Optimization method and device for low-temperature cold start of fuel cell stack and electronic equipment

Abstract

The invention provides an optimization method and device for low-temperature cold start of a fuel cell stack and electronic equipment. The method comprises the following steps: determining a low-temperature cold start model based on internal parameters of a fuel cell stack; determining the initial membrane water content and the segmented step current as optimization variables; determining the cold start time of the low-temperature cold start model based on the optimization variable and the low-temperature cold start model, and taking the cold start time as an optimization target; based on the optimization variable and the optimization target, generating a particle swarm by adopting a particle swarm algorithm, and performing iterative global optimization in the particle swarm; and acquiring a local optimal solution of any iteration, and performing next iteration based on the local optimal solution and the low-temperature cold start model until the iteration is finished to obtain a global optimal solution meeting the optimization constraint condition. Therefore, according to the scheme, the cold start time is taken as the optimization target, and the optimization constraint condition of the cold start of the model is established, so that the cold start time can be shortened on the premise of ensuring that the low-temperature cold start of the electric pile is successful.

Description

Technical Field

[0001] The present application relates to the field of fuel cell technology, and in particular to an optimization method, device and electronic equipment for low-temperature cold start of a fuel cell stack. Background Art

[0002] The existing fuel cell stack achieves low-temperature cold start mainly through a combination of positive temperature coefficient (PTC) heating and fuel cell self-heating to achieve the ultimate low-temperature cold start goal. The serious spatial distribution inconsistency of the fuel cell stack during the low-temperature cold start process is ignored, resulting in more ice during the cold start process, which causes oxygen transmission blockage, and ultimately the output voltage drops to the cut-off voltage, resulting in the failure of the stack cold start. Summary of the invention

[0003] The present application aims to solve one of the technical problems in the related art at least to some extent.

[0004] To this end, the first purpose of the present application is to propose an optimization method for low-temperature cold start of a fuel cell stack, so as to reduce the cold start time while ensuring the success of the low-temperature cold start of the stack.

[0005] The second objective of the present application is to provide an optimization device for low-temperature cold start of a fuel cell stack.

[0006] The third objective of the present application is to provide an electronic device.

[0007] A fourth objective of the present application is to provide a computer-readable storage medium.

[0008] A fifth object of the present application is to provide a computer program product.

[0009] To achieve the above-mentioned purpose, the first aspect of the present application proposes an optimization method for low-temperature cold start of a fuel cell stack, comprising: determining a low-temperature cold start model of the fuel cell stack based on the internal parameters of the fuel cell stack; determining the initial membrane water content of the fuel cell stack, and the segmented step current of the cold start, and using the initial membrane water content and the segmented step current as optimization variables; based on the optimization variables and the low-temperature cold start model, determining the cold start time when the low-temperature cold start model meets the successful conditions for cold start, and using the cold start time as the optimization target; based on the optimization variables and the optimization target, using a particle swarm algorithm to generate a particle population, and performing iterative global optimization in the particle population; obtaining the local optimal solution of any iteration, and performing the next iteration based on the local optimal solution and the low-temperature cold start model, until the iteration is completed to obtain a global optimal solution that meets the optimization constraints, and the global optimal solution at least includes the optimal cold start time of the low-temperature cold start model.

[0010] To achieve the above-mentioned purpose, the second embodiment of the present application proposes an optimization device for low-temperature cold start of a fuel cell stack, comprising: a first determination module, used to determine the low-temperature cold start model of the fuel cell stack based on the internal parameters of the fuel cell stack; a second determination module, used to determine the initial membrane water content of the fuel cell stack, and the segmented step current of the cold start, and use the initial membrane water content and the segmented step current as optimization variables; a third determination module, used to determine the cold start time when the low-temperature cold start model meets the successful conditions for cold start based on the optimization variables and the low-temperature cold start model, and use the cold start time as the optimization target; a generation module, used to generate a particle population based on the optimization variables and the optimization target using a particle swarm algorithm, and perform iterative global optimization in the particle population; an iteration module, used to obtain the local optimal solution of any iteration, and perform the next iteration based on the local optimal solution and the low-temperature cold start model, until the iteration is completed to obtain the global optimal solution that meets the optimization constraints, and the global optimal solution at least includes the optimal cold start time of the low-temperature cold start model.

[0011] To achieve the above-mentioned purpose, the third aspect embodiment of the present application proposes an electronic device, comprising: a processor; and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory, so that the processor can execute the optimization method for low-temperature cold start of a fuel cell stack described in the first aspect embodiment above.

[0012] To achieve the above-mentioned purpose, the fourth aspect of the present application proposes a computer-readable storage medium having a computer program stored thereon, wherein the computer instructions are used to enable the computer to execute the optimization method for low-temperature cold start of a fuel cell stack described in the first aspect of the above-mentioned embodiment.

[0013] To achieve the above-mentioned purpose, the fifth embodiment of the present application proposes a computer program product, including a computer program, which, when executed by a processor, implements the optimization method for low-temperature cold start of a fuel cell stack described in the first embodiment above.

[0014] The optimization method, device and electronic device for low-temperature cold start of a fuel cell stack provided by the present application, by constructing a low-temperature cold start model of the fuel cell stack, and determining the optimization variables of the low-temperature cold start model, by inputting the optimization variables into the low-temperature cold start model, the cold start time corresponding to the optimization variables can be determined, and the cold start time is used as the optimization target to generate a particle population. By iterative global optimization in the particle population, the optimal cold start time corresponding to the low-temperature cold start model can be determined. By loading according to the segmented step current, the cold start time can be further optimized compared to the constant current cold start mode. By taking the cold start time as the optimization target and establishing the optimization constraint conditions for the cold start of the model, the cold start time can be reduced under the premise of ensuring the success of the low-temperature cold start of the stack.

[0015] Additional aspects and advantages of the present application will be given in part in the description below, and in part will become apparent from the description below, or will be learned through the practice of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0017] Figure 1 A schematic flow chart of a method for optimizing a low-temperature cold start of a fuel cell stack provided in an embodiment of the present application;

[0018] Figure 2 A schematic flow chart of another method for optimizing a low-temperature cold start of a fuel cell stack provided in an embodiment of the present application;

[0019] Figure 3 A schematic flow chart of another method for optimizing a low-temperature cold start of a fuel cell stack provided in an embodiment of the present application;

[0020] Figure 4 A schematic flow chart of the motion process of determining respective internal parameters in a method for optimizing a low-temperature cold start of a fuel cell stack provided in an embodiment of the present application;

[0021] Figure 5 A schematic diagram of a low-temperature cold start optimization method provided in an embodiment of the present application;

[0022] Figure 6 A schematic diagram of changes in the end output voltage and the minimum membrane electrode temperature after low-temperature cold start optimization at -20°C provided in an embodiment of the present application;

[0023] Figure 7 A schematic diagram of changes in the end output voltage and the minimum membrane electrode temperature after low-temperature cold start optimization at -25°C provided in an embodiment of the present application;

[0024] Figure 8 A schematic structural diagram of a fuel cell stack low-temperature cold start optimization device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0025] Embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present application, and should not be construed as limiting the present application.

[0026] The following describes the optimization method and device for low-temperature cold start of a fuel cell stack according to an embodiment of the present application with reference to the accompanying drawings.

[0027] Figure 1 is a flow chart of a method for optimizing a low temperature cold start of a fuel cell stack according to an exemplary embodiment. Figure 1 As shown, the optimization method for low temperature cold start of a fuel cell stack in an embodiment of the present application includes but is not limited to the following steps:

[0028] S101, determining a low-temperature cold start model of the fuel cell stack based on internal parameters of the fuel cell stack.

[0029] It should be noted that the execution subject of the optimization method for low-temperature cold start of a fuel cell stack provided in the embodiment of the present application is an electronic device, which may be a terminal device. Optionally, the terminal device may be a mobile electronic device or a non-mobile electronic device. Exemplarily, the mobile electronic device may be a mobile phone, a tablet computer, a laptop computer, a PDA, an in-vehicle electronic device, a wearable device, an ultra-mobile personal computer (UMPC), a netbook or a personal digital assistant (PDA), etc., and the non-mobile electronic device may be a personal computer (PC), a television, etc. The embodiment of the present application is not specifically limited.

[0030] In some implementations, the internal parameters of the fuel cell stack include but are not limited to electrical parameters, thermal parameters, gas parameters, liquid parameters, etc. The internal parameters can be determined through their respective motion transfer processes, and based on the motion transfer process, a one-dimensional cold start numerical model of the fuel cell stack along the charge transfer direction can be established as a low-temperature cold start model of the fuel cell stack.

[0031] S102, determining the initial membrane water content of the fuel cell stack and the segmented step current of the cold start, and taking the initial membrane water content and the segmented step current as optimization variables.

[0032] It is understandable that the fuel cell stack needs to go through a purge process when it is shut down to remove the liquid water inside the battery and the proton membrane bound water, thereby improving the membrane water storage capacity during the cold start process. The initial membrane water content of the fuel cell stack can be determined based on the mapping relationship between the saturated membrane water content of the proton exchange membrane and the temperature change.

[0033] In some implementations, the temperature can be divided into ranges, and the current magnitudes in different temperature ranges can be determined, and the segmented step current for cold start can be determined based on the correspondence between different temperature ranges and current magnitudes. Furthermore, optimization variables can be generated based on the initial membrane water content and the segmented step current.

[0034] For example, suppose the temperature ranges are: [253.15, 258), [258, 263), [263, 268), [268, 237.15], where the unit of temperature is Kelvin K. Suppose the temperature is within [253.15, 258), and the current is I a Start; Assume the temperature is within [258,263) and the current is I b Start; Assume the temperature is within [263,268) and the current is I c Start; set the temperature to be within [268,237.15], and the current to be I d Start it.

[0035] S103, based on the optimization variables and the low-temperature cold start model, determining the cold start time when the low-temperature cold start model meets the cold start success condition, and taking the cold start time as the optimization target.

[0036] In some implementations, the optimization variables may be input into the low-temperature cold start model, and the low-temperature cold start model performs simulation based on the optimization variables to output the cold start time. Optionally, the time required for a successful cold start of the low-temperature cold start model may be used as the cold start time, and the cold start time may be used as the optimization target to determine a cold start time with a short cold start time.

[0037] Optionally, the lowest membrane in the fuel cell stack can be used as the target membrane, and by judging whether the electrode temperature of the target membrane reaches the set temperature value, it can be judged whether the low-temperature cold start model is successfully cold started. Optionally, if the target membrane electrode temperature reaches 0°C, it is determined that the low-temperature cold start model is successfully cold started, and the time required for the cold start is used as the cold start time.

[0038] S104, based on the optimization variables and the optimization target, a particle swarm algorithm is used to generate a particle population, and an iterative global optimization is performed in the particle population.

[0039] In some implementations, the optimization variables can be used as particles in a particle population, and the optimization target can be used as the fitness value of the particle to generate a particle population based on the particles. By performing iterative global optimization in the particle population, the particle in the optimal position can be determined, and the optimization variables and optimization targets corresponding to the particles can be used as the optimal parameters of the cold start model.

[0040] S105, obtaining the local optimal solution of any iteration, and performing the next iteration based on the local optimal solution and the low-temperature cold start model, until the iteration is completed to obtain the global optimal solution that meets the optimization constraints, and the global optimal solution at least includes the optimal cold start time of the low-temperature cold start model.

[0041] In some implementations, the global optimal position of the particle population at the end of any iteration can be obtained, and the position can be used as the local optimal solution. The particles on the local optimal solution, that is, the optimization variables, can be input into the low-temperature cold start model for simulation, and it can be determined whether the optimization variables meet the constraints of the model. The optimization variables that meet the constraints can be used as the optimization variables for the next iteration, so as to continue to iterate the global optimization in the optimization variables until the iteration ends. The global optimal solution, that is, the particles at the position corresponding to the global optimal solution, can be obtained. By obtaining the fitness value corresponding to the particle, the optimal cold start time of the low-temperature cold start model can be determined. By determining the optimization variable corresponding to the particle, the optimal initial membrane water content corresponding to the global optimal solution and the optimal segmented step current can be determined, so that the model can be cold started according to the optimal initial membrane water content and the optimal segmented step current.

[0042] Optionally, the iteration may be terminated when the number of iterations reaches a threshold. Optionally, the optimization constraint may be determined based on the minimum membrane electrode temperature of the fuel cell stack, the minimum output voltage of the stack, and the sum of ice and supercooled water saturation in the cathode catalyst layer of each fuel cell.

[0043] For example, the optimization constraint condition is: the minimum membrane electrode temperature T of the fuel cell stack MEA >273.15K, minimum output voltage of battery stack V min>0.2V, the sum of ice and supercooled water saturation in the cathode catalyst layer of each fuel cell ice +s lq <0.95.

[0044] In the optimization method for low-temperature cold start of a fuel cell stack provided in an embodiment of the present application, by constructing a low-temperature cold start model of the fuel cell stack and determining the optimization variables of the low-temperature cold start model, the cold start time corresponding to the optimization variables can be determined by inputting the optimization variables into the low-temperature cold start model, and the cold start time is used as the optimization target to generate a particle population. By iterative global optimization in the particle population, the optimal cold start time corresponding to the low-temperature cold start model can be determined. By loading according to the segmented step current, the cold start time can be further optimized compared to the constant current cold start mode. By taking the cold start time as the optimization target and establishing the optimization constraint conditions for the cold start of the model, the cold start time can be reduced under the premise of ensuring the success of the low-temperature cold start of the stack.

[0045] Figure 2 is a flow chart of a method for optimizing a low temperature cold start of a fuel cell stack according to an exemplary embodiment. Figure 2 As shown, the optimization method for low temperature cold start of a fuel cell stack in an embodiment of the present application includes but is not limited to the following steps:

[0046] S201, determining a low-temperature cold start model of the fuel cell stack based on internal parameters of the fuel cell stack.

[0047] In some implementations, the low temperature cold start model can be established by determining the motion process of each internal parameter and based on the motion process. That is, the electrode kinetic process, charge transfer process, gas transfer process, membrane water and supercooled water transfer process and heat transfer process can be determined as the motion process of each internal parameter.

[0048] S202, determining the initial membrane water content of the fuel cell stack and the segmented step current of the cold start, and using the initial membrane water content and the segmented step current as optimization variables.

[0049] In the embodiment of the present application, the implementation method of step S202 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0050] S203, based on the optimization variables and the low-temperature cold start model, determining the cold start time when the low-temperature cold start model meets the cold start success condition, and taking the cold start time as the optimization target.

[0051] In some implementations, the optimization variables are input into the low-temperature cold start model, and the temperature of the target membrane electrode in the fuel cell stack is obtained. The target membrane may be the lowest membrane in the fuel cell stack. By taking the temperature of the target membrane electrode reaching the set temperature as a success condition, and judging whether the temperature of the target membrane electrode reaches the set temperature, it can be determined whether the low-temperature cold start model is successfully cold started. That is, in response to the temperature reaching the set temperature, it is determined that the success condition of the cold start is met, and the time required for the successful cold start is taken as the cold start time.

[0052] S204, based on the optimization variables and the optimization target, a particle swarm algorithm is used to generate a particle population, and an iterative global optimization is performed in the particle population.

[0053] In the embodiment of the present application, the implementation method of step S204 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0054] S205, obtaining the local optimal solution of any iteration.

[0055] In the embodiment of the present application, the implementation method of step S205 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0056] S206, inputting the local optimal solution into the low-temperature cold start model to perform a cold start simulation, and determining whether the cold start simulation satisfies the optimization constraint condition.

[0057] In some implementations, the optimization constraint condition may be that the minimum membrane electrode temperature of the fuel cell stack is greater than a set temperature, the minimum output voltage of a single cell of the stack is greater than a set voltage, and the sum of the ice and supercooled water saturation in the cathode catalyst layer of each fuel cell is less than a set value. MEA >273.15K, minimum output voltage of battery stack V min >0.2V, the sum of ice and supercooled water saturation in the cathode catalyst layer of each fuel cell ice +s lq <0.95.

[0058] Optionally, the local optimal solution includes multiple particles. The local optimal solution is input into the low-temperature cold start model for cold start simulation, and the particle with successful cold start in the local optimal solution is determined according to the cold start success condition, and it is determined from the particle whether the cold start simulation corresponding to the particle meets the optimization constraint condition.

[0059] S207 , in response to satisfying the optimization constraint condition, determining a plurality of candidate cold start times corresponding to the local optimal solution, and determining a minimum candidate cold start time from the candidate cold start times as the first cold start time.

[0060] In some implementations, when determining whether the cold start simulation corresponding to a particle satisfies the optimization constraint, the fitness values ​​of multiple particles satisfying the optimization constraint can be determined based on the local optimal solution as multiple candidate cold start times, and the candidate cold start times are compared to determine the minimum candidate cold start time as the first cold start time. Optionally, the first cold start time can correspond to multiple optimization variables, that is, the same cold start time can be obtained according to different optimization variables.

[0061] S208, determining a first optimization variable corresponding to the first cold start time, and performing next iteration based on the first cold start time and the first optimization variable, until the number of iterations reaches a set number, the iteration ends, and a global optimal solution is obtained.

[0062] In some implementations, by determining the particle corresponding to the first cold start time and using the optimization variable corresponding to the particle as the first optimization variable, the first cold start time can be used as the optimization target of the next iteration, and the first optimization variable can be used as the optimization variable of the next iteration to perform the next iteration until the number of iterations reaches the set number and the iteration is terminated, so that the global optimal solution can be obtained.

[0063] For example, if the number of times is set to 50, a cold start simulation is performed based on the local optimal solution outputted at the 50th iteration, and the particle that successfully cold starts in the local optimal solution is determined according to the cold start success condition, and the particle whose cold start simulation satisfies the optimization constraint condition is determined from the particle. The fitness value of the particle that satisfies the optimization constraint condition, that is, the cold start time, is determined, and the cold start time is compared to determine the minimum cold start time, which is the cold start time of the global optimal solution.

[0064] In other words, the optimal cold start time can be determined according to the global optimal solution, and the optimal particles, that is, the optimal optimization variables: the optimal initial membrane water content, and the optimal segmented step current, can be determined according to the optimal cold start time, so as to cold start the model according to the optimal initial membrane water content and the optimal segmented step current.

[0065] In the optimization method for low-temperature cold start of a fuel cell stack provided in an embodiment of the present application, by constructing a low-temperature cold start model of the fuel cell stack and determining the optimization variables of the low-temperature cold start model, by inputting the optimization variables into the low-temperature cold start model, the cold start time corresponding to the optimization variables can be determined, and the cold start time is used as the optimization target to generate a particle population. By iterative global optimization in the particle population, the next iteration is performed according to the local optimal solution of each iteration to determine the global optimal solution of the particle population, and then the optimal cold start time corresponding to the low-temperature cold start model, as well as the optimal initial membrane water content and the optimal segmented step current can be determined. By loading according to the segmented step current, the cold start time can be further optimized compared to the constant current cold start mode. By taking the cold start time as the optimization target and establishing the optimization constraint conditions for the cold start of the model, the cold start time can be reduced under the premise of ensuring the success of the low-temperature cold start of the stack.

[0066] Figure 3 is a flow chart of a method for optimizing a low temperature cold start of a fuel cell stack according to an exemplary embodiment. Figure 3 As shown, the optimization method for low temperature cold start of a fuel cell stack in an embodiment of the present application includes but is not limited to the following steps:

[0067] S301, determining a low-temperature cold start model of the fuel cell stack based on internal parameters of the fuel cell stack.

[0068] In the embodiment of the present application, the implementation method of step S301 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0069] S302, determining the initial membrane water content of the fuel cell stack and the segmented step current of the cold start, and taking the initial membrane water content and the segmented step current as optimization variables.

[0070] In some implementations, the membrane water content is related to the temperature, and the saturated membrane water content of the proton exchange membrane is determined based on the temperature of the proton exchange membrane of the fuel cell stack, and the initial membrane water content is determined based on the saturated membrane water content of the proton exchange membrane. Optionally, the saturated membrane water content of the proton exchange membrane can be used as the upper limit of the initial membrane water content, and the initial membrane water content can be determined by setting the lower limit of the initial membrane water content.

[0071] Alternatively, the formula for calculating the saturated membrane water content of the proton exchange membrane is as follows:

[0072] λ sat =6.346×10 -5 T 3 -0.04306T 2 +9.762T-731.4 223.15K,,T <Tfre (1)

[0073] Among them, λ sat represents the saturated membrane water content of the proton exchange membrane, T represents the temperature of the proton exchange membrane, T fre Indicates the freezing temperature point.

[0074] Optionally, the membrane electrode temperature can be divided into ranges, and the current magnitude in different temperature ranges can be determined, and the segmented step current for cold start can be determined based on the corresponding relationship between different temperature ranges and current magnitudes. The determination of the initial membrane water content and the segmented step current is as follows:

[0075]

[0076] Among them, λ init represents the initial film water content, I a ,I b ,I c ,I d represents the current, T MEA Indicates the membrane electrode temperature.

[0077] Furthermore, the initial membrane water content and the step-by-step current can be used as optimization variables. Let the optimization variable be X, then X = (λ init ,I a ,I b ,I c ,I d ).

[0078] S303, based on the optimization variables and the low-temperature cold start model, determining the cold start time when the low-temperature cold start model meets the cold start success condition, and taking the cold start time as the optimization target.

[0079] In the embodiment of the present application, the implementation method of step S303 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0080] S304, based on the optimization variables and the optimization target, a particle swarm algorithm is used to generate a particle population, and an iterative global optimization is performed in the particle population.

[0081] In the embodiment of the present application, the implementation method of step S304 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0082] S305 , for the kth iteration, obtaining the particle position i,k-1 of the i-th particle in the particle population after the k-1th iteration, and the focusing position k-1 of the particle in the particle population.

[0083] S306, based on the particle position i,k-1 and the focus position k-1, determine the particle position i,k after the kth iteration.

[0084] In some implementations, when performing the kth iteration, the particle position i,k after the kth iteration can be calculated by obtaining the particle position i,k-1 of the i-th particle after the k-1th iteration and the focus position k-1 of the particle in the particle population. Optionally, the particle position can be determined according to the decision vector corresponding to the particle. The decision vector is a velocity vector and a position vector.

[0085] That is, by determining the particle velocity i,k-1 of the particle after the k-1th iteration and the individual optimal position of the particle in the particle population. Further, the inertia weight of the particle is obtained, and based on the inertia weight, the particle velocity i,k-1, the particle position i,k-1, the focus position k-1 and the individual optimal position, the particle velocity i,k of the particle after the kth iteration is determined.

[0086] Optionally, after determining the particle speed i,k, the particle position i,k may be determined based on the particle speed i,k and the particle position i,k-1.

[0087] Optionally, the formula for calculating the particle velocity i,k is as follows:

[0088] v i (k) = ωv i (k-1)+c1r1(pbest i -x i (k-1))+c2r2(gbest-x i (k-1))(3)

[0089] Among them, v i (k) represents the particle velocity i,k, ω represents the inertia weight, c1 and c2 represent the learning factors, r1 and r2 represent random numbers, gbest represents the focus position k-1, and pbest represents the focus position k-1. i represents the optimal position of an individual, x i (k-1) represents the particle position i,k-1.

[0090] Furthermore, the particle position i,k can be calculated based on the particle velocity i,k calculated by formula (3). The calculation formula is as follows:

[0091] x i (k) = x i (k-1)+v i (k)(4)

[0092] Among them, x i (k) represents the particle position i, k, v i(k) represents the particle velocity i,k,x i (k-1) represents the particle position i,k-1.

[0093] It is understandable that the inertia weight represents the tendency of particles to maintain inertial motion. The smaller the inertia weight, the higher the local search ability of the particle population and the better the convergence, but this also weakens the global optimization ability of the particle population, and it is easy to fall into the local optimal solution and fail to obtain the global optimal solution. Therefore, the value of the inertia weight needs to be adjusted during the optimization process.

[0094] Optionally, the inertia weight may be determined based on the number of iterations of the iterative global optimization. The inertia weight is determined based on the maximum number of iterations, the number of iterations, the maximum inertia weight, and the minimum inertia weight by determining the maximum number of iterations and the current number of iterations of the particle, and obtaining the maximum inertia weight and the minimum inertia weight.

[0095] Optionally, the formula for calculating the inertia weight is as follows:

[0096]

[0097] Among them, ω represents the inertia weight, it max represents the number of iterations, it represents the current number of iterations, ω max represents the maximum inertia weight, ω min Represents the minimum inertia weight.

[0098] S307, during the iteration process, determine whether the focus position k-1 is the same as the particle position i,k. If they are the same, determine that the particle position i,k is the optimal position, and take the particle at the optimal position as the local optimal solution.

[0099] In some implementations, after determining the particle position i, k, it is possible to determine whether the particles are focused on the same position, that is, to determine whether the focus position k-1 is the same as the particle position i, k. If they are the same, it means that the particles are focused on the same position, then this position is the optimal position, and the particle at the optimal position is used as the local optimal solution.

[0100] Optionally, if the particles are not focused on the same position, that is, if the focusing position k-1 is different from the particle position i,k, the particle at the focusing position k-1 is taken as the local optimal solution, and the next iteration is performed based on the local optimal solution to determine the local optimal solution after the next iteration.

[0101] S308, performing the next iteration based on the local optimal solution and the low-temperature cold start model, until the iteration is completed to obtain a global optimal solution that meets the optimization constraints, and the global optimal solution at least includes the optimal cold start time of the low-temperature cold start model.

[0102] In the embodiment of the present application, the implementation method of step S308 can be implemented by any method in the embodiments of the present application, which is not limited here and will not be repeated.

[0103] In the optimization method for low-temperature cold start of a fuel cell stack provided in an embodiment of the present application, by constructing a low-temperature cold start model of a fuel cell stack and determining the optimization variables of the low-temperature cold start model, by inputting the optimization variables into the low-temperature cold start model, the cold start time corresponding to the optimization variables can be determined, and the cold start time is used as the optimization target to generate a particle population. By iterative global optimization in the particle population, by determining the focusing position of the particles, if the particles are focused on a certain position, the particles at the position can be used as the local optimal solution, and the iteration is continued until the global optimal solution is determined at the end of the iteration, so as to determine the optimal cold start time corresponding to the low-temperature cold start model according to the global optimal solution. By loading according to the segmented step current, the cold start time can be further optimized compared to the constant current cold start mode. By taking the cold start time as the optimization target and establishing the optimization constraint conditions for the cold start of the model, the cold start time can be reduced under the premise of ensuring the success of the low-temperature cold start of the stack.

[0104] Based on the above embodiments, the embodiments of the present application can explain the motion process of determining each internal parameter, such as Figure 4 As shown, the motion process of determining each internal parameter in the embodiment of the present application includes but is not limited to the following steps:

[0105] S401, determining the electrode kinetic process based on the electrochemical reaction rates of the cathode and anode of the fuel cell stack.

[0106] In some implementations, the movement process of the internal parameters of the fuel cell stack includes: electrode kinetics process, charge transfer process, gas transfer process, membrane water and supercooled water transfer process and heat transfer process.

[0107] In some implementations, in a fuel cell stack, hydrogen is oxidized in the anode catalyst layer, and oxygen is reduced in the cathode catalyst layer to generate water. Optionally, the electrochemical reaction rates of the cathode and anode of the fuel cell stack can be calculated based on the molar concentrations of hydrogen and oxygen, and the electrochemical reaction rates can be used as electrode kinetic processes.

[0108] Alternatively, the formula for calculating the electrochemical reaction rates at the cathode and anode is as follows:

[0109]

[0110] Among them, j a represents the electrochemical reaction rate of the anode, j c represents the cathode electrochemical reaction rate, s iceand lq is the volume fraction of ice and liquid water in the cathode catalyst layer, and is the molar concentration of oxygen and hydrogen in the catalyst layer, and is the reference molar concentration of oxygen and hydrogen, α a and α c is the charge transfer coefficient for oxidation and reduction reactions, η is the electrochemical reaction overpotential, T is the temperature, R is the gas constant, and F is the Faraday constant.

[0111] Alternatively, the formula for calculating the electrochemical reaction overpotential η is as follows:

[0112] η=φ s -φ e -E eq (7)

[0113] Where η is the electrochemical reaction overpotential, φ s represents the electrode, φ e represents the electrolyte potential, E eq is the thermodynamic equilibrium potential. Among them, the thermal equilibrium potential corresponding to the hydrogen oxidation reaction at the anode is zero. The thermal equilibrium potential corresponding to the cathode can be calculated according to the Nernst equation, and the calculation formula is as follows:

[0114]

[0115] Among them, E eq is the thermodynamic equilibrium potential, T is the temperature, T0 is the reference temperature, R is the gas constant, F is the Faraday constant, and p is the gas pressure.

[0116] S402, determining a charge transfer process based on an effective conductivity of charges in a fuel cell stack.

[0117] In some implementations, the charges in the fuel cell stack are divided into electrons and protons, and the transfer rates of electrons and protons can be determined based on the effective electrical conductivity of electrons and protons as a charge transfer process. Optionally, the formula for calculating the transfer rates of electrons and protons is as follows:

[0118]

[0119] Among them, -j represents the transfer rate of electrons, j represents the transfer rate of protons, represents the effective conductivity of the electrode, is the effective conductivity of the electrolyte, Represents divergence.

[0120] In some implementations, since the electrodes and electrolytes are porous media, a correction can be made to the conductivity. The correction formula is as follows:

[0121]

[0122] in, represents the effective conductivity of the electrode, is the effective conductivity of the electrolyte, ε represents the porosity, ω represents the volume fraction of ionomer, σ m represents the conductivity of the proton exchange membrane, σ s Indicates the electrode conductivity.

[0123] S403, determining the reaction gas of the fuel cell stack, and determining the gas transfer process based on the molar concentration of the reaction gas.

[0124] In some implementations, the reaction gases of the fuel cell stack are hydrogen and oxygen, and the gas transfer process can be determined based on the molar concentration of the reaction gases, that is, the molar concentration of hydrogen and oxygen, combined with the material conservation equation. Optionally, the calculation formula is as follows:

[0125]

[0126] Where C represents the molar concentration, S i represents the gas source term, ε represents the porosity, represents the effective diffusion coefficient of gas, s lq Indicates the supercooled water saturation, s ice represents ice saturation, t represents time, and x represents the dimension in the thickness direction.

[0127] Alternatively, the gas source term can be determined based on the electrochemical reaction rate as follows:

[0128]

[0129] Wherein, j represents the electrochemical reaction rate, M represents the molar mass, F represents the Faraday constant, ACL represents the anode catalyst layer, and CCL represents the cathode catalyst layer.

[0130] Optionally, in the gas diffusion layer, the gas effective diffusion coefficient can be corrected according to the Bruggeman formula. In the catalyst layer, since the pores of the catalyst layer are in the size of tens of nanometers, the correction formula for the effective diffusion coefficient of the gas in the catalyst layer is as follows:

[0131]

[0132] in, represents, ε0 represents, D i represents the gas diffusion coefficient, τ c and τd Indicates the correction parameter.

[0133] S404, determining a first physical property of membrane water and a second physical property of supercooled water in a fuel cell stack, and determining a membrane water and supercooled water transfer process based on the first physical property and the second physical property.

[0134] It can be understood that the water transport inside the proton membrane is mainly dominated by two parts. One is the potential drag. Because the water molecules inside the proton membrane combine with the water sulfonic acid to form H + SO3 is transferred under the action of potential difference; the second is reverse diffusion water, because there is a concentration gradient of membrane water inside the proton membrane, resulting in concentration diffusion. In other words, the first physical properties of membrane water include: the density of the proton membrane, the equivalent molar mass of the proton membrane, and the electrolyte current density. Optionally, the membrane water transfer process can be determined based on the mass conservation equation, and the calculation formula is as follows:

[0135]

[0136] Among them, S mw represents the membrane water source term, ρ m represents the density of the proton membrane, EW represents the equivalent molar mass of the proton membrane, I ion represents the electrolyte current density, D m represents the membrane water diffusion coefficient, ω represents the proton membrane volume fraction, K d represents the membrane water diffusion coefficient correction term.

[0137] Optionally, calculate the membrane water diffusion coefficient D m The formula is as follows:

[0138]

[0139] Among them, λ m Indicates the water content of the membrane.

[0140] In some implementations, for the supercooled water transfer process, it can be calculated according to the mass conservation equation, and the calculation formula is as follows:

[0141]

[0142] Among them, K lq represents the relative permeability of liquid water, which is related to the saturation of liquid water and ice, μ lq represents the dynamic viscosity of liquid water, p c represents the capillary pressure due to the surface tension of liquid water, ρ lq represents the density of liquid water, S lq Indicates supercooled water saturation.

[0143] Alternatively, the relative permeability of liquid water can be determined based on the absolute permeability of the porous medium, and the calculation formula is as follows:

[0144]

[0145] Among them, K lq represents the relative permeability of liquid water, K0 represents the absolute permeability of porous media, s lq Indicates the supercooled water saturation, s ice Indicates ice saturation.

[0146] Optionally, calculate the capillary pressure p due to the surface tension of liquid water c The formula is as follows:

[0147]

[0148] Among them, σ lq represents the surface tension of liquid water, which is temperature-dependent, that is, σ lq =-0.0001676×T+0.1218.

[0149] S405, determining thermal parameters of the fuel cell stack, and based on the thermal parameters, determining a heat transfer process.

[0150] In some implementations, the thermal parameters of the fuel cell stack include: effective volume heat capacity, effective thermal conductivity, and fuel cell heat source. That is, the heat transfer process can be determined based on the effective volume heat capacity, effective thermal conductivity, and fuel cell heat source, and the calculation formula is as follows:

[0151]

[0152] Among them, (ρc p ) eff Represents the effective volume heat capacity, -k eff represents the effective thermal conductivity, S heat Represents the fuel cell heat source.

[0153] It is understandable that since there are gas flow channels and coolant flow channels in the bipolar plates of the fuel cell stack, and the heat capacity and thermal conductivity of the coolant and the graphite bipolar plates are different, the bipolar plates can be regarded as uniform materials to calculate the corresponding equivalent heat capacity and equivalent heat transfer coefficient. The calculation formula for the effective heat capacity of each component of the fuel cell is as follows:

[0154]

[0155] Among them, ρ m represents the density of the proton membrane, is the effective heat capacity of the proton membrane, represents the effective heat capacity of the catalyst layer, is the effective heat capacity of the gas diffusion layer, represents the effective heat capacity of the bipolar plate, ω represents the proton membrane volume fraction, c represents the specific heat capacity, ε represents porosity, A represents the active area of ​​the fuel cell, V represents volume, and δ represents thickness.

[0156] In the optimization method for low-temperature cold start of a fuel cell stack provided in the embodiment of the present application, the internal parameters of the fuel cell stack are determined, and a low-temperature cold start model of the fuel cell stack is constructed according to the movement process of the internal parameters. This helps to establish a more accurate low-temperature cold start model and improve the prediction ability and reliability of the model.

[0157] Figure 5 Shown is a flow chart of the low-temperature cold start optimization method. Step 1, according to the movement process of the internal parameters of the fuel cell stack, a cold start numerical model of the fuel cell stack is constructed according to the movement process as a low-temperature cold start model. Step 2, determine the cold start time for a successful cold start as the optimization target, and determine the optimization constraints based on the minimum membrane electrode temperature of the fuel cell stack, the minimum output voltage of the single chip, and the ice and supercooled water saturation. Step 3, determine the initial membrane water content and the segmented step current, and use the initial membrane water content and the segmented step current as optimization variables to generate a particle population according to the optimization variables and the optimization target, and perform iterative global optimization in the particle population to obtain the optimal initial membrane water content and segmented step current.

[0158] As an example, Table 1 shows the results before and after the low-temperature cold start optimization of the low-temperature cold start model at -20°C using the low-temperature cold start optimization method for the fuel cell stack proposed in this application. Figure 6 Shown is a schematic diagram of the changes in the terminal output voltage and the minimum membrane electrode temperature after low-temperature cold start optimization at -20°C.

[0159] Table 1

[0160]

[0161] Table 2 shows the results before and after optimizing the low-temperature cold start at -25°C using the optimization method for the low-temperature cold start of the fuel cell stack proposed in this application. Figure 7 Shown is a schematic diagram of the changes in the terminal output voltage and the minimum membrane electrode temperature after low-temperature cold start optimization at -25°C.

[0162] Table 2

[0163]

[0164] In order to implement the above-mentioned embodiment, the present application also proposes an optimization device for low-temperature cold start of a fuel cell stack.

[0165] Figure 8 A schematic structural diagram of a fuel cell stack low-temperature cold start optimization device provided in an embodiment of the present application.

[0166] like Figure 8 As shown, the optimization device 800 for low temperature cold start of a fuel cell stack includes:

[0167] A first determination module 801 is used to determine a low-temperature cold start model of the fuel cell stack based on internal parameters of the fuel cell stack;

[0168] A second determination module 802 is used to determine the initial membrane water content of the fuel cell stack and the segmented step current of the cold start, and use the initial membrane water content and the segmented step current as optimization variables;

[0169] A third determination module 803 is used to determine the cold start time when the low-temperature cold start model meets the cold start success condition based on the optimization variable and the low-temperature cold start model, and use the cold start time as an optimization target;

[0170] A generation module 804 is used to generate a particle population using a particle swarm algorithm based on the optimization variable and the optimization target, and perform iterative global optimization in the particle population;

[0171] Iteration module 805 is used to obtain the local optimal solution of any iteration, and perform the next iteration based on the local optimal solution and the low-temperature cold start model, until the iteration is completed to obtain the global optimal solution that meets the optimization constraints, and the global optimal solution at least includes the optimal cold start time of the low-temperature cold start model.

[0172] In a possible implementation of an embodiment of the present application, the third determination module 803 is also used to: input the optimization variables into the low-temperature cold start model and obtain the temperature of the target membrane electrode in the fuel cell stack; in response to the temperature reaching the set temperature, determine whether the success conditions for the cold start are met, and use the time required for a successful cold start as the cold start time.

[0173] In a possible implementation of an embodiment of the present application, the iteration module 805 is also used to: input the local optimal solution into the low-temperature cold start model for cold start simulation, and determine whether the cold start simulation satisfies the optimization constraint; in response to satisfying the optimization constraint, determine multiple candidate cold start times corresponding to the local optimal solution, and determine the minimum candidate cold start time from the candidate cold start times as the first cold start time; determine the first optimization variable corresponding to the first cold start time, and perform the next iteration based on the first cold start time and the first optimization variable, until the number of iterations reaches the set number of iterations to end the iteration and obtain the global optimal solution.

[0174] In a possible implementation of an embodiment of the present application, the iteration module 805 is further used to: for the kth iteration, obtain the particle position i,k-1 of the i-th particle in the particle population after the k-1th iteration, and the focusing position k-1 of the particle in the particle population; based on the particle position i,k-1 and the focusing position k-1, determine the particle position i,k after the kth iteration; during the iteration process, determine whether the focusing position k-1 is the same as the particle position i,k; if they are the same, determine the particle position i,k as the optimal position, and use the particle at the optimal position as the local optimal solution.

[0175] In a possible implementation of an embodiment of the present application, the iteration module 805 is also used to: if the focusing position k-1 is different from the particle position i,k, take the particle at the focusing position k-1 as the local optimal solution, and perform the next iteration based on the local optimal solution to determine the local optimal solution after the next iteration.

[0176] In a possible implementation manner of an embodiment of the present application, the iteration module 805 is further used to: determine the particle velocity i,k-1 of the particle after the k-1th iteration, and the individual optimal position of the particle in the particle population; obtain the inertia weight of the particle, and determine the particle velocity i,k of the particle after the kth iteration based on the inertia weight, the particle velocity i,k-1, the particle position i,k-1, the focusing position k-1 and the individual optimal position; determine the particle position i,k based on the particle velocity i,k and the particle position i,k-1.

[0177] In a possible implementation of an embodiment of the present application, the iteration module 805 is further used to: determine the maximum number of iterations and the current number of iterations of the particle; obtain the maximum inertia weight and the minimum inertia weight, and determine the inertia weight based on the maximum number of iterations, the number of iterations, and the maximum inertia weight and the minimum inertia weight.

[0178] In a possible implementation of the embodiment of the present application, the second determination module 802 is further used to: determine the saturated membrane water content of the proton exchange membrane based on the temperature of the proton exchange membrane of the fuel cell stack; and determine the initial membrane water content based on the saturated membrane water content of the proton exchange membrane.

[0179] In a possible implementation of the embodiment of the present application, the first determination module 801 is further used to: determine the movement process of each of the internal parameters, and establish the low-temperature cold start model based on the movement process.

[0180] In a possible implementation of the embodiment of the present application, the first determination module 801 is also used to: determine the electrode kinetic process based on the electrochemical reaction rates of the cathode and anode of the fuel cell stack; determine the charge transfer process based on the effective conductivity of the charge in the fuel cell stack; determine the reaction gas of the fuel cell stack, and determine the gas transfer process based on the molar concentration of the reaction gas; determine the first physical property of membrane water and the second physical property of supercooled water in the fuel cell stack, and determine the membrane water and supercooled water transfer process based on the first physical property and the second physical property; determine the thermal parameters of the fuel cell stack, and determine the heat transfer process based on the thermal parameters; wherein the motion process includes: electrode kinetic process, charge transfer process, gas transfer process, membrane water and supercooled water transfer process and heat transfer process.

[0181] In the optimization device for low-temperature cold start of a fuel cell stack provided in an embodiment of the present application, by constructing a low-temperature cold start model of the fuel cell stack and determining the optimization variables of the low-temperature cold start model, by inputting the optimization variables into the low-temperature cold start model, the cold start time corresponding to the optimization variables can be determined, and the cold start time is used as the optimization target to generate a particle population. By iterative global optimization in the particle population, the optimal cold start time corresponding to the low-temperature cold start model can be determined. By loading according to the segmented step current, the cold start time can be further optimized compared to the constant current cold start mode. By taking the cold start time as the optimization target and establishing the optimization constraint conditions for the cold start of the model, the cold start time can be reduced under the premise of ensuring the success of the low-temperature cold start of the stack.

[0182] It should be noted that the aforementioned explanation of the embodiment of the optimization method for low-temperature cold start of a fuel cell stack is also applicable to the optimization device for low-temperature cold start of a fuel cell stack of this embodiment, and will not be repeated here.

[0183] In order to implement the above embodiments, the present application also proposes an electronic device, comprising: a processor, and a memory communicatively connected to the processor; the memory stores computer-executable instructions; the processor executes the computer-executable instructions stored in the memory to implement the method provided by the above embodiments.

[0184] In order to implement the above embodiments, the present application also proposes a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement the methods provided by the above embodiments.

[0185] In order to implement the above embodiments, the present application also proposes a computer program product, including a computer program, which implements the methods provided by the above embodiments when executed by a processor.

[0186] The collection, storage, use, processing, transmission, provision and application of user personal information involved in this application are in compliance with relevant laws and regulations and do not violate public order and good morals.

[0187] It should be noted that personal information from users should be collected for legitimate and reasonable purposes and should not be shared or sold outside of these legitimate uses. In addition, such collection / sharing should be carried out after receiving the user's informed consent, including but not limited to notifying the user to read the user agreement / user notice and sign the agreement / authorization including authorization of relevant user information before the user uses the function. In addition, any necessary steps should be taken to protect and safeguard access to such personal information data and ensure that others who have access to personal information data comply with its privacy policy and procedures.

[0188] This application is expected to provide an implementation scheme for users to selectively block the use or access of personal information data. That is, this application is expected to provide hardware and / or software to prevent or block access to such personal information data. Once the personal information data is no longer needed, risks can be minimized by limiting data collection and deleting data. In addition, when applicable, personal identifiers are removed from such personal information to protect the privacy of users.

[0189] In the description of the aforementioned embodiments, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present application. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0190] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of this application, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0191] Any process or method description in a flowchart or otherwise described herein may be understood to represent a module, fragment or portion of code comprising one or more executable instructions for implementing the steps of a custom logical function or process, and the scope of the preferred embodiments of the present application includes alternative implementations in which functions may not be performed in the order shown or discussed, including performing functions in a substantially simultaneous manner or in the reverse order depending on the functions involved, which should be understood by technicians in the technical field to which the embodiments of the present application belong.

[0192] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute the instructions), or in combination with these instruction execution systems, devices or apparatuses. For the purpose of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in combination with these instruction execution systems, devices or apparatuses. More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk box (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), a fiber optic device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium and then editing, interpreting or processing in other suitable ways if necessary, and then stored in a computer memory.

[0193] It should be understood that the various parts of the present application can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0194] A person skilled in the art may understand that all or part of the steps in the method for implementing the above-mentioned embodiment may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable storage medium, which, when executed, includes one or a combination of the steps of the method embodiment.

[0195] In addition, each functional unit in each embodiment of the present application may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a computer-readable storage medium.

[0196] The storage medium mentioned above may be a read-only memory, a magnetic disk or an optical disk, etc. Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and cannot be understood as limiting the present application. A person of ordinary skill in the art may change, modify, replace and modify the above embodiments within the scope of the present application.

Claims

1. A method for optimizing low-temperature cold start of a fuel cell stack, characterized in that: include: Determining a low-temperature cold start model of the fuel cell stack based on internal parameters of the fuel cell stack; Determining the initial membrane water content of the fuel cell stack and the segmented step current of the cold start, and using the initial membrane water content and the segmented step current as optimization variables; Based on the optimization variables and the low-temperature cold start model, determining a cold start time when the low-temperature cold start model satisfies a successful cold start condition, and taking the cold start time as an optimization target; Based on the optimization variables and the optimization target, a particle swarm algorithm is used to generate a particle population, and an iterative global optimization is performed in the particle population; The local optimal solution of any iteration is obtained, and the next iteration is performed based on the local optimal solution and the low-temperature cold start model, until the iteration is completed to obtain a global optimal solution that meets the optimization constraints, and the global optimal solution at least includes the optimal cold start time of the low-temperature cold start model.

2. The method according to claim 1, characterized in that The determining, based on the optimization variable and the low-temperature cold start model, a cold start time when the low-temperature cold start model satisfies a successful cold start condition includes: Inputting the optimization variables into the low-temperature cold start model, and obtaining the target membrane electrode temperature in the fuel cell stack; In response to the temperature reaching the set temperature, it is determined that the success condition of the cold start is met, and the time required for the cold start to succeed is used as the cold start time.

3. The method according to claim 1, characterized in that The step of performing the next iteration based on the local optimal solution and the low-temperature cold start model until the iteration is completed and a global optimal solution satisfying the optimization constraint condition is obtained includes: Inputting the local optimal solution into the low-temperature cold start model to perform a cold start simulation, and determining whether the cold start simulation satisfies the optimization constraint condition; In response to satisfying the optimization constraint condition, determining a plurality of candidate cold start times corresponding to the local optimal solution, and determining a minimum candidate cold start time from the candidate cold start times as a first cold start time; A first optimization variable corresponding to the first cold start time is determined, and based on the first cold start time and the first optimization variable, the next iteration is performed until the number of iterations reaches a set number, and the iteration is terminated to obtain the global optimal solution.

4. The method according to claim 1, characterized in that The obtaining of the local optimal solution of any iteration includes: For the kth iteration, obtaining the particle position i,k-1 of the i-th particle in the particle population after the k-1th iteration, and the focusing position k-1 of the particle in the particle population; Determine the particle position i,k after the kth iteration based on the particle position i,k-1 and the focus position k-1; During the iteration process, it is determined whether the focus position k-1 is the same as the particle position i,k. If they are the same, the particle position i,k is determined to be the optimal position, and the particle at the optimal position is used as the local optimal solution.

5. The method according to claim 4, characterized in that The method further comprises: If the focus position k-1 is different from the particle position i,k, the particle at the focus position k-1 is taken as the local optimal solution, and the next iteration is performed based on the local optimal solution to determine the local optimal solution after the next iteration.

6. The method according to claim 4, characterized in that The step of determining the particle position i,k after the kth iteration based on the particle position i,k-1 and the focus position k-1 comprises: Determine the particle velocity i,k-1 of the particle after the k-1th iteration, and the individual optimal position of the particle in the particle population; Obtaining the inertia weight of the particle, and determining the particle velocity i,k of the particle after the kth iteration based on the inertia weight, the particle velocity i,k-1, the particle position i,k-1, the focus position k-1 and the individual optimal position; Based on the particle velocity i,k and the particle position i,k-1, the particle position i,k is determined.

7. The method according to claim 6, characterized in that The obtaining the inertia weight of the particle comprises: Determine the maximum number of iterations, and the current number of iterations of the particle; A maximum inertia weight and a minimum inertia weight are obtained, and the inertia weight is determined based on the maximum number of iterations, the number of iterations, and the maximum inertia weight and the minimum inertia weight.

8. The method according to claim 1, characterized in that The determining of the initial membrane water content of the fuel cell stack comprises: Determining a saturated membrane water content of a proton exchange membrane based on a temperature of a proton exchange membrane of the fuel cell stack; Based on the saturated membrane water content of the proton exchange membrane, an initial membrane water content is determined.

9. The method according to claim 1, characterized in that: The step of determining a low-temperature cold start model of the fuel cell stack based on internal parameters of the fuel cell stack includes: The motion process of each of the internal parameters is determined, and based on the motion process, the low-temperature cold start model is established.

10. The method according to claim 9, characterized in that The method comprises: Determining the electrode kinetics based on the electrochemical reaction rates of the cathode and anode of the fuel cell stack; Determining the charge transfer process based on the effective conductivity of the charge in the fuel cell stack; Determining a reactant gas of the fuel cell stack and determining the gas transfer process based on the molar concentration of the reactant gas; Determining a first physical property of membrane water and a second physical property of supercooled water in the fuel cell stack, and determining a transfer process of the membrane water and supercooled water based on the first physical property and the second physical property; Determining thermal parameters of the fuel cell stack, and determining the heat transfer process based on the thermal parameters; The movement process includes: electrode kinetic process, charge transfer process, gas transfer process, membrane water and supercooled water transfer process and heat transfer process.

11. A fuel cell stack low temperature cold start optimization device, characterized in that: include: A first determination module, configured to determine a low-temperature cold start model of the fuel cell stack based on internal parameters of the fuel cell stack; A second determination module is used to determine the initial membrane water content of the fuel cell stack and the segmented step current of the cold start, and use the initial membrane water content and the segmented step current as optimization variables; A third determination module is used to determine, based on the optimization variables and the low-temperature cold start model, a cold start time when the low-temperature cold start model meets the cold start success condition, and use the cold start time as an optimization target; A generation module, used to generate a particle population using a particle swarm algorithm based on the optimization variable and the optimization target, and perform iterative global optimization in the particle population; The iteration module is used to obtain the local optimal solution of any iteration, and perform the next iteration based on the local optimal solution and the low-temperature cold start model, until the iteration is completed to obtain the global optimal solution that meets the optimization constraints, and the global optimal solution at least includes the optimal cold start time of the low-temperature cold start model.

12. An electronic device, characterized in that: include: A processor, and a memory communicatively connected to the processor; The memory stores computer-executable instructions; The processor executes the computer-executable instructions stored in the memory to implement the method according to any one of claims 1 to 10.

13. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, which are used to implement the method according to any one of claims 1 to 10 when executed by a processor.

14. A computer program product, characterized in that The invention comprises a computer program, which implements the method according to any one of claims 1 to 10 when being executed by a processor.

Images