffusion layer, and the porosity of the diffusion layer, are selected as optimization variables.

9. A method for optimizing parameters of a porous electrode of a fuel cell as claimed in claim 1, characterized in that: According to the actual operation requirements of the fuel cell, the process of selecting the parameter combination of the porous electrode in the Pareto front includes: if the fuel cell is applied to a fixed power generation scenario and the start-stop frequency is less than the set value, a solution with better fuel cell performance under normal temperature conditions is selected; if the fuel cell is applied to a scenario where the start-stop frequency exceeds the set value and the ambient temperature is lower than the predetermined value, a solution with better fuel cell performance under low temperature cold start conditions is selected.

10. A fuel cell porous electrode parameter optimization system, characterized in that: include: Orthogonal test module, used to conduct orthogonal test and obtain the test results of the coupling effect of fuel cell porous electrode parameters on fuel cell performance; A regression analysis module, used to perform regression analysis on the coupling impact test results and construct a fuel cell performance regression equation; A model improvement module, used for improving the crested porcupine algorithm by using the cuckoo algorithm to obtain the crested porcupine-cuckoo algorithm, wherein the crested porcupine-cuckoo algorithm is obtained by integrating the second defense strategy of the crested porcupine by using the Levy flight global search mechanism and the host discovery probability mechanism of the cuckoo algorithm; Specifically, the crested porcupine-cuckoo algorithm is obtained by integrating the Levy flight global search mechanism and the host discovery probability mechanism of the cuckoo algorithm into the second defense mechanism of the crested porcupine algorithm; The mathematical description of the second defense strategy of the crested porcupine is: ； in, It is in The iteration step A solution, It is in The iteration step A solution; and They are two solutions randomly selected from all solutions; is a randomly generated binary vector; is a random value between 0 and 1; represents the location of the predator; Is in the current crested porcupine and crested porcupines randomly selected from the population The vector generated between is used to represent the position of the predator at iteration t; The calculation method is as follows, where Here is a solution chosen randomly from among all possible solutions: ； The cuckoo algorithm simulates the parasitic laying of cuckoo eggs. When looking for a suitable host nest, the cuckoo uses a large-scale Levy flight. This behavior represents the global search of the algorithm. The host has a certain probability The eggs in the nest are found to be cuckoo eggs. After being discovered, the cuckoo will look for a new host nest; The mathematical description of the global search mechanism of the cuckoo algorithm is: ； in, is the step size factor, is a Levy flight random vector: ； in, is the distribution index, and its value is ; is the gamma function; is the random step size; is the minimum step size; The mathematical description of the crested porcupine-cuckoo algorithm is: ； ； in, It is the result of the host's awareness of the cuckoo's eggs; is the host discovery probability, which is a preset constant; yes Random numbers within The improved crested porcupine-cuckoo algorithm uses the above formula to replace the original second defense strategy; when the host finds the cuckoo egg, , the last term of the above formula is 0, and the second defense strategy of the crested porcupine algorithm is used for search; when the host does not find the cuckoo egg, , the second term of the above formula is 0, and a global search is performed according to the cuckoo Levy flight; The multi-objective optimization module is used to normalize the fuel cell performance regression equation, construct a multi-objective optimization fitness function based on the normalized result, use the crested porcupine-cuckoo algorithm to optimize the multi-objective optimization fitness function to obtain the Pareto frontier, and select the parameter combination of the porous electrode in the Pareto frontier according to the actual operation requirements of the fuel cell.

Images