Proton exchange membrane fuel cell aging performance prediction method, device and electronic equipment
By constructing a two-dimensional battery and electrode aging model and optimizing aging parameters using genetic algorithms, the problem of in-depth analysis of the internal aging mechanism of fuel cells in the existing technology is solved, and the accurate prediction and evaluation of the aging performance of proton exchange membrane fuel cells is achieved.
Patent Information
- Application Number
- CN202311009193.2
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2023-08-10
- Publication Date
- 2024-11-26
- Estimated Expiration
- 2043-08-10
AI Technical Summary
The existing proton exchange membrane fuel cell aging performance evaluation method fails to deeply analyze the internal aging mechanism and is unable to accurately evaluate the specific aging status of key aging areas.
By obtaining the physical parameters and real polarization curve of the fuel cell, a two-dimensional battery model and electrode aging model are constructed, and a genetic algorithm is used to iteratively optimize the aging parameters until the voltage performance output matches the real polarization curve, a target battery aging prediction model is obtained, and a goal battery aging prediction model is realized. Assessment of aging status in key aging sites.
The accuracy of the prediction of the aging performance of proton exchange membrane fuel cells is improved, and the aging status of each key aging site can be accurately evaluated.
Smart Images

Figure CN117057230B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of new energy, and in particular to a method, device, electronic equipment and computer-readable storage medium for predicting aging performance of a proton exchange membrane fuel cell. Background Art
[0002] Proton exchange membrane fuel cells use hydrogen and oxygen to produce energy through chemical reactions. The reaction product is clean water. They have the advantages of low operating temperature, no pollution, high energy efficiency and high energy density. They are widely used in new energy vehicles, ships, residential electricity and mobile portable devices. However, the current development of proton exchange membrane fuel cells is limited by their service life. The commercialization of proton exchange membrane fuel cells depends on continuously improving their service life and durability. Therefore, it is necessary to evaluate the aging performance of proton exchange membranes.
[0003] Existing research on the aging performance of proton exchange membrane fuel cells mainly focuses on equivalent circuit models, pressure drop semi-empirical models, and polarization curve characterization. The equivalent current model is tested offline through impedance spectroscopy technology; the pressure drop semi-empirical model is parameter fitted through a large amount of aging test data; and the polarization curve characterization is obtained by setting up circuit measurements to obtain the polarization curve of the battery. However, the existing proton exchange membrane fuel cell aging performance evaluation methods only study the results of battery aging performance, but do not provide in-depth mechanism analysis of the internal mechanism of aging, so it is impossible to accurately evaluate the specific aging status of each key aging part. Summary of the invention
[0004] In view of this, it is necessary to provide a proton exchange membrane fuel cell aging performance prediction method, device, electronic device and computer-readable storage medium to solve the technical problem in the prior art that there is no in-depth analysis of the internal mechanism of proton exchange membrane fuel cell aging and the specific aging status of each key aging part cannot be accurately evaluated.
[0005] In order to solve the above problems, on the one hand, the present invention provides a method for predicting aging performance of a proton exchange membrane fuel cell, the method comprising:
[0006] Obtain the physical parameters of the proton exchange membrane fuel cell to be tested and the real polarization curve of the battery aging test;
[0007] Constructing a two-dimensional battery model of the proton exchange membrane fuel cell to be tested according to the physical parameters;
[0008] Constructing an electrode aging model of a key aging part in the proton exchange membrane fuel cell to be tested according to the physical parameters and the two-dimensional battery model;
[0009] An initial battery aging prediction model of the proton exchange membrane fuel cell to be tested is constructed according to the two-dimensional battery model and the electrode aging model, and aging parameters of the battery aging prediction model are iteratively optimized based on a genetic algorithm until the voltage performance output of the battery aging prediction model matches the true polarization curve, thereby obtaining a target battery aging prediction model of the proton exchange membrane fuel cell to be tested, and obtaining a voltage performance output and an electrode aging curve of the proton exchange membrane fuel cell to be tested according to the output of the target battery aging prediction model.
[0010] Furthermore, the physical parameters of the proton exchange membrane fuel cell to be tested include: structural parameters and material parameters of the proton exchange membrane fuel cell to be tested, and test environment parameters in the battery aging test.
[0011] Furthermore, a two-dimensional battery model of the proton exchange membrane fuel cell to be tested is constructed according to the physical parameters, including:
[0012] Determining the cell reaction conditions and electrochemical reaction formula of the proton exchange membrane fuel cell to be tested according to the physical parameters of the proton exchange membrane fuel cell to be tested;
[0013] A two-dimensional battery model of the proton exchange membrane fuel cell to be tested is constructed according to the battery reaction conditions and electrochemical reaction formula of the proton exchange membrane fuel cell to be tested.
[0014] Furthermore, an electrode aging model of a key aging part in the proton exchange membrane fuel cell to be tested is constructed according to the physical parameters and the two-dimensional battery model, including:
[0015] Determine the key aging part among the aging parts in the proton exchange membrane fuel cell to be tested according to the two-dimensional battery model of the proton exchange membrane fuel cell to be tested;
[0016] Based on the aging mechanism of proton exchange membrane fuel cells, an electrode aging model of the key aging parts in the proton exchange membrane fuel cell to be tested is established.
[0017] Furthermore, a battery aging prediction model for the proton exchange membrane fuel cell to be tested is constructed based on the two-dimensional battery model and the electrode aging model, including:
[0018] A battery aging prediction model is constructed based on the two-dimensional battery model and the electrode aging models of each part and using the proton exchange membrane conductivity, the electrochemical active area of the catalyst layer and the porosity of the diffusion layer as aging parameters.
[0019] Further, the aging parameters of the battery aging prediction model are iteratively optimized based on the genetic algorithm until the voltage performance output of the battery aging prediction model matches the true polarization curve, thereby obtaining a target battery aging prediction model for the proton exchange membrane fuel cell to be tested, including:
[0020] Randomly set multiple groups of initial aging parameters of the battery aging prediction model;
[0021] Perform a battery aging simulation test based on the battery aging prediction model to obtain a voltage performance curve corresponding to each group of aging parameters;
[0022] Calculating the mean square error between the voltage performance curve and the true polarization curve, and obtaining the fitness score of each group of aging parameters according to the mean square error;
[0023] A mean square error threshold is set, the aging parameters are iteratively reorganized according to the fitness score, a battery aging simulation experiment is performed based on the battery aging prediction model after the aging parameters are reorganized, and the mean square error and the fitness score corresponding to the reorganized aging parameters are calculated until the mean square error reaches the mean square error threshold, and an optimal aging parameter group is obtained, and a target battery aging prediction model is obtained according to the optimal aging parameter group.
[0024] Further, iteratively reorganizing the aging parameters according to the fitness score includes:
[0025] The fitness scores of the aging parameter groups are compared, and the aging parameter group with a high fitness score is selected. Some of the aging parameters are exchanged or new aging parameters are randomly created to replace the aging parameters in the aging parameter group to obtain the iterated aging parameter group.
[0026] On the other hand, the present invention also provides a proton exchange membrane fuel cell aging performance prediction device, comprising:
[0027] A data acquisition unit, used to obtain the physical parameters of the proton exchange membrane fuel cell to be tested and the real polarization curve of the battery aging test;
[0028] A two-dimensional model building unit, used to build a two-dimensional battery model of the proton exchange membrane fuel cell to be tested according to the physical parameters;
[0029] An aging model building unit, used to build an electrode aging model of a key aging part in a proton exchange membrane fuel cell to be tested according to the physical parameters and the two-dimensional battery model;
[0030] An aging parameter optimization unit is used to construct an initial battery aging prediction model of the proton exchange membrane fuel cell to be tested according to the two-dimensional battery model and the electrode aging model, iteratively optimize the aging parameters of the battery aging prediction model based on a genetic algorithm until the voltage performance output of the battery aging prediction model matches the true polarization curve, thereby obtaining a target battery aging prediction model of the proton exchange membrane fuel cell to be tested, and obtaining the voltage performance output and electrode aging curve of the proton exchange membrane fuel cell to be tested according to the output of the target battery aging prediction model.
[0031] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein:
[0032] The memory is used to store programs;
[0033] The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in any one of the above-mentioned methods for predicting aging performance of proton exchange membrane fuel cells.
[0034] On the other hand, the present invention also provides a computer-readable storage medium for storing computer-readable programs or instructions, which, when executed by a processor, can implement the steps in any of the above-mentioned methods for predicting the aging performance of proton exchange membrane fuel cells.
[0035] Compared with the prior art, the beneficial effect of adopting the above embodiment is: in the proton exchange membrane fuel cell aging performance prediction method provided by the present invention, firstly, the physical parameters of the proton exchange membrane fuel cell to be tested and the real polarization curve of the battery aging test are obtained; then, a two-dimensional battery model of the proton exchange membrane fuel cell to be tested is constructed according to the physical parameters; an electrode aging model of the key aging parts in the proton exchange membrane fuel cell to be tested is constructed according to the physical parameters and the two-dimensional battery model; finally, an initial battery aging prediction model of the proton exchange membrane fuel cell to be tested is constructed according to the two-dimensional battery model and the electrode aging model, and the aging parameters of the battery aging prediction model are iteratively optimized based on a genetic algorithm until the voltage performance output of the battery aging prediction model matches the real polarization curve, so as to obtain a target battery aging prediction model of the proton exchange membrane fuel cell to be tested, and the voltage performance output and the electrode aging curve of the proton exchange membrane fuel cell to be tested are obtained according to the output of the target battery aging prediction model. In summary, the present invention determines the key aging parts of the proton exchange membrane fuel cell to be tested and constructs an electrode aging model based on its aging mechanism, thereby realizing accurate evaluation of the aging status of each key aging part of the proton exchange membrane fuel cell to be tested, and establishes an initial electrode aging prediction model by combining the electrode aging model with the two-dimensional battery model, and obtains a target battery aging prediction model by iteratively optimizing the aging parameters based on a genetic algorithm, thereby realizing prediction of the aging performance of the proton exchange membrane fuel cell in combination with the internal aging mechanism, thereby improving the accuracy of performance prediction of the aging of the proton exchange membrane fuel cell to be tested. BRIEF DESCRIPTION OF THE DRAWINGS
[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.
[0037] Figure 1 A schematic flow chart of an embodiment of a method for predicting aging performance of a proton exchange membrane fuel cell provided by the present invention;
[0038] Figure 2 A schematic diagram of the structure of a two-dimensional battery model according to an embodiment of the present invention;
[0039] Figure 3 A schematic structural diagram of an embodiment of a device for predicting aging performance of a proton exchange membrane fuel cell provided by the present invention;
[0040] Figure 4 A schematic structural diagram of an embodiment of an electronic device provided by the present invention. DETAILED DESCRIPTION
[0041] The following will be combined with the accompanying drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0042] It should be understood that the drawings of the schematic diagrams are not drawn to scale. The flowcharts used in the present invention illustrate the operations implemented according to some embodiments of the present invention. It should be understood that the operations of the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowcharts, or may remove one or more operations from the flowcharts, under the guidance of the content of the present invention.
[0043] Some of the block diagrams shown in the accompanying drawings are functional entities that do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor systems and / or microcontroller systems.
[0044] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0045] Figure 1 A schematic diagram of a process flow of an embodiment of a method for predicting aging performance of a proton exchange membrane fuel cell provided by the present invention is shown in FIG. Figure 1 As shown, the proton exchange membrane fuel cell aging performance prediction method includes:
[0046] S101, obtaining physical parameters of the proton exchange membrane fuel cell to be tested and a real polarization curve of a battery aging test;
[0047] S102, constructing a two-dimensional battery model of the proton exchange membrane fuel cell to be tested according to the physical parameters;
[0048] S103, constructing an electrode aging model of a key aging part in the proton exchange membrane fuel cell to be tested according to the physical parameters and the two-dimensional battery model;
[0049] S104. Construct an initial battery aging prediction model for the proton exchange membrane fuel cell to be tested based on the two-dimensional battery model and the electrode aging model, iteratively optimize the aging parameters of the battery aging prediction model based on a genetic algorithm until the voltage performance output of the battery aging prediction model matches the true polarization curve, thereby obtaining a target battery aging prediction model for the proton exchange membrane fuel cell to be tested, and obtain the voltage performance output and electrode aging curve of the proton exchange membrane fuel cell to be tested based on the output of the target battery aging prediction model.
[0050] Specifically, in the proton exchange membrane fuel cell aging performance prediction method provided by the present invention, the physical parameters of the proton exchange membrane fuel cell to be tested and the real polarization curve of the battery aging test are first obtained; then a two-dimensional battery model of the proton exchange membrane fuel cell to be tested is constructed according to the physical parameters; an electrode aging model of the key aging parts in the proton exchange membrane fuel cell to be tested is constructed according to the physical parameters and the two-dimensional battery model; finally, an initial battery aging prediction model of the proton exchange membrane fuel cell to be tested is constructed according to the two-dimensional battery model and the electrode aging model, and the aging parameters of the battery aging prediction model are iteratively optimized based on a genetic algorithm until the voltage performance output of the battery aging prediction model matches the real polarization curve, so as to obtain a target battery aging prediction model of the proton exchange membrane fuel cell to be tested, and the voltage performance output and the electrode aging curve of the proton exchange membrane fuel cell to be tested are obtained according to the output of the target battery aging prediction model. In summary, the present invention determines the key aging parts of the proton exchange membrane fuel cell to be tested and constructs an electrode aging model based on its aging mechanism, thereby realizing accurate evaluation of the aging status of each key aging part of the proton exchange membrane fuel cell to be tested, and establishes an initial electrode aging prediction model by combining the electrode aging model with the two-dimensional battery model, and obtains a target battery aging prediction model by iteratively optimizing the aging parameters based on a genetic algorithm, thereby realizing prediction of the aging performance of the proton exchange membrane fuel cell in combination with the internal aging mechanism, thereby improving the accuracy of performance prediction of the aging of the proton exchange membrane fuel cell to be tested.
[0051] In a specific embodiment of the present invention, the physical parameters of the proton exchange membrane fuel cell to be tested include: structural parameters and material parameters of the proton exchange membrane fuel cell to be tested, and test environment parameters in the battery aging test.
[0052] Specifically, the main structural parameters of the proton exchange membrane fuel cell that need to be obtained in the fuel cell modeling process include: thickness and length of basic components such as proton exchange membrane, catalyst layer and diffusion layer; material parameters include: proton exchange membrane conductivity, catalyst layer active surface area, diffusion layer porosity and gas diffusion coefficient; test environment parameters in battery aging test include: temperature, pressure and humidity, etc.
[0053] In a specific embodiment of the present invention, a two-dimensional battery model of a proton exchange membrane fuel cell to be tested is constructed according to physical parameters, including:
[0054] Determine the battery reaction conditions and electrochemical reaction formula of the proton exchange membrane fuel cell to be tested according to the physical parameters of the proton exchange membrane fuel cell to be tested;
[0055] A two-dimensional battery model of the proton exchange membrane fuel cell to be tested is constructed according to the battery reaction conditions and electrochemical reaction formula of the proton exchange membrane fuel cell to be tested.
[0056] Specifically, Figure 2 Schematic diagram of the structure of a two-dimensional battery model according to an embodiment of the present invention. Figure 2 As shown, during the operation of the fuel cell, electrochemical reactions and transmission phenomena occur inside the battery, including the transmission of oxygen and hydrogen, the generation and transmission of water, the transmission of protons and electrons, and the generation and heat dissipation of heat. These electrochemical reactions and transmission phenomena affect each other, and the reaction mechanism is a nonlinear process. In the embodiment, the continuity equation, momentum equation, component transport equation, charge conservation equation and energy conservation equation are used for description, and the equation is established based on the following assumptions: the reaction gas is an ideal gas, and the permeation phenomenon of the gas in the proton exchange membrane is not considered; the anode is hydrogen, the cathode is oxygen, and the gas at both ends is humidified; the flow Reynolds coefficient is small, and the turbulence phenomenon is not considered, and the flow involved is laminar flow; the porous medium is uniform, each part is the same, and an electrochemical reaction occurs on the catalyst surface. And the anode potential is 0V, the external output voltage of the cathode potential is used as the potential boundary, and the gas mass flow rate and pressure at the import and export are used as the mass and pressure boundaries, and a two-dimensional battery model is constructed in the COMSOL simulation software. The formula is as follows:
[0057]
[0058]
[0059]
[0060]
[0061]
[0062] Where ρ is the density of the reaction gas, u is the velocity of the reaction gas, ε is the porosity of the porous medium, S m is the source term, which is 0 in the cathode flow channel, anode flow channel, diffusion layer and proton exchange membrane of the fuel cell. P and μ are pressure and dynamic viscosity coefficient respectively. i is the current density, ω i is the mass fraction of each gas, x j is the gas mole fraction, D ij is the diffusion coefficient, R i is the reaction source term of the gas, c p is the heat capacity at constant pressure, k eff is the effective thermal conductivity and Q is the heat source.
[0063] In a specific embodiment of the present invention, an electrode aging model of a key aging part in a proton exchange membrane fuel cell to be tested is constructed based on physical parameters and a two-dimensional battery model, including:
[0064] Determine the key aging part among the aging parts in the proton exchange membrane fuel cell to be tested according to the two-dimensional battery model of the proton exchange membrane fuel cell to be tested;
[0065] Based on the aging mechanism of proton exchange membrane fuel cells, an electrode aging model of the key aging parts in the proton exchange membrane fuel cell to be tested is established.
[0066] Specifically, in a proton exchange membrane fuel cell, the main components include a proton exchange membrane, a catalyst layer, a diffusion layer, and a bipolar plate. During battery operation, the membrane electrode assembly composed of the proton exchange membrane, the catalyst layer, and the diffusion layer is a key component that affects the battery performance output. Therefore, in the embodiment, the proton exchange membrane, the catalyst layer, and the diffusion layer are taken as key aging parts, and an electrode aging model of each aging part is established based on their aging mechanism and aging experience.
[0067] Among them, the electrode aging model of the active surface area of the catalytic layer is:
[0068]
[0069] K=Ksc×K×KRH×KV
[0070]
[0071]
[0072]
[0073] Wherein, ECSA stands for electrochemically active surface area, (ECSA) N represents the electrochemically active surface area at the Nth cycle load, (ECSA)0 represents the standardized electrochemically active surface area, S min Represents the minimum value of the electrochemically active surface area, K SC =4.537×10 -4 Indicates the attenuation factor under standard operating conditions, K T Indicates the attenuation factor related to the cyclic load characteristics, V amp Indicates the maximum voltage, V ave represents the average voltage, and Δt represents the duration of maximum voltage.
[0074] The electrode aging model of proton exchange membrane is:
[0075]
[0076]
[0077] Among them, r cuu (U(t)) represents the aging rate of the proton exchange membrane, r ref represents the reference aging rate of the proton exchange membrane, a0 is the regression constant, a1 is the temperature regression coefficient, a2 is the relative humidity regression coefficient, a3 is the hydrogen pressure regression coefficient, a4 is the proton exchange membrane thickness regression coefficient, T cuu and T ref are the current and reference stack operating temperatures, RH cuu and RH ref They are the relative humidity of the stack operation and the reference operating humidity, and are the proton exchange membrane thickness and the reference proton exchange membrane thickness, σ mem represents the conductivity of the proton exchange membrane, and U(t) represents the voltage of a single cell in PEMFC.
[0078] The electrode aging model of the gas diffusion layer is:
[0079] ε=f(T)
[0080] Among them, in the experiment, the aging of the gas diffusion layer is usually manifested as the loss of hydrophobicity of the diffusion layer, the decrease of porosity and the increase of carbon corrosion. However, due to the lack of research on the aging of the gas diffusion layer, the porosity is modeled as a time function under the current operating conditions, and the genetic algorithm is used to optimize the accurate gas diffusion layer electrode aging model.
[0081] In a specific embodiment of the present invention, a battery aging prediction model of a proton exchange membrane fuel cell to be tested is constructed based on a two-dimensional battery model and an electrode aging model, including:
[0082] A battery aging prediction model was constructed based on the two-dimensional battery model and the electrode aging model of each part, with the proton exchange membrane conductivity, the electrochemical active area of the catalytic layer and the porosity of the diffusion layer as aging parameters.
[0083] Specifically, after constructing the electrode aging model of each key aging part, the two-dimensional battery model and the electrode aging model are combined for analysis to construct a battery aging performance prediction model for the proton exchange membrane battery to be tested. The three parameters that can intuitively reflect the key aging parts, namely the proton exchange membrane conductivity, the electrochemical active area of the catalytic layer and the porosity of the diffusion layer, are used as aging parameters to construct a battery aging prediction model to realize the analysis of the battery performance aging mechanism.
[0084] In a specific embodiment of the present invention, the aging parameters of the battery aging prediction model are iteratively optimized based on a genetic algorithm until the voltage performance output of the battery aging prediction model matches the actual polarization curve, thereby obtaining a target battery aging prediction model for the proton exchange membrane fuel cell to be tested, including:
[0085] Randomly set multiple groups of initial aging parameters of the battery aging prediction model;
[0086] Conduct battery aging simulation tests based on the battery aging prediction model to obtain voltage performance curves corresponding to each group of aging parameters;
[0087] The mean square error between the voltage performance curve and the true polarization curve is calculated, and the fitness score of each group of aging parameters is obtained according to the mean square error;
[0088] A mean square error threshold is set, the aging parameters are iteratively reorganized according to the fitness score, a battery aging simulation experiment is performed based on the battery aging prediction model after the reorganized aging parameters, and the mean square error and fitness score corresponding to the reorganized aging parameters are calculated until the mean square error reaches the mean square error threshold, and an optimal aging parameter group is obtained, and a target battery aging prediction model is obtained according to the optimal aging parameter group.
[0089] In a specific embodiment of the present invention, iteratively reorganizing aging parameters according to fitness scores includes:
[0090] The fitness scores of the aging parameter groups are compared, and the aging parameter group with a high fitness score is selected. Some of the aging parameters are exchanged or new aging parameters are randomly created to replace the aging parameters in the aging parameter group to obtain the iterated aging parameter group.
[0091] Specifically, after constructing the initial battery aging prediction model, it is necessary to optimize the aging parameters of the initial battery aging prediction model based on the principle of genetic algorithm. First, multiple groups of initial aging parameters are set, and battery aging simulation tests are performed based on each group of aging parameters through the battery aging prediction model, with the battery voltage-current curve in the simulation test as the output voltage performance curve of the simulation test. Then the voltage performance curve and the true polarization curve are compared and the mean square error is calculated, and the corresponding conversion relationship between the mean square error and the fitness score is set and determined, and the accuracy of each group of aging parameters is evaluated to obtain the fitness score. According to the fitness score, for the aging parameter combination with a higher fitness score, some of the aging parameters are interchanged or new aging parameters are randomly set to replace the parameters in the aging parameter combination, where the random replacement method is set to occur with a lower probability. After obtaining the new aging parameter group, the simulation test is repeated to obtain the mean square error and fitness score. If the mean square error reaches the set mean square error threshold requirement or there is no obvious improvement in the individuals in the past few generations during the iteration process, the algorithm is terminated to obtain the optimal aging parameter group, and the target battery aging prediction model is determined based on the optimal aging parameter group. The voltage performance output and electrode aging curve of the proton exchange membrane fuel cell to be tested are obtained based on the battery aging prediction model.
[0092] In summary, compared with the prior art, the present invention analyzes the specific aging status of each part of the battery to be tested by analyzing and constructing an electrode aging model of each aging part, and iteratively optimizes the aging parameters based on a genetic algorithm to obtain the optimal aging parameter group of the battery aging prediction model and the target battery aging prediction model, so as to achieve the effect of accurately evaluating the specific aging status of each key aging part in the prediction of the aging performance of the proton exchange membrane fuel cell.
[0093] Based on the proton exchange membrane fuel cell aging performance prediction method provided by the present invention, the present invention also provides a proton exchange membrane fuel cell aging performance prediction device, such as Figure 3 As shown, including:
[0094] The data acquisition unit 301 is used to acquire the physical parameters of the proton exchange membrane fuel cell to be tested and the real polarization curve of the battery aging test;
[0095] A two-dimensional model building unit 302 is used to build a two-dimensional battery model of the proton exchange membrane fuel cell to be tested according to physical parameters;
[0096] An aging model building unit 303 is used to build an electrode aging model of a key aging part in a proton exchange membrane fuel cell to be tested according to physical parameters and a two-dimensional battery model;
[0097] The aging parameter optimization unit 304 is used to construct an initial battery aging prediction model of the proton exchange membrane fuel cell to be tested based on the two-dimensional battery model and the electrode aging model, and iteratively optimize the aging parameters of the battery aging prediction model based on the genetic algorithm until the voltage performance output of the battery aging prediction model matches the actual polarization curve, so as to obtain the target battery aging prediction model of the proton exchange membrane fuel cell to be tested, and obtain the voltage performance output and electrode aging curve of the proton exchange membrane fuel cell to be tested according to the output of the target battery aging prediction model.
[0098] The proton exchange membrane fuel cell aging performance prediction device 300 provided in the above embodiment can implement the technical solution described in the above proton exchange membrane fuel cell aging performance prediction method embodiment. The specific implementation principles of the above modules or units can refer to the corresponding contents in the above proton exchange membrane fuel cell aging performance prediction method embodiment, which will not be repeated here.
[0099] The present invention also provides an electronic device 400, such as Figure 4 As shown, Figure 4 This is a structural schematic diagram of an embodiment of an electronic device provided by the present invention. The electronic device 400 includes a processor 401, a memory 402, and a computer program stored in the memory 402 and executable on the processor 401. When the processor 401 executes the program, the above-mentioned proton exchange membrane fuel cell aging performance prediction method is implemented.
[0100] As a preferred embodiment, the electronic device further comprises a display 403 for displaying the process of the processor 401 executing the above-mentioned proton exchange membrane fuel cell aging performance prediction method.
[0101] The processor 401 may be an integrated circuit chip with signal processing capability. The processor 401 may be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it may also be a digital signal processor (DSP), an application specific integrated circuit (ASIC). The methods, steps and logic block diagrams disclosed in the embodiments of the present invention may be implemented or executed. The general-purpose processor may also be a microprocessor or the processor may also be any conventional processor, etc.
[0102] The memory 402 may be, but is not limited to, a random access memory (RAM), a read only memory (ROM), a secure digital (SD card), a flash card, etc. The memory 402 is used to store programs, and the processor 401 executes the programs after receiving the execution instruction. The process definition method disclosed in any of the embodiments of the present invention may be applied to the processor 401 or implemented by the processor 401.
[0103] The display 403 may be an LED display screen, a liquid crystal display, or a touch-sensitive display, etc. The display 403 is used to display various information on the electronic device 400 .
[0104] Understandably, Figure 3 The structure shown is only a schematic diagram of the structure of the electronic device 400. The electronic device 400 may also include Figure 4 More or fewer components as shown. Figure 4 Each component shown in the figure can be implemented by hardware, software or a combination thereof.
[0105] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, the above-mentioned method for predicting the aging performance of a proton exchange membrane fuel cell is implemented.
[0106] Generally speaking, the computer instructions for implementing the method of the present invention can be carried by any combination of one or more computer-readable storage media. Non-transitory computer-readable storage media can include any computer-readable media except for the signal itself that is temporarily propagating.
[0107] The computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more conductors, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in conjunction with an instruction execution system, apparatus, or device.
[0108] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed by the present invention should be covered within the protection scope of the present invention.
Claims
1. A method for predicting aging performance of a proton exchange membrane fuel cell, characterized in that: The method comprises: Obtain the physical parameters of the proton exchange membrane fuel cell to be tested and the real polarization curve of the battery aging test; Constructing a two-dimensional battery model of the proton exchange membrane fuel cell to be tested according to the physical parameters; Constructing an electrode aging model of a key aging part in the proton exchange membrane fuel cell to be tested according to the physical parameters and the two-dimensional battery model; Wherein, the key aging parts include the proton exchange membrane, the catalytic layer and the diffusion layer; A battery aging prediction model is constructed based on the two-dimensional battery model and the electrode aging models of each key aging part, and the proton exchange membrane conductivity, the electrochemical active area of the catalyst layer and the porosity of the diffusion layer are used as aging parameters. The aging parameters of the battery aging prediction model are iteratively optimized based on a genetic algorithm until the voltage performance output of the battery aging prediction model matches the true polarization curve, so as to obtain a target battery aging prediction model of the proton exchange membrane fuel cell to be tested, and the voltage performance output and the electrode aging curve of the proton exchange membrane fuel cell to be tested are obtained according to the output of the target battery aging prediction model.
2. The method for predicting aging performance of a proton exchange membrane fuel cell according to claim 1, characterized in that: The physical parameters of the proton exchange membrane fuel cell to be tested include: structural parameters and material parameters of the proton exchange membrane fuel cell to be tested, and test environment parameters in a battery aging test.
3. The method for predicting aging performance of a proton exchange membrane fuel cell according to claim 1, characterized in that: The method of constructing a two-dimensional battery model of the proton exchange membrane fuel cell to be tested according to the physical parameters comprises: Determining the cell reaction conditions and electrochemical reaction formula of the proton exchange membrane fuel cell to be tested according to the physical parameters of the proton exchange membrane fuel cell to be tested; A two-dimensional battery model of the proton exchange membrane fuel cell to be tested is constructed according to the battery reaction conditions and electrochemical reaction formula of the proton exchange membrane fuel cell to be tested.
4. The method for predicting aging performance of a proton exchange membrane fuel cell according to claim 1, characterized in that: The electrode aging model of the key aging parts in the proton exchange membrane fuel cell to be tested is constructed according to the physical parameters and the two-dimensional battery model, including: Determine the key aging part among the aging parts in the proton exchange membrane fuel cell to be tested according to the two-dimensional battery model of the proton exchange membrane fuel cell to be tested; Based on the aging mechanism of proton exchange membrane fuel cells, an electrode aging model of the key aging parts in the proton exchange membrane fuel cell to be tested is established.
5. The method for predicting aging performance of a proton exchange membrane fuel cell according to claim 1, characterized in that: The aging parameters of the battery aging prediction model are iteratively optimized based on the genetic algorithm until the voltage performance output of the battery aging prediction model matches the true polarization curve, thereby obtaining a target battery aging prediction model for the proton exchange membrane fuel cell to be tested, including: Randomly set multiple groups of initial aging parameters of the battery aging prediction model; Perform a battery aging simulation test based on the battery aging prediction model to obtain a voltage performance curve corresponding to each group of aging parameters; Calculating the mean square error between the voltage performance curve and the true polarization curve, and obtaining the fitness score of each group of aging parameters according to the mean square error; A mean square error threshold is set, the aging parameters are iteratively reorganized according to the fitness score, a battery aging simulation experiment is performed based on the battery aging prediction model after the aging parameters are reorganized, and the mean square error and the fitness score corresponding to the reorganized aging parameters are calculated until the mean square error reaches the mean square error threshold, and an optimal aging parameter group is obtained, and a target battery aging prediction model is obtained according to the optimal aging parameter group.
6. The method for predicting aging performance of a proton exchange membrane fuel cell according to claim 5, characterized in that: The iterative reorganization of the aging parameters according to the fitness score comprises: The fitness scores of the aging parameter groups are compared, and the aging parameter group with a high fitness score is selected. Some of the aging parameters are exchanged or new aging parameters are randomly created to replace the aging parameters in the aging parameter group to obtain the iterated aging parameter group.
7. A device for predicting aging performance of a proton exchange membrane fuel cell, characterized in that: include: A data acquisition unit, used to obtain the physical parameters of the proton exchange membrane fuel cell to be tested and the real polarization curve of the battery aging test; A two-dimensional model building unit, used to build a two-dimensional battery model of the proton exchange membrane fuel cell to be tested according to the physical parameters; An aging model building unit, used to build an electrode aging model of a key aging part in a proton exchange membrane fuel cell to be tested according to the physical parameters and the two-dimensional battery model; Wherein, the key aging parts include the proton exchange membrane, the catalytic layer and the diffusion layer; An aging parameter optimization unit is used to construct a battery aging prediction model based on the two-dimensional battery model and the electrode aging models of each key aging part and use the proton exchange membrane conductivity, the electrochemical active area of the catalytic layer and the porosity of the diffusion layer as aging parameters, and iteratively optimize the aging parameters of the battery aging prediction model based on a genetic algorithm until the voltage performance output of the battery aging prediction model matches the true polarization curve, thereby obtaining a target battery aging prediction model for the proton exchange membrane fuel cell to be tested, and obtaining the voltage performance output and electrode aging curve of the proton exchange membrane fuel cell to be tested according to the output of the target battery aging prediction model.
8. An electronic device, characterized in that: comprising a memory and a processor, wherein: The memory is used to store programs; The processor is coupled to the memory and is used to execute the program stored in the memory to implement the steps in the method for predicting aging performance of a proton exchange membrane fuel cell as described in any one of claims 1 to 6.
9. A computer-readable storage medium, characterized in that: Used to store computer-readable programs or instructions, which, when executed by a processor, can implement the steps in the method for predicting the aging performance of a proton exchange membrane fuel cell as described in any one of claims 1 to 6.
