A method for optimizing the performance of a fuel cell

Abstract

The application discloses a kind of performance optimization methods of fuel cell, and the present application relates to the technical field of fuel cell, wherein including: obtaining the first optimization parameter of single fuel cell in stack;Based on the environmental data under different operating environments and preset genetic algorithm, the first optimization parameter is optimized, and the optimal parameter value of the first optimization parameter under different operating environments is obtained;Based on the optimal parameter value of the first optimization parameter under different operating environments, the polarization curve of fuel cell under different operating environments is determined, wherein the polarization curve is the three-section function curve of voltage about current density;Based on the preset flow network algorithm, the parameter value of the second optimization parameter of stack is updated and iterated, until the preset flow distribution condition is satisfied, the optimal flow distribution coefficient of stack is output;Based on the optimal flow distribution coefficient and the polarization curve under different operating environments, the optimization result of stack is determined.The application can solve the problem of uneven flow distribution of fuel cell stack.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of fuel cells, in particular to a performance optimization method of a fuel cell. BACKGROUND

[0002] At present, the global fossil fuel proportion has reached more than 80%, and the energy and environmental problems caused thereby have attracted widespread attention. Under the energy and environmental problems, hydrogen gas with high efficiency and cleanliness has become an ideal fuel with the potential to replace traditional fossil fuels. Among them, the fuel cell is an electrochemical device that can efficiently convert chemical energy into electrical energy. Compared with traditional combustion power generation, the fuel cell has the advantages of high thermal efficiency, less pollution, low noise, etc., and has been widely used in automobiles, ships, battery energy storage and other fields. Through the fuel cell, the chemical energy of hydrogen can be directly converted into electrical energy, and the proton exchange membrane (PEM) fuel cell can operate at a lower temperature, thereby reducing heat loss and having the advantages of zero emission and higher efficiency, and is considered to be the ideal energy conversion device and power generation equipment in the future. In order to realize the large-scale commercialization of fuel cells, the performance of fuel cells needs to be further optimized.

[0003] At present, with the continuous improvement of the power density of the fuel cell, the number of cells contained in the stack is increasing, and the problem of uneven flow distribution of the stack is increasingly prominent. The uneven flow distribution of the fuel cell stack will directly affect the performance of the stack, and in severe cases, it will even cause the service life of the fuel cell to decrease sharply. However, the existing technology has not yet proposed an effective means to solve the uneven flow distribution of the stack and improve the performance of the fuel cell. In order to solve the problem of uneven flow distribution of the fuel cell stack, simulation optimization research is needed to provide guidance for its design, and new design and optimization methods need to be adopted to improve the simulation optimization efficiency. SUMMARY

[0004] The present application provides a performance optimization method of a fuel cell, which can solve the problem of uneven flow distribution of the fuel cell stack, thereby improving the performance of the fuel cell.

[0005] According to a first aspect of an embodiment of the present application, a performance optimization method of a fuel cell is provided, comprising:

[0006] obtaining a first optimization parameter of a single fuel cell in a stack;

[0007] optimizing the first optimization parameter based on environmental data under different operating environments and a preset genetic algorithm to obtain an optimal parameter value of the first optimization parameter under different operating environments;

[0008] determine a polarization curve of the fuel cell under different operating environments based on the optimal parameter value of the first optimization parameter under the different operating environments, wherein the polarization curve is a three-segment function curve of voltage with respect to current density;

[0009] update and iterate the parameter value of the second optimization parameter of the stack based on a preset flow network algorithm until a preset flow distribution condition is met, and output an optimal flow distribution coefficient of the stack;

[0010] determine an optimization result of the stack based on the optimal flow distribution coefficient and the polarization curve under the different operating environments.

[0011] According to a second aspect of the embodiment of the present application, a performance optimization device of a fuel cell is provided, comprising:

[0012] an acquisition unit configured to acquire a first optimization parameter of a single fuel cell in a stack;

[0013] an optimization unit configured to optimize the first optimization parameter based on environmental data under different operating environments and a preset genetic algorithm, and obtain an optimal parameter value of the first optimization parameter under the different operating environments;

[0014] a first determination unit configured to determine a polarization curve of the fuel cell under the different operating environments based on the optimal parameter value of the first optimization parameter under the different operating environments, wherein the polarization curve is a three-segment function curve of voltage with respect to current density;

[0015] an iteration unit configured to update and iterate the parameter value of the second optimization parameter of the stack based on a preset flow network algorithm until a preset flow distribution condition is met, and output an optimal flow distribution coefficient of the stack;

[0016] a second determination unit configured to determine an optimization result of the stack based on the optimal flow distribution coefficient and the polarization curve under the different operating environments.

[0017] According to a third aspect of the embodiment of the present application, a computer readable storage medium is provided, which stores a computer program, and the program is executed by a processor to implement the following steps:

[0018] acquire a first optimization parameter of a single fuel cell in a stack;

[0019] optimize the first optimization parameter based on environmental data under different operating environments and a preset genetic algorithm, and obtain an optimal parameter value of the first optimization parameter under the different operating environments;

[0020] determine a polarization curve of the fuel cell under different operating environments based on the optimal parameter value of the first optimization parameter under the different operating environments, wherein the polarization curve is a three-segment function curve of voltage with respect to current density;

[0021] update and iterate the parameter value of the second optimization parameter of the stack based on a preset flow network algorithm until a preset flow distribution condition is met, and output an optimal flow distribution coefficient of the stack;

[0022] determine an optimization result of the stack based on the optimal flow distribution coefficient and the polarization curve under the different operating environments.

[0023] According to a fourth aspect of the embodiments of the present application, an electronic device is provided, which comprises a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor implements the following steps when executing the program:

[0024] obtain a first optimization parameter of a single fuel cell in a stack;

[0025] optimize the first optimization parameter based on environmental data under different operating environments and a preset genetic algorithm, and obtain an optimal parameter value of the first optimization parameter under the different operating environments;

[0026] determine a polarization curve of the fuel cell under different operating environments based on the optimal parameter value of the first optimization parameter under the different operating environments, wherein the polarization curve is a three-segment function curve of voltage with respect to current density;

[0027] update and iterate the parameter value of the second optimization parameter of the stack based on a preset flow network algorithm until a preset flow distribution condition is met, and output an optimal flow distribution coefficient of the stack;

[0028] determine an optimization result of the stack based on the optimal flow distribution coefficient and the polarization curve under the different operating environments.

[0029] The innovative points of the embodiments of the present application include:

[0030] 1. Optimizing the polarization curve of the fuel cell under different operating environments, so that the simulation effect of the polarization curve is consistent with the experimental result, and improving the simulation effect of the polarization curve at low current density and high current density is one of the innovative points of the embodiments of the present application.

[0031] 2. Applying the genetic algorithm to the optimization of the polarization curve to save the calculation time is one of the innovative points of the embodiments of the present application.

[0032] 3. Determining the optimal flow distribution coefficient of the stack based on the flow network algorithm to solve the problem of uneven flow distribution of the fuel cell stack is one of the innovative points of the embodiments of the present application.

[0033] 4. The present application determines the optimal operating environment of the fuel cell stack based on the polarization curve of the fuel cell under different operating environments to improve the performance of the fuel cell.

[0034] The performance optimization method of the fuel cell provided by the present application can obtain the first optimization parameter of a single fuel cell in the stack, and optimize the first optimization parameter based on the environmental data under different operating environments and a preset genetic algorithm to obtain the optimal parameter value of the first optimization parameter under different operating environments. At the same time, the polarization curve of the fuel cell under different operating environments is determined based on the optimal parameter value of the first optimization parameter under different operating environments, wherein the polarization curve is a three-segment function curve of voltage with respect to current density. Then, the parameter value of the second optimization parameter of the stack is updated and iterated based on a preset flow network algorithm until the preset flow distribution condition is met, and the optimal flow distribution coefficient of the stack is output. Finally, the optimization result of the stack is determined based on the optimal flow distribution coefficient and the polarization curve under different operating environments. Therefore, the polarization curve under different operating environments is optimized by the preset genetic algorithm, which can make the simulation effect of the polarization curve consistent with the experimental result, thereby improving the simulation effect of the polarization curve at low current density and high current density. At the same time, the optimal operating environment of the fuel cell can be determined through the polarization curve of the fuel cell under different operating environments, thereby improving the performance of the fuel cell. Further, the optimal flow distribution coefficient of the fuel cell stack is determined by the flow network algorithm, which can solve the problem of uneven flow distribution of the fuel cell stack, thereby further improving the performance of the fuel cell.

[0035] The above description is only a summary of the technical solutions of the present application. In order to more clearly understand the technical means of the present application, the specific embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the following specific embodiments of the present application are described. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creating any creative labor.

[0037] Figure 1 A flow chart of a performance optimization method of a fuel cell provided by an embodiment of the present application is shown;

[0038] Figure 2 Polarization curves of the fuel cell provided by the embodiment of the present application at different working temperatures are shown;

[0039] Figure 3 Polarization curves of the fuel cell provided by the embodiment of the present application at different working pressures are shown;

[0040] Figure 4 Polarization curves of the fuel cell provided by the embodiment of the present application at different relative humidities are shown;

[0041] Figure 5 Polarization curves of the fuel cell provided by the embodiment of the present application at different contact resistances are shown;

[0042] Figure 6 Polarization curves of the fuel cell provided by the embodiment of the present application at different proton exchange membrane thicknesses are shown;

[0043] Figure 7 A flow network schematic diagram provided by the embodiment of the present application is shown;

[0044] Figure 8 A structural schematic diagram of a performance optimization device of a fuel cell provided by the embodiment of the present application is shown;

[0045] Figure 9 An entity structural schematic diagram of an electronic device provided by the embodiment of the present application is shown. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative effort belong to the scope of protection of the present application.

[0047] It should be noted that the terms “include” and “have” and any variations thereof in the embodiments of the present application and the drawings are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units is not limited to the listed steps or units, but optionally further includes steps or units not listed or optionally further includes other steps or units inherent to the process, method, product or device.

[0048] The prior art has not proposed an effective means to solve the problem of uneven flow distribution of the stack to improve the performance of the fuel cell.

[0049] To solve the above problem, the embodiment of the present application provides a performance optimization method of a fuel cell, as shown in Figure 1As shown, the method comprises:

[0050] Step 101, obtaining a first optimization parameter of a single fuel cell in the stack.

[0051] The first optimization parameter is a parameter related to the activation loss voltage, ohmic loss voltage and concentration loss voltage of the fuel cell.

[0052] The embodiment of the present application is mainly applicable to the scene of optimizing the performance of the fuel cell. The execution subject of the embodiment of the present application is a device or equipment capable of optimizing the performance of the fuel cell.

[0053] The polarization curve of the fuel cell reflects the change of the fuel cell voltage with the current density. The function of the change of the fuel cell voltage with the current density is determined, and then the polarization curve of the fuel cell can be determined. In the existing polarization curve, when the current density is low, the activation loss voltage dominates in the voltage loss of the fuel cell. With the decrease of the current density, the voltage will sharply increase and approach infinity. When the current density is high, the concentration loss voltage dominates in the voltage loss of the fuel cell. When the current density approaches the maximum value, with the increase of the current density, the voltage sharply decreases and approaches negative infinity. However, the above two cases are contrary to the actual experimental test data, so it is necessary to optimize the existing polarization curve to ensure that the simulation effect of the optimized polarization curve at low current density and high current density is consistent with the experimental test result.

[0054] Based on this, the embodiment of the present application sets a small first current density threshold I0 for low current density. When the current density is less than the first current density threshold I0, the voltage of the fuel cell is E0, wherein E0 is the open circuit voltage measured by experiment. For high current density, a second current density threshold I1 close to the limit current is set. When the current density is greater than the second current density threshold I1 and less than the limit current density I max , the voltage of the fuel cell is 0. The final polarization curve function of the fuel cell is as follows:

[0055]

[0056] Wherein, E cell is the output voltage of the fuel cell, the first current density threshold I0 and the second current density threshold I1 can be obtained by assuming E cell is a continuous function, E Nemst is the Nernst voltage, V act is the activation loss voltage, V ohmic is the ohmic loss voltage, and V con is the concentration loss voltage.

[0057] Further, for E NemstNernst voltage, according to Faraday's law, the theoretical potential of a single fuel cell is:

[0058]

[0059] Where ΔG is the enthalpy of formation, F is the Faraday constant, and n is the number of electrons per hydrogen molecule, which is equal to 2. According to the definition of enthalpy, under certain temperature and pressure, the enthalpy of formation can be expressed as:

[0060] ΔG = ΔH - TΔS

[0061] Although ΔH and ΔS change with temperature and pressure, for low-temperature fuel cells (temperature below 100℃), the change of ΔH and ΔS with temperature is very small. Therefore, for low-temperature fuel cells, the effect of temperature on ΔH and ΔS is ignored, and ΔG changes linearly with temperature T under constant pressure.

[0062] Further, according to the knowledge of thermodynamics, for an isothermal process,

[0063]

[0064] Thus, for an isothermal process, the enthalpy of formation expression of the fuel cell system is:

[0065]

[0066] When the product of formation is liquid water, Taking into account the effects of temperature and pressure, we can get the famous Nernst equation:

[0067]

[0068] The Nernst equation can be brought into the theoretical potential formula of the fuel cell to get another form of the Nernst equation:

[0069]

[0070] Where the calculation formula of hydrogen and oxygen partial pressure on the interface of the catalyst layer is:

[0071]

[0072]

[0073] Where, When the water vapor in the gas flow reaches saturation, the mole fraction of water vapor is as follows:

[0074]

[0075] Further, The mole fraction of other gases in the gas stream can be expressed as a logarithmic average of the mole fractions of the gases at the inlet and outlet:

[0076]

[0077] wherein,

[0078] Further, for V act The activation overpotential for the reversible reaction is given by the chemical equation:

[0079]

[0080] The net current is the difference between the electrons consumed by the forward reaction and the electrons released by the reverse reaction,

[0081] i = nF(K f C ox -K b C Rd )

[0082]

[0083] wherein, i0is the current of the forward or reverse reaction when the reaction is at equilibrium. Further, the Butler-Volmer equation is constructed as follows:

[0084]

[0085] Since the overpotential for the cathode is negative (E c <E r,c ), the first term of the above Butler-Volmer equation is much larger than the second term, based on which, the overpotential for the cathode can be simplified as:

[0086]

[0087] Similarly, the overpotential for the anode can be obtained as follows:

[0088]

[0089]

[0090] wherein, is the oxygen concentration at the interface, and thus the total overpotential can be written as follows:

[0091]

[0092] Further, for V ohmic is the ohmic overpotential, which is the voltage drop due to the resistance R electronic of the conductive element through which the electrons flow, and the contact resistance Rcontact , the ion passing through the proton exchange membrane will generate a resistance R proton . Therefore, the total internal resistance R internal is the sum of the three, and the Ohm's law can be combined to get the expression of Ohmic voltage loss, as follows:

[0093] V ohmic = -iR internal = -i(R electronic + R proton + R contact )

[0094] Generally, R electronic is smaller than the other two and can be ignored, so the Ohmic voltage can be simplified as:

[0095] V ohmic = -i(R proton + R contact )

[0096] In a certain range of working conditions, R contact is small and is generally treated as a constant. The proton resistance R proton is a complex function of water content and its distribution, and also depends on the temperature and the size and distribution of the current. It can be calculated by an empirical formula:

[0097]

[0098] where r M is the resistivity of the proton exchange membrane (ohm.cm), l is the thickness of the proton exchange membrane, and A is the area of the proton exchange membrane. The empirical formula of the resistivity of the proton exchange membrane is as follows:

[0099]

[0100] where λ_m is the equivalent ratio of the membrane.

[0101] Further, the rapid consumption of reactants on the electrode in the electrochemical reaction forms a large concentration gradient, resulting in a concentration loss voltage V con . The mass transport affects the concentrations of the fuel and oxygen, thereby affecting the partial pressures of the fuel and oxygen and the size of the concentration polarization voltage. According to Faraday's law, the current density is proportional to the consumption rate of the fuel / hydrogen, and the consumption rate of the fuel / hydrogen is proportional to the decrease in the concentrations of the fuel and oxygen. Therefore, when the reactants on the electrode are consumed faster, the concentrations of the reactants on the electrode are lower, and the current is larger. When the consumption rate of the reactants on the electrode approaches the maximum fuel supply rate, the concentrations of the reactants on the electrode approach zero, and the current approaches the limiting current. The semi-empirical formula of the concentration loss voltage can be expressed as:

[0102]

[0103] wherein b is a constant to be determined, I L is the limiting current.

[0104] Thus, according to the above formulas of Nernst voltage, activation loss voltage, ohmic loss voltage and concentration loss voltage, there are eight first optimization parameters in the embodiment of the present application, wherein, four parameters β1, β2, β3, β4 related to the activation loss voltage, two parameters R contact , λ_m related to the ohmic loss voltage, and two parameters b, I L related to the concentration loss voltage.

[0105] Step 102, based on the environmental data under different operating environments and the preset genetic algorithm, the first optimization parameter is optimized to obtain the optimal parameter value of the first optimization parameter under different operating environments.

[0106] The environmental data includes the working temperature, working pressure, relative humidity, contact resistance and proton exchange membrane thickness of the fuel cell.

[0107] For the embodiment of the present application, the process of optimizing the polarization curve of the fuel cell is the process of determining the parameter value of the first optimization parameter. For this process, step 102 specifically includes: according to the first optimization parameter, establishing a parent parameter population of the fuel cell under different operating environments, wherein the parent parameter population includes multiple parent individuals; based on the parameter value of the first optimization parameter in each parent individual and the environmental data under different operating environments, calculating the output voltage of the fuel cell under different operating environments; based on the output voltage of the fuel cell under different operating environments and the test voltage, generating a child parameter population of the fuel cell under different operating environments, and taking the child parameter population as a new parent parameter population to continue population iteration until a preset iteration number is reached, outputting the optimal child individual under different operating environments; determining the parameter value of the first optimization parameter in the optimal child individual as the optimal parameter value of the first optimization parameter under different operating environments.

[0108] Further, the calculation of the output voltage of the fuel cell under different operating environments based on the parameter value of the first optimization parameter in each parent individual and the environmental data under different operating environments includes: according to the parameter value of the first optimization parameter in each parent individual and the environmental data under different operating environments, calculating the Nernst voltage, activation loss voltage, ohmic loss voltage and concentration loss voltage of the fuel cell under different operating environments respectively; adding the Nernst voltage, the activation loss voltage, the ohmic loss voltage and the concentration loss voltage to obtain the output voltage of the fuel cell under different operating environments.

[0109] Further, the generating the offspring parameter population of the fuel cell under different operating environments based on the output voltage and the test voltage of the fuel cell under different operating environments comprises: calculating the fitness of each parent individual based on the output voltage and the test voltage of the fuel cell under different operating environments; selecting target parent individuals from the parent parameter population under different operating environments based on the fitness; and generating the offspring parameter population under different operating environments by crossing and mutating the target parent individuals under different operating environments.

[0110] Specifically, it is assumed that the environment data corresponding to the operating environment A is working temperature 50°, working pressure 0.1 Mpa, relative humidity 70%, and contact resistance 5.0×10 -6 , and the environment data corresponding to the operating environment B is working temperature 70°, working pressure 0.1 Mpa, relative humidity 70%, and contact resistance 5.0×10 -6 , i.e., the working temperatures of the operating environment A and the operating environment B are different. For the eight first optimization parameters determined in step 101, the parent parameter population of the fuel cell under the operating environment A and the operating environment B is established, and the parent parameter population includes a plurality of parent individuals, and each parent individual corresponds to the parameter values of the eight first optimization parameters.

[0111] Further, the environment data corresponding to the operating environment A and the parameter values of the first optimization parameters corresponding to each parent individual in the parent parameter population under the operating environment A are brought into the formula in step 101, so that the Nernst voltage, the activation loss voltage, the ohmic loss voltage, and the concentration loss voltage corresponding to each parent individual in the parent parameter population under the operating environment A can be obtained. Then, the Nernst voltage, the activation loss voltage, the ohmic loss voltage, and the concentration loss voltage are added to obtain the output voltage of the fuel cell corresponding to each parent individual in the parent parameter population under the operating environment A. Similarly, the output voltage of the fuel cell corresponding to each parent individual in the parent parameter population under the operating environment B can be obtained.

[0112] Further, the fitness function is constructed as follows:

[0113]

[0114] wherein, E cell is the output voltage of the fuel cell, and E test is the test voltage of the fuel cell. Thus, the output voltage of the fuel cell corresponding to each parent individual is brought into the fitness function, so that the fitness corresponding to each parent individual under the operating environment A and the fitness corresponding to each parent individual under the operating environment B can be obtained.

[0115] Further, based on the fitness, a target parent class individual is screened from the parent parameter population under the running environment A, then the target parent class individual is crossed and mutated to generate a child parameter population under the running environment A, then the child parameter population is taken as a new parent parameter population to continue iteration until a preset iteration number is reached, an optimal child class individual is output, and a parameter value of the first optimization parameter corresponding to the optimal child class individual is determined as an optimal parameter value of the fuel cell under the running environment A. Similarly, an optimal parameter value of the fuel cell under the running environment B can be determined.

[0116] It should be noted that the embodiments of the present application only take the working temperature as an example to illustrate how to optimize the first optimization parameter of the fuel cell under different working temperatures, but are not limited thereto. The embodiments of the present application can also optimize the first optimization parameter of the fuel cell under different working pressures, different relative humidities, different contact resistances and different proton exchange membrane thicknesses.

[0117] Step 103, based on the optimal parameter values of the first optimization parameter under different running environments, a polarization curve of the fuel cell under different running environments is determined.

[0118] The polarization curve is a three-segment function curve of voltage with respect to current density.

[0119] For the embodiments of the present application, after the first optimization parameter of the fuel cell under different running environments is determined, the polarization curve of the fuel cell under different running environments can be determined. Figure 2 For the polarization curves of the fuel cell under three working temperatures, it can be seen that as the working temperature increases, the polarization curve moves upward, and the performance of the battery is improved. Figure 3 For the polarization curves of the fuel cell under three working pressures, it can be seen that as the inlet pressure increases, the voltage loss is small, and the performance of the fuel cell is improved. Figure 4 For the polarization curves of the fuel cell under three relative humidities, it can be seen that as the relative humidity of hydrogen increases, the voltage loss decreases, and the performance of the fuel cell is improved. Figure 5 For the polarization curves of the fuel cell under three contact resistances, it can be seen that as the contact resistance increases, the voltage loss increases, and the performance of the fuel cell decreases, so the contact resistance should be reduced to an optimal value in actual fuel cell design. Figure 6 For the polarization curves of the fuel cell under three proton exchange membrane thicknesses, it can be seen that as the proton exchange membrane thickness increases, the voltage loss increases, and the performance of the fuel cell decreases.

[0120] Step 104, based on a preset flow network algorithm, the parameter value of the second optimization parameter of the stack is updated and iterated until a preset flow distribution condition is met, and an optimal flow distribution coefficient of the stack is output.

[0121] The second set of optimization parameters includes the gas temperature, gas flow rate, relative humidity, gas inlet pressure, and manifold diameter of the fuel cell stack.

[0122] In this embodiment of the invention, in order to determine the optimal flow distribution coefficient of the fuel cell stack, step 104 specifically includes: initializing the second optimization parameters of the stack; calculating the flow distribution coefficient of the stack based on the initial value of the second optimization parameters and a preset flow network algorithm; updating and iterating the second optimization parameters based on the flow distribution coefficient until the preset flow distribution conditions are met, and then outputting the optimal flow distribution coefficient.

[0123] Further, the initialization of the second optimization parameters of the fuel cell stack, and the calculation of the distribution coefficient of the fuel cell stack based on the initial values ​​of the second optimization parameters and a preset flow network algorithm, includes: constructing the mass conservation equation of the fuel cell stack based on the preset flow network algorithm; substituting the initial values ​​of the second optimization parameters into the mass conservation equation to solve for the pressure of each exhaust manifold segment and each intake manifold segment in the fuel cell stack; and calculating the current distribution coefficient of the fuel cell stack based on the pressure of each exhaust manifold segment and each intake manifold segment.

[0124] Specifically, the embodiments of the present invention employ a method analogous to circuits, considering the manifold of the fuel cell stack as n equally divided small manifold segments, each manifold segment corresponding to a flow resistance R. header The flow resistance R header This is equal to the pressure drop across the manifold divided by the gas flow rate through it. Similarly, the pressure drop between the inlet and outlet of the bipolar plate divided by the gas flow rate through that bipolar plate is equal to the flow resistance R of the bipolar plate. fc These N intake manifolds, N exhaust manifolds, and N bipolar plate channels are connected by 2N nodes, together forming a system as shown in the image. Figure 7 The flow network shown is illustrated. In other words, this embodiment of the invention transforms the problem of uneven flow distribution in a fuel cell stack containing N fuel cells into a flow network problem containing N loops.

[0125] Furthermore, any flow network problem must satisfy the following three basic conditions: 1. The flow into a node is equal to the flow out of that node; 2. The pressure loss of each manifold segment is equal to the flow through that manifold segment as a function; 3. The sum of the pressure drops of each loop is 0.

[0126] Depend on Figure 7 As shown in the flow network, there are N fuel cells in total. The manifold corresponding to each fuel cell includes 5 variables, namely the gas flow rate Q in the intake manifold. in (i) Gas flow rate Q in the exhaust manifold out (i) Intake manifold end pressure Pin (i) the end point pressure P of the exhaust manifold out (i) and the gas flow q through the bipolar plate x (i). That is, the total of 5N variables for the stack of N fuel cells.

[0127] According to the above first law of mass conservation, the following expression can be obtained:

[0128]

[0129]

[0130] Q in (1) = q x (1) = Q out (1)

[0131] Q in (N) = q x (N) = Q f

[0132] Thus, 2N+2 equations can be constructed, and 3N-2 equations are needed to solve the 5N variables. At this time, the pressure loss formula of the manifold and the pressure loss formula of the bipolar plate can be further constructed through the second and third laws. Through the Bernoulli equation, the pressure loss of the exhaust manifold can be obtained as:

[0133]

[0134] Similarly, the pressure loss formula of the intake manifold can be obtained as:

[0135]

[0136] Further, the pressure loss formula of the bipolar plate channel is as follows:

[0137]

[0138] where f out (i), f in (i), f x (i) are the friction factors of the i-th section of the exhaust manifold, the intake manifold, and the bipolar plate channel, respectively. L out , L in is the length of each section of the exhaust manifold and the intake manifold, and L x is the length of the bipolar plate channel. D H_out (i), D H_in (i), D H_x are the diameters of the i-th section of the exhaust manifold, the intake manifold, and the bipolar plate channel, respectively. The diameter is the cross-sectional area divided by the circumference, and then multiplied by 4. K L is the local resistance.

[0139] Further, for the flow layer problem, the expression of the friction factor is:

[0140]

[0141] wherein C0 is a constant, C0 = 64 for the annular channel, C0 = 56 for the square channel, and C0 = 48 for the rectangular channel,

[0142]

[0143] Therefore, when the parameter values of the second optimization parameters (such as the lengths of the exhaust manifold and the intake manifold and the diameters of the bipolar plate pipes) are determined, the 2*(N-1) equations of the intake manifold and the exhaust manifold, the N equations of the pressure loss of the bipolar plate pipes, and the 2N+2 equations initially constructed can be used to solve 5N variables.

[0144] Further, after the mass conservation equation is constructed, the second optimization parameters can be initialized, and the initial values corresponding to the second optimization parameters are brought into the mass conservation equation to solve the endpoint pressure of each intake manifold and the endpoint pressure of each exhaust manifold. Then, according to the endpoint pressure of each intake manifold and the endpoint pressure of each exhaust manifold, the pressure drop of each intake manifold and the pressure drop of each exhaust manifold can be obtained. Finally, the pressure drop of each intake manifold and the pressure drop of each exhaust manifold are added to obtain the total pressure drop corresponding to each fuel cell.

[0145] Further, by comparing the total pressure drop corresponding to each fuel cell, the flow distribution coefficient of the current stack is obtained, and the flow distribution of the fuel cell stack can be fed back through the flow distribution coefficient.

[0146] Therefore, based on the calculated flow distribution coefficient, the genetic algorithm or the greedy algorithm can be used to update and iterate the parameter values of the second optimization parameters until the calculated flow distribution coefficient meets the requirements, that is, the flow distribution is uniform, the iteration is stopped, and the finally calculated flow distribution coefficient is output as the optimal flow distribution coefficient of the fuel cell stack.

[0147] Step 105, based on the optimal flow distribution coefficient and the polarization curve under different operating environments, determining the optimization result of the stack.

[0148] For the embodiment of the present application, in order to improve the working performance of the fuel cell stack, step 105 specifically includes: determining the optimal operating environment of the stack according to the polarization curve under different operating environments; and determining the optimization result of the stack based on the optimal operating environment and the optimal flow distribution coefficient.

[0149] Specifically, after obtaining the polarization curves of the fuel cell under different operating environments, the optimal operating environment can be selected based on these curves to ensure the fuel cell operates at high performance. Thus, the performance of the fuel cell stack can be optimized using this optimal operating environment and the optimal flow distribution coefficient.

[0150] This invention provides a fuel cell performance optimization method. By utilizing a preset genetic algorithm to optimize the polarization curves under different operating environments, the simulated polarization curves can better match experimental results, thereby improving the simulation performance of the polarization curves at low and high current densities. Simultaneously, by analyzing the polarization curves of the fuel cell under different operating conditions, this invention can determine the optimal operating environment for the fuel cell, thereby improving fuel cell performance. Furthermore, this invention utilizes a flow network algorithm to determine the optimal current distribution coefficient of the fuel cell stack, solving the problem of uneven current distribution in the fuel cell stack, thus further improving fuel cell performance.

[0151] Furthermore, as Figure 1 In specific implementation, embodiments of the present invention provide a fuel cell performance optimization device, such as... Figure 8 As shown, the device includes: an acquisition unit 31, an optimization unit 32, a first determination unit 33, an iteration unit 34, and a second determination unit 35.

[0152] The acquisition unit 31 can be used to acquire the first optimized parameters of a single fuel cell in the stack.

[0153] The optimization unit 32 can be used to optimize the first optimization parameter based on environmental data under different operating environments and a preset genetic algorithm, so as to obtain the optimal parameter value of the first optimization parameter under different operating environments.

[0154] The first determining unit 33 can determine the polarization curve of the fuel cell under different operating environments based on the optimal parameter values ​​of the first optimized parameters under different operating environments, wherein the polarization curve is a three-segment function curve of voltage with respect to current density.

[0155] The iteration unit 34 can be used to update and iterate the parameter values ​​of the second optimization parameter of the fuel cell stack based on a preset flow network algorithm until the preset current distribution condition is met, and then output the optimal current distribution coefficient of the fuel cell stack.

[0156] The second determining unit 35 can be used to determine the optimization result of the fuel cell stack based on the optimal current distribution coefficient and the polarization curves under different operating environments.

[0157] In a specific application scenario, the optimization unit 32 includes: an establishment module, a first calculation module, a first iteration module, and a determination module.

[0158] The establishment module can be used to establish a parent parameter population of the fuel cell under different operating environments based on the first optimization parameters, wherein the parent parameter population includes multiple parent individuals.

[0159] The first calculation module can be used to calculate the output voltage of the fuel cell under different operating environments based on the parameter value corresponding to the first optimization parameter in each parent individual and the environmental data under different operating environments.

[0160] The first iteration module can be used to generate a sub-parameter population of the fuel cell under different operating environments based on the output voltage and test voltage of the fuel cell under different operating environments, and use the sub-parameter population as a new parent parameter population to continue population iteration until a preset number of iterations is reached, and then output the optimal sub-individual under different operating environments.

[0161] The determining module can be used to determine the parameter value corresponding to the first optimization parameter in the optimal subclass individual as the optimal parameter value of the first optimization parameter under different operating environments.

[0162] Furthermore, the first calculation module can be specifically used to calculate the Nernst voltage, activation loss voltage, ohmic loss voltage and concentration loss voltage of the fuel cell under different operating environments based on the parameter value corresponding to the first optimization parameter in each parent individual and the environmental data under different operating environments; and to add the Nernst voltage, the activation loss voltage, the ohmic loss voltage and the concentration loss voltage together to obtain the output voltage of the fuel cell under different operating environments.

[0163] Furthermore, the first iteration module can be specifically used to calculate the fitness of each parent individual based on the output voltage and test voltage of the fuel cell under different operating environments; based on the fitness, select target parent individuals from the parent parameter population under different operating environments; and perform crossover and mutation on the target parent individuals under different operating environments to generate offspring parameter populations under different operating environments.

[0164] In a specific application scenario, the iteration unit 34 includes: a second calculation module and a second iteration module.

[0165] The second calculation module can be used to initialize the second optimization parameters of the fuel cell stack, and calculate the current distribution coefficient of the fuel cell stack based on the initial value of the second optimization parameters and a preset flow network algorithm.

[0166] The second iteration module can be configured to update the second optimization parameter based on the flow distribution coefficient until a preset flow distribution condition is met, and output an optimal flow distribution coefficient.

[0167] Further, the second calculation module can be specifically configured to construct a mass conservation equation of the stack based on the preset flow network algorithm, bring an initial value of the second optimization parameter into the mass conservation equation to obtain a pressure of each exhaust manifold and a pressure of each intake manifold in the stack, and calculate a current flow distribution coefficient of the stack according to the pressure of each exhaust manifold and the pressure of each intake manifold.

[0168] Further, the second determination unit 35 can be specifically configured to determine an optimal operating environment of the stack according to the polarization curve under different operating environments, and determine an optimization result of the stack based on the optimal operating environment and the optimal flow distribution coefficient.

[0169] It should be noted that other corresponding descriptions of the various functional modules involved in the performance optimization device of the fuel cell provided by the embodiments of the present application can be referred to the corresponding descriptions of the method shown in Figure 1 Therefore, the detailed description is omitted here.

[0170] Based on the above method as Figure 1 shown, correspondingly, the embodiments of the present application also provide a computer readable storage medium, which stores a computer program, and the program is executed by a processor to realize the following steps: obtaining a first optimization parameter of a single fuel cell in a stack; optimizing the first optimization parameter based on environmental data under different operating environments and a preset genetic algorithm to obtain optimal parameter values of the first optimization parameter under different operating environments; determining a polarization curve of the fuel cell under different operating environments based on the optimal parameter values of the first optimization parameter under different operating environments, wherein the polarization curve is a three-segment function curve of voltage with respect to current density; updating and iterating a parameter value of a second optimization parameter of the stack based on a preset flow network algorithm until a preset flow distribution condition is met, and outputting an optimal flow distribution coefficient of the stack; and determining an optimization result of the stack based on the optimal flow distribution coefficient and the polarization curve under different operating environments.

[0171] Based on the above method as Figure 1 shown and the device as Figure 8 shown, the embodiments of the present application also provide a physical structure diagram of an electronic device, as Figure 9As shown, the electronic device comprises a processor 41, a memory 42, and a computer program stored on the memory 42 and executable on the processor, wherein the memory 42 and the processor 41 are both arranged on a bus 43, and the processor 41 implements the following steps when executing the program: obtaining a first optimization parameter of a single fuel cell in a fuel cell stack; based on environmental data under different operating environments and a preset genetic algorithm, the first optimization parameter is optimized to obtain an optimal parameter value of the first optimization parameter under different operating environments; based on the optimal parameter value of the first optimization parameter under different operating environments, a polarization curve of the fuel cell under different operating environments is determined, wherein the polarization curve is a three-segment function curve of voltage with respect to current density; based on a preset flow network algorithm, the parameter value of a second optimization parameter of the fuel cell stack is iteratively updated until a preset flow distribution condition is met, and an optimal flow distribution coefficient of the fuel cell stack is output; and based on the optimal flow distribution coefficient and the polarization curve under different operating environments, an optimization result of the fuel cell stack is determined.

[0172] By using the preset genetic algorithm to optimize the polarization curve under different operating environments, the embodiment of the present application can make the simulation effect of the polarization curve consistent with the experimental results, thereby improving the simulation effect of the polarization curve at low current density and high current density. At the same time, by using the polarization curve of the fuel cell under different operating environments, the present application can determine the optimal operating environment of the fuel cell, thereby improving the performance of the fuel cell. Further, by using the flow network algorithm to determine the optimal flow distribution coefficient of the fuel cell stack, the present application can solve the problem of uneven flow distribution of the fuel cell stack, thereby further improving the performance of the fuel cell.

[0173] Those skilled in the art can understand that the modules or flows in the drawings are not necessarily required to implement the present application.

[0174] Those skilled in the art can understand that the modules in the device in the embodiment can be distributed in the device in the embodiment as described in the embodiment, or can be changed and located in one or more devices different from the embodiment. The modules in the above embodiment can be combined into one module, or can be further split into multiple sub-modules.

[0175] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit them; although the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that they can modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacements for some technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method of performance optimization of a fuel cell, characterized by, The method comprises the following steps: acquiring a first optimization parameter of a single fuel cell in a fuel cell stack; optimizing the first optimization parameter based on environmental data under different operating environments and a preset genetic algorithm to obtain optimal parameter values of the first optimization parameter under different operating environments, wherein the first optimization parameter is a parameter related to activation loss voltage, ohmic loss voltage, and concentration loss voltage of the fuel cell; determining a polarization curve of the fuel cell under different operating environments based on the optimal parameter values of the first optimization parameter under different operating environments, wherein the polarization curve is a three-segment function curve of voltage with respect to current density, and the polarization curve is a three function curves formed by the horizontal coordinate of current density and the vertical coordinate of voltage under three operating environments; updating and iterating parameter values of a second optimization parameter of the fuel cell stack based on a preset flow network algorithm until a preset flow distribution condition is met, and outputting an optimal flow distribution coefficient of the fuel cell stack, wherein the second optimization parameter includes gas temperature, gas flow, relative humidity, gas inlet pressure, and manifold diameter of the fuel cell stack, and the flow distribution coefficient can feedback whether the flow distribution of the fuel cell stack is uniform, and the flow distribution coefficient when the flow distribution is uniform is the optimal flow distribution coefficient; determining an optimization result of the fuel cell stack based on the optimal flow distribution coefficient and the polarization curve under different operating environments; wherein the optimization of the first optimization parameter based on the environmental data under different operating environments and the preset genetic algorithm to obtain the optimal parameter values of the first optimization parameter under different operating environments comprises: establishing a parent parameter population of the fuel cell under different operating environments according to the first optimization parameter, wherein the parent parameter population includes a plurality of parent individuals; calculating output voltages of the fuel cell under different operating environments based on parameter values corresponding to the first optimization parameter in each parent individual and the environmental data under different operating environments; generating a child parameter population of the fuel cell under different operating environments based on the output voltages of the fuel cell under different operating environments and test voltages, and taking the child parameter population as a new parent parameter population to continue population iteration until a preset iteration number is reached, and outputting optimal child individuals under different operating environments; determining parameter values corresponding to the first optimization parameter in the optimal child individuals as the optimal parameter values of the first optimization parameter under different operating environments.

2. The method of claim 1, wherein, The calculation of the output voltages of the fuel cell under different operating environments based on the parameter values corresponding to the first optimization parameter in each parent individual and the environmental data under different operating environments comprises: calculating Nernst voltages, activation loss voltages, ohmic loss voltages, and concentration loss voltages of the fuel cell under different operating environments respectively based on the parameter values corresponding to the first optimization parameter in each parent individual and the environmental data under different operating environments; adding the Nernst voltages, the activation loss voltages, the ohmic loss voltages, and the concentration loss voltages to obtain the output voltages of the fuel cell under different operating environments.

3. The method of claim 1, wherein, The process of generating a population of offspring parameters for the fuel cell under different operating environments, based on the output voltage and test voltage of the fuel cell under different operating conditions, includes: Based on the output voltage and test voltage of the fuel cell under different operating environments, the fitness of each parent individual is calculated respectively; Based on the fitness, target parent individuals are selected from the parent parameter population under different operating environments; Crossover and mutation are performed on the target parent individuals under different operating environments to generate offspring parameter populations under different operating environments.

4. The method of claim 1, wherein, The step of updating and iterating the parameter values ​​of the second optimization parameter of the fuel cell stack based on a preset flow network algorithm until a preset current distribution condition is met, and then outputting the optimal current distribution coefficient of the fuel cell stack, includes: The second optimization parameters of the fuel cell stack are initialized, and the current distribution coefficient of the fuel cell stack is calculated based on the initial values ​​of the second optimization parameters and the preset flow network algorithm. Based on the distribution coefficient, the second optimization parameter is updated and iterated until the preset distribution conditions are met, and then the optimal distribution coefficient is output.

5. The method of claim 4, wherein, The initialization of the second optimization parameters of the fuel cell stack, and the calculation of the current distribution coefficient of the fuel cell stack based on the initial values ​​of the second optimization parameters and a preset flow network algorithm, includes: Based on the preset flow network algorithm, the mass conservation equation of the fuel cell stack is constructed; Substitute the initial value of the second optimization parameter into the mass conservation equation to solve for the pressure of each exhaust manifold and each intake manifold in the fuel cell stack. The current distribution coefficient of the fuel cell stack is calculated based on the pressure of each exhaust manifold section and the pressure of each intake manifold section.

6. The method according to any one of claims 1 to 5, characterized in that, The process of determining the optimization result of the fuel cell stack based on the optimal current distribution coefficient and the polarization curves under different operating environments includes: Based on the polarization curves under different operating environments, the optimal operating environment of the fuel cell stack is determined. Based on the optimal operating environment and the optimal current distribution coefficient, the optimization result of the fuel cell stack is determined.

7. A performance optimization device for a fuel cell, characterized in that, include: The acquisition unit is used to acquire the first optimized parameters of a single fuel cell in the fuel cell stack. An optimization unit is used to optimize the first optimization parameter based on environmental data under different operating conditions and a preset genetic algorithm to obtain the optimal parameter value of the first optimization parameter under different operating conditions. The first optimization parameter is a parameter related to the activation loss voltage, ohmic loss voltage and concentration loss voltage of the fuel cell. The first determining unit is used to determine the polarization curve of the fuel cell under different operating environments based on the optimal parameter values ​​of the first optimized parameters under different operating environments. The polarization curve is a three-segment function curve of voltage with respect to current density. The polarization curve is a function curve formed by the current density on the horizontal axis and the voltage under the three operating environments on the vertical axis. The iteration unit is configured to perform an update iteration on the parameter value of the second optimization parameter of the stack based on a preset flow network algorithm until a preset flow distribution condition is met, and output an optimal flow distribution coefficient of the stack, wherein the second optimization parameter includes a gas temperature, a gas flow, a relative humidity, a gas inlet pressure, and a manifold diameter size of the fuel cell stack, the flow distribution coefficient can reflect whether the flow distribution of the fuel cell stack is uniform, and the flow distribution coefficient when the flow distribution is uniform is the optimal flow distribution coefficient. The second determination unit is configured to determine an optimization result of the stack based on the optimal flow distribution coefficient and the polarization curve under the different operating environments. The optimization unit is specifically configured to: establish a parent parameter population of the fuel cell under different operating environments according to the first optimization parameter, wherein the parent parameter population includes a plurality of parent individuals; calculate an output voltage of the fuel cell under different operating environments based on a parameter value corresponding to the first optimization parameter in each parent individual and environment data under the different operating environments; generate a child parameter population of the fuel cell under different operating environments based on the output voltage and a test voltage of the fuel cell under different operating environments, and continue population iteration by taking the child parameter population as a new parent parameter population until a preset iteration number is reached, and output an optimal child individual under different operating environments; determine a parameter value corresponding to the first optimization parameter in the optimal child individual as an optimal parameter value of the first optimization parameter under different operating environments.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

9. An electronic device comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, The computer program is executed by the processor to implement the steps of the method in any one of claims 1 to 6.

Images