A thermal management method for a fuel cell

Abstract

The present invention discloses a thermal management method for a fuel cell. The method includes: for the fuel cell thermal management system, an outlet fuzzy controller and an inlet fuzzy controller are set up. Among them, the fuel cell thermal management system includes a water tank, a cooling water pump, a radiator, and an electric stack. The outlet fuzzy controller takes the error between the current outlet temperature of the electric stack and the set target outlet temperature and the error change rate as input quantities, and takes the cooling water flow rate as the output quantity; the inlet fuzzy controller takes the error between the current inlet temperature of the electric stack and the set target inlet temperature and the change rate of the error as input quantities, and takes the fan speed of the radiator as the output quantity; determine the membership functions, fuzzy universes, and fuzzy rules of the outlet fuzzy controller and the inlet fuzzy controller; perform parameterization processing on the membership functions, and optimize the membership functions through the particle swarm and genetic algorithms. The present invention can accurately control the temperature in the fuel cell thermal management system.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cell management, and more specifically, to a thermal management method for a fuel cell. Background Art

[0002] Hydrogen energy is a secondary energy source with rich sources, green, low-carbon, and wide applications, and is of great significance for building a clean, low-carbon, safe, and efficient energy system and achieving the goals of carbon peak and carbon neutrality. With the rapid development of new energy vehicles, hydrogen fuel cell vehicles have received extensive attention due to their advantages such as high efficiency and cleanliness. The Proton Exchange Membrane Fuel Cell (PEMFC) has the advantages of high energy conversion efficiency, low-temperature operation, high reliability, and zero emissions, and has broad application prospects in the automotive field. PEMFC is a non-linear complex system with multi-physical fields and multi-parameter coupling. Its operating temperature is a key factor affecting the output performance and lifespan. If the operating temperature is too high, liquid water will evaporate, resulting in membrane dry-out failure; if the temperature is too low, the cathode flow channel will be flooded with water, and oxygen cannot pass through the gas diffusion layer. The normal operating temperature range of PEMFC is 60-80 °C. However, a large amount of heat is generated during its operation, so effective thermal management of PEMFC is required. Improper thermal management will lead to an irreversible decrease in the output voltage of PEMFC and accelerate its aging rate.

[0003] In the prior art, PEMFC thermal management can be classified into three methods according to the principle: adjusting the structure, phase change cooling, and optimizing control. Changing the flow channel structure will make the internal structure of the fuel cell more complex, increase the temperature control circulating cooling shell, and increase the volume of the fuel cell. The fluid used in phase change cooling is relatively expensive, which is not conducive to commercialization. Both application methods have defects. Currently, PEMFC thermal management mainly controls the cooling water flow rate and fan speed on the temperature model. The control methods include PI (Proportion Integration) control, state feedback control, predictive control, etc. These control methods have simple principles and are easy to use, but they have disadvantages such as slow response speed and long adjustment time. Due to the inherent nonlinear characteristics of the fuel cell and the uncertainty of parameters, as well as the fact that the output performance and durability of high-power fuel cells applied to commercial vehicles are very sensitive to the change of the stack temperature, the application of existing control methods has certain difficulties. Fuzzy control has a fast response speed and strong anti-interference ability, especially suitable for the control of lag systems. Some scholars have designed a fuzzy control method applied to PEMFC thermal management, and by adjusting the fan speed to control the temperature of PEMFC. The comparison results with the above control methods show that fuzzy control has superiority. In addition, some researchers have considered overcoming the interference of external loads and adopted a fuzzy controller with integral to adjust the flow rate of cooling water in real time. The results show that this method can quickly reach the target temperature under very small fluctuations and control the temperature of the PEMFC stack within a reasonable range, and has stronger robustness than traditional similar models. Another existing solution is to use improved particle swarm optimization fuzzy PID control. The control strategy is set according to control experience rules and has advantages such as strong robustness and fast response speed.

[0004] After analysis, the existing fuzzy control designs mainly rely on the experience of experts, and most methods use step load signals to verify fuzzy control. However, in the actual driving of hydrogen fuel cell vehicles, there are processes such as acceleration, constant speed, and deceleration. The frequent change of working conditions will make the fuel cell temperature control more complex, and the temperature may show extreme values. The existing fuzzy logic has difficulties in controlling the temperature to the target value, and there are large fluctuations at the control target temperature value. Summary of the Invention

[0005] The object of the present invention is to overcome the defects of the above prior art and provide a thermal management method for fuel cells, which includes the following steps:

[0006] For a fuel cell thermal management system, an outlet fuzzy controller and an inlet fuzzy controller are set up. The fuel cell thermal management system includes a water tank, a cooling water pump, a radiator and a fuel cell stack. The outlet fuzzy controller takes the error between the current outlet temperature of the fuel cell stack and the set target outlet temperature and the rate of change of the error as input variables, and takes the cooling water flow rate as the output variable. The inlet fuzzy controller takes the error between the current inlet temperature of the fuel cell stack and the set target inlet temperature and the rate of change of the error as input variables, and takes the fan speed of the radiator as the output variable.

[0007] Determine the membership functions, fuzzy universes of discourse of the outlet fuzzy controller and the inlet fuzzy controller and set fuzzy rules.

[0008] Perform parameterization processing on the membership functions, use the parameters to be optimized as the particle swarm, optimize the membership functions of the inlet fuzzy controller and the outlet fuzzy controller to control the current cooling water flow rate of the fuel cell thermal management system and the fan speed of the radiator.

[0009] Compared with the prior art, the advantages of the present invention are as follows: aiming at making the error between the inlet and outlet temperatures of the fuel cell stack and the target temperature value smaller, combining the characteristics of fuzzy control rules and the optimization of membership functions, optimizing the membership functions of the fuzzy controller through an algorithm with better overall performance. The optimized fuzzy controller has obvious improvement in stability and accuracy compared with the conventional fuzzy controller, and overcomes the defect that the particle swarm optimization algorithm is prone to fall into local optimum. Compared with the existing optimization algorithms, the present invention has better temperature regulation ability, smaller deviation from the set value, and can better resist the disturbance of external load.

[0010] Through the following detailed description of the exemplary embodiments of the present invention with reference to the accompanying drawings, other features and advantages of the present invention will become clear. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The drawings incorporated in the specification and constituting a part of the specification illustrate embodiments of the present invention and, together with the description, are used to explain the principles of the present invention.

[0012] Figure 1 is a schematic diagram of a fuel cell thermal management system of the prior art;

[0013] Figure 2 is a flowchart of a fuel cell thermal management method according to an embodiment of the present invention;

[0014] Figure 3 is a schematic diagram of a fuzzy control process according to an embodiment of the present invention;

[0015] Figure 4 is a schematic diagram of a triangular membership function according to an embodiment of the present invention;

[0016] Figure 5 It is a schematic diagram of an optimized fuzzy controller based on a particle swarm-genetic hybrid algorithm according to an embodiment of the present invention;

[0017] Figure 6 It is a flow chart of an optimized fuzzy control by a particle swarm-genetic hybrid algorithm according to an embodiment of the present invention;

[0018] Figure 7 It is a schematic diagram of the chromosome crossover process according to an embodiment of the present invention. Detailed implementation manners

[0019] Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: Unless otherwise specifically stated, the relative arrangements of components and steps, numerical expressions, and numerical values set forth in these embodiments do not limit the scope of the present invention.

[0020] The following description of at least one exemplary embodiment is merely illustrative in nature and in no way limits the present invention, its application, or its use.

[0021] Techniques, methods, and devices known to those of ordinary skill in the relevant art may not be discussed in detail, but where appropriate, such techniques, methods, and devices should be considered as part of the specification.

[0022] In all the examples shown and discussed herein, any specific values should be construed as merely exemplary and not as a limitation. Thus, other examples of the exemplary embodiments may have different values.

[0023] It should be noted that: Similar reference numerals and letters denote similar items in the following drawings, and thus, once an item is defined in one drawing, it does not need to be further discussed in subsequent drawings.

[0024] For clarity, the PEMFC thermal management system is first introduced. Refer to Figure 1 As shown, the system includes a water tank, a cooling water pump, a radiator, and a fuel cell stack (i.e., a fuel cell stack). Temperature sensors are respectively provided at the inlet and outlet of the fuel cell stack. In this system, the generated heat is first taken to the water tank by the cooling water pump by controlling the cooling water flow rate, and then the heat is taken to the radiator, and the radiator discharges the heat into the air by controlling the radiator air volume. In the present invention, it is assumed that the temperature in the cooling water is uniform, and the temperature of the cooling water at the outlet of the fuel cell stack is taken as the temperature at the outlet of the fuel cell stack, and the temperature at the outlet of the radiator is taken as the temperature at the inlet of the fuel cell stack.

[0025] Refer to Figure 2 As shown, the provided fuel cell thermal management method includes the following steps:

[0026] Step S110: For the fuel cell thermal management system, with the stack as a reference, set up an outlet fuzzy controller and an inlet fuzzy controller.

[0027] For the fuzzy logic design, two two-dimensional fuzzy controllers are adopted to control the temperatures at the inlet and outlet of the stack. According to the selected stack, set the outlet target temperature T tar.out , and set the stack inlet target temperature T tar.in . Adopt appropriate fuzzy control rules to design the fuzzy inference system. After fuzzy inference, the weighted average method can be used for defuzzification.

[0028] Fuzzy control is essentially a non-linear control and belongs to the category of intelligent control. In one embodiment, two two-dimensional Mamdani-type fuzzy controllers are established, which are respectively called the outlet fuzzy controller and the inlet fuzzy controller, for controlling the stack outlet temperature and the inlet temperature. The overall framework of the fuzzy control is as Figure 3 shown. For the stack outlet temperature control, set the stack outlet target temperature T tar.out , set the current stack outlet temperature T st.out and the error and the error change rate between the target outlet temperature T tar.out as the inputs of the outlet fuzzy controller, and the cooling water flow rate as the output of the outlet fuzzy controller. Through the cooling water, the heat generated by the stack is first brought to the water tank through the cooling water to reach the stack outlet target temperature value; after part of the heat is dissipated, the remaining heat reaches the radiator along with the cooling water. For the stack inlet temperature control, set the stack inlet target temperature T tar.in , and take the error and the change rate of the temperature error between the current stack inlet temperature T st.in and the set target temperature T tar.in as the inputs of the inlet fuzzy controller, and the radiator air volume as the output of the fuzzy controller to dissipate the remaining heat into the environment, and finally reach the stack inlet target temperature value.

[0029] Step S120: Determine the membership functions, fuzzy universes of discourse and fuzzy rules of the outlet fuzzy controller and the inlet fuzzy controller.

[0030] Regarding the design of the controller structure based on fuzzy logic, it involves the selection of membership functions, fuzzy universes of discourse and the formulation of fuzzy rules, etc. The forms of the membership functions of the fuzzy controller are diverse, the selections of the fuzzy universes of discourse are also different, and the formulations of the fuzzy rules also vary according to the control problems. To illustrate the basic principle of the control method of the present invention, in the following description, taking the triangular membership function, the input and output quantities of the fuzzy controller are divided into 7 fuzzy subsets, and the if-then control rule is adopted in the fuzzy controller as an example for illustration. It should be understood that the described idea is also applicable to other types of membership functions or control rules.

[0031] 1) Determination of membership function

[0032] For any element x in the universe of discourse U, there is a number A(x) ∈ [0, 1] corresponding to it. When x varies in U, A(x) is a function, called the membership function of A. The closer the membership degree A(x) is to 1, the higher the degree that x belongs to A; the closer A(x) is to 0, the lower the degree that x belongs to A. The membership degree of x belonging to A is characterized by the membership function A(x) taking values in the interval [0, 1]. For example, a triangular membership function is selected and expressed as:

[0033]

[0034] The membership degree shape of the fuzzy subset depends on the abscissa a of the vertex of the triangular membership function, as well as the abscissas b and c of the base, as Figure 4 shown. Optimizing the input and output language variables of the fuzzy controller is also to optimize the parameters a i , b i , c i (i represents different fuzzy subsets).

[0035] 2) Determination of fuzzy universe of discourse

[0036] When controlling the temperature at the outlet of the stack, both the input and output variables of the fuzzy control are divided into 7 fuzzy subsets, as Figure 4 shown, namely NB (Negative Big), NM (Negative Medium), NS (Negative Small), ZO (Zero), PS (Positive Small), PM (Positive Medium), and PB (Positive Big). According to the temperature control target, the fuzzy universes of discourse of the stack outlet temperature error and the temperature error change rate, as well as the fuzzy universe of discourse of the cooling water flow rate, are designed. Similarly, when designing the stack inlet temperature controller, both the input and output variables of the fuzzy control are divided into 7 fuzzy subsets, and the fuzzy universes of discourse of the stack inlet temperature error and the temperature error change rate, as well as the fuzzy universe of discourse of the radiator air velocity, are designed.

[0037] 3) Design of fuzzy rules

[0038] Fuzzy control rules are the core of the fuzzy controller and are part of the knowledge base in the fuzzy controller. Since the value ranges of each input and output variable are different, first, each basic universe of discourse is mapped to a standardized universe of discourse with different corresponding relationships. In one embodiment, the standard universe of discourse is equally discretized, and then the universe of discourse is fuzzy partitioned to define fuzzy subsets. For example, using if-then fuzzy control rules, fuzzy rules are formulated for the controlled variables respectively:

[0039]

[0040] ......

[0042]

[0043] Among them, e represents the error value, represents the change rate of the error, and ΔU represents the output of the fuzzy controller. See Table 1. After fuzzy inference, the weighted average method can be used for defuzzification.

[0044] Table 1 Example of Fuzzy Control Rules

[0045]

[0046] Step S130, use the particle swarm and genetic hybrid algorithm to optimize the membership functions of the outlet fuzzy controller and the inlet fuzzy controller to achieve temperature control of the fuel cell thermal management system.

[0047] In one embodiment, the particle swarm-genetic hybrid algorithm is used to optimize the membership function of the fuzzy controller. See Figure 5 as shown. When using the particle swarm-genetic hybrid algorithm to optimize the fuzzy controller, it is necessary to parameterize the input and output language variables of the membership function, and then through four steps: initializing each parameter, evaluating the fitness function, optimizing and updating the particle velocity and position, and selection, crossover, and mutation of individuals. Finally, the optimal individual in the last generation population is decoded, which is the optimal solution of the optimized membership function of the fuzzy controller. Input the optimal solution into the fuzzy controller, thereby improving the accuracy of the controller and making the temperature within a smaller fluctuation range.

[0048] The particle swarm algorithm (Particle Swarm Optimization, PSO) is a stochastic search algorithm based on group collaboration developed by simulating the foraging behavior of bird flocks. The genetic algorithm (Genetic Algorithm, GA) is an evolutionary algorithm, and its basic principle is to imitate the evolutionary law of "survival of the fittest" in the biological world. The particle swarm algorithm has a simple logic and a fast convergence speed, but it is easy to fall into local optima; while the genetic algorithm has a strong global search ability but a slow search speed. These two algorithms have strong complementarity.

[0049] In the embodiment of the present invention, first, use the characteristic of the fast convergence speed of the particle swarm algorithm for the first-stage optimization to obtain an initial population with a certain degree of evolution. Then, the genetic algorithm is used for the second-stage optimization to finally obtain the optimal solution of the membership function, thereby improving the accuracy of the fuzzy controller. For simplicity, the control rules and the initial state of the membership function of the stack inlet fuzzy controller and the stack outlet fuzzy controller are set to be the same. Therefore, the optimization process based on the particle swarm-genetic algorithm only introduces the fuzzy controller for the stack outlet, but the optimization process is also applicable to the inlet fuzzy controller.

[0050] See Figure 6 As shown, the overall process of optimizing a fuzzy controller using a particle swarm-genetic hybrid algorithm includes:

[0051] Step S610: Randomly generate a particle population.

[0052] For example, initialize the parameters in the objective function, randomly generate a particle population, complete the real-number encoding of the particles, and determine the fitness value range of the particles.

[0053] Step S620: Perform fitness evaluation.

[0054] Through fitness function evaluation, record the optimal solution of the particle itself and the optimal solution currently found by the entire particle population.

[0055] Step S630: Update the particle velocity and position.

[0056] For example, according to the global optimal model, loop to optimize and update the velocity and position of the particles themselves. After reaching the maximum number of iterations, output the initial optimized population.

[0057] Step S640: Perform genetic operations on the initial optimized population.

[0058] Specifically, the genetic operation process includes:

[0059] In the initial optimized population, select the individuals to be crossed according to the fitness value size, and perform the crossover operation of the genetic algorithm with a crossover probability Pc to replace and recombine part of the structures of two parent individuals to generate new individuals;

[0060] With P m as the mutation probability, perform the mutation operation to assist in generating new individuals and adding them to the offspring population;

[0061] Repeat the above genetic operations for the new generation population until reaching the maximum number of generations G max or other set termination conditions.

[0062] Step S650: When the iteration termination condition is met, decode the chromosome to output the optimal parameters.

[0063] In subsequent fuzzy control (FLC), the chromosome is assigned to the center position and width of the membership function, the control system model is run and the fitness is calculated to feedback to the particle swarm algorithm for fitness evaluation. The overall process of fuzzy control belongs to the prior art and will not be elaborated here.

[0064] The following will specifically introduce the specific embodiments of parameter initialization, fitness evaluation, updating the velocity and position of the particles, and genetic operations (including individual selection, crossover, and mutation) involved in the above process.

[0065] 1) Regarding parameter initialization

[0066] The particle swarm optimization algorithm starts from a randomly generated population. Since the membership function needs to be optimized, the parameters to be optimized are first determined, and the membership function is encoded. For example, in fuzzy control, both the input and output quantities are divided into 7 fuzzy subsets, and there are a total of 17 parameters to be optimized for the membership function, as shown in Figure 4 As shown. To more intuitively illustrate the process of initializing parameters, taking real number encoding as an example according to the number of parameters to be optimized for input and output, the shape of the membership function can be determined by 3 points: the abscissa a of the vertex, and the abscissas b and c of the bottom edge. The width range of the bottom edge interval of the triangle is stipulated, and they are sequentially encoded as {x1, x2, x3, x4,...x 17}, then the center and width of the membership function can be parameterized, and the array {x1, x2,...x 17} is the particle population after initialization, and its fitness value range is the value range [b, d] of the abscissa of the membership function, as shown in Figure 4 .

[0067] 2) Regarding fitness evaluation

[0068] In the particle swarm optimization algorithm, the fitness function is a tool for producing the optimal solution. The selection of the fitness function directly affects the convergence speed of the algorithm and whether the optimal solution can be found. The ultimate goal of the embodiment of the present invention is to adjust the width and center position of the membership function to make the temperature control more accurate. Therefore, the design of the fitness function should be as simple as possible to minimize the computational complexity. For example, the Integral Time-Weighted Absolute Error (ITAE) performance index has advantages such as fast response speed and short adjustment time, and the ITAE performance index can be selected as the fitness function. Taking the minimization of the fitness function value as the standard, the optimal solution of the particle itself and the optimal solution currently found by the entire population are recorded. Specifically expressed as:

[0069] minF = ∫1 N t|T tar -T st |dt (2)

[0070] where N is the number of individuals in the population; t is the time; T tar is the target temperature; T st is the current temperature of the stack.

[0071] 3) Update the velocity and position of the particle itself

[0072] The particle swarm optimization (PSO) algorithm relies on a population, enabling all individuals in the population to move to areas with better positions according to the change in the fitness of the environment. The PSO algorithm allows all particles to fly at a certain speed in the search space, and all particles dynamically adjust their flying speeds based on information such as their individual extreme values and global extreme values. It is a parallel global stochastic search algorithm. In the embodiments of the present invention, the abscissa a of the vertex of the membership function, as well as the abscissas b and c of the base, form an array {x1, x2,... x 17}, as the initialized particle population. According to the PSO algorithm, for particle x i (i = 1, 2,... m) at the k-th iteration, it updates its speed and position according to the global optimization model:

[0073]

[0074]

[0075] where, v id is the flying speed of particle i; x id is the position of particle i; p id is the best position experienced by particle i (p best ); p gd is the best position experienced by all particles in the population (g best ); ω is the inertia weight, responsible for adjusting the global search and local exploration capabilities of the particle swarm; c1 and c2 are acceleration constants, representing random values that pull the particle towards p best and g best ; rand() are two random numbers generated in the range [0, 1]. The initialized particle population {x1, x2,... x 17} is the initial optimized population obtained after multiple iterations.

[0076] 4) Selection, Crossover, and Mutation of Individuals

[0077] Genetic operations include selection, crossover, and mutation of individuals. For the selection operation, the purpose of selection is to select excellent individuals from the current initial optimized population, enabling them to have the opportunity to serve as parents to reproduce offspring for the next generation. The basis for selection is that individuals with strong adaptability have a greater probability of contributing one or more offspring to the next generation. For example, the roulette wheel method is used for selection. The roulette wheel method determines the probability of an individual being selected based on its fitness, that is, a selection strategy based on fitness proportion. The probability of individual i being selected is:

[0078]

[0079] where, F i , F jThey are the fitness values of individual i and individual j respectively; N is the number of individuals in the population.

[0080] For the crossover operation, for each individual, with the crossover probability P c By exchanging some chromosomes between them, new-generation individuals can be obtained. The quality of the crossover operator directly affects the convergence speed of the genetic algorithm. The abscissa a of the vertex of the membership function of the fuzzy controller, as well as the abscissas b and c of the base, form a set {x1, x2, x3, x4... x 17}, which forms the initial optimized population after being optimized by the particle swarm algorithm. The chromosome is this initial optimized population. The real number crossover method is adopted for the crossover operation. The method for the α-th chromosome c α and the β-th chromosome c β to crossover at ξ is as follows:

[0081]

[0082] where P c is the crossover probability and is a random number in [0, 1]; c αξ and c βξ are the chromosomes after the crossover operation, and the process is as Figure 7 shown.

[0083] For the mutation operation, random numbers conforming to a uniform distribution within a certain range are used respectively, with the mutation probability P m to replace the original gene values at each locus of the individual coding string. The purpose of introducing mutation is to endow the genetic algorithm with local random search ability. The particle swarm-genetic hybrid optimization algorithm of the present invention is to solve the abscissa a of the vertex of the membership function of the fuzzy controller, as well as the abscissas b and c of the base. When approaching the neighborhood of the optimal solution through the crossover operator, this local random search ability of the mutation operator can accelerate the convergence to the optimal solution.

[0084] When the iteration ends or no new changes are generated during the evolution, that is, the maximum number of generations G max is obtained, it is proved that the optimization of the fuzzy control membership function ends. Since the process of optimizing the fuzzy controller by the particle swarm-genetic hybrid algorithm is relatively complex and online optimization has certain difficulties, most of the current research in this area basically adopts the offline method, that is, after obtaining ideal results in the simulation system, it is copied into the actual fuzzy controller. The embodiment of the present invention also adopts this offline optimization method. After decoding, the optimization result is input into the fuzzy controller, and the temperature control effects of the optimized fuzzy controller and the unoptimized fuzzy controller on the fuel cell inlet and outlet temperatures are compared under the same working conditions. The optimized fuzzy control has higher temperature control accuracy than the unoptimized one.

[0085] In summary, for the optimization of the particle swarm-genetic hybrid algorithm, after parameterizing the fuzzy rules and membership function parameters, the fast convergence speed of the particle swarm algorithm is first utilized for the first-stage optimization to obtain an initial population with a certain degree of evolution. Then, the genetic algorithm is used for the second-stage optimization to finally obtain the optimal solution of the membership function, thereby improving the accuracy of the fuzzy controller.

[0086] In summary, the present invention improves the accuracy of fuel cell thermal management. With the goal of making the error between the inlet and outlet temperatures of the fuel cell stack and the target temperature value smaller, the center and width of the membership function of the fuzzy controller are optimized through the particle swarm-genetic hybrid optimization algorithm. The fuzzy control adopted has a fast response speed and is suitable for the control of lag systems. The fuzzy controller optimized by the particle swarm-genetic hybrid algorithm can better resist the changes of external loads, making the error between the inlet and outlet temperatures and the target temperature value smaller, and can be effectively applied to the fuel cell thermal management of high-power hybrid vehicles, having advantages in accuracy and stability. Verified by computer simulation, the present invention effectively improves the temperature control accuracy and stability, and can be extended to the temperature control of similar systems.

[0087] The present invention can be a system, a method, and / or a computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for causing a processor to implement various aspects of the present invention.

[0088] The computer-readable storage medium can be a tangible device that can hold and store instructions used by an instruction execution device. The computer-readable storage medium can be, for example, but not limited to, an electrical storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a static random access memory (SRAM), a portable compact disc read-only memory (CD-ROM), a digital versatile disc (DVD), a memory stick, a floppy disk, a mechanical encoding device, such as a punched card or raised structures in grooves storing instructions thereon, and any suitable combination of the above. The computer-readable storage medium used herein is not construed as an instantaneous signal itself, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through an optical fiber cable), or electrical signals transmitted through wires.

[0089] The computer-readable program instructions described herein can be downloaded to various computing / processing devices from a computer-readable storage medium or downloaded to an external computer or an external storage device through a network, such as the Internet, a local area network, a wide area network, and / or a wireless network. The network can include copper transmission cables, optical fiber transmission, wireless transmission, routers, firewalls, switches, gateway computers, and / or edge servers. A network adapter card or network interface in each computing / processing device receives the computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in each computing / processing device.

[0090] The computer program instructions for carrying out operations of the present invention may be assembly instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, state-setting data, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages - such as Smalltalk, C++, Python, etc., and conventional procedural programming languages - such as the "C" language or similar programming languages. The computer-readable program instructions may be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network - including a local area network (LAN) or a wide area network (WAN) - or, alternatively, may be connected to an external computer (e.g., through the Internet using an Internet service provider). In some embodiments, by using the state information of the computer-readable program instructions to customize an electronic circuit, such as a programmable logic circuit, a field-programmable gate array (FPGA), or a programmable logic array (PLA), the electronic circuit can execute the computer-readable program instructions to implement various aspects of the present invention.

[0091] Aspects of the present invention are described herein with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer-readable program instructions.

[0092] These computer-readable program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing apparatus to produce a machine such that, when the instructions are executed by the processor of the computer or other programmable data processing apparatus, an apparatus is created that implements the functions / acts specified in one or more blocks of the flowchart and / or block diagram. These computer-readable program instructions can also be stored in a computer-readable storage medium that causes a computer, a programmable data processing apparatus, and / or other devices to operate in a particular manner, so that the computer-readable medium storing the instructions comprises a manufacture, which includes instructions that implement various aspects of the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0093] The computer-readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices, such that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other devices to produce a computer-implemented process, so that the instructions executed on the computer, other programmable data processing apparatus, or other devices implement the functions / acts specified in one or more blocks of the flowchart and / or block diagram.

[0094] The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods, and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagram may represent a module, a segment of a program, or a portion of an instruction, which contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the figures. For example, two consecutive blocks may in fact be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block of the block diagrams and / or flowcharts, and combinations of blocks in the block diagrams and / or flowcharts, can be implemented by a dedicated hardware-based system that performs the specified functions or acts, or by a combination of dedicated hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, implementation by software, and implementation by a combination of software and hardware are equivalent.

[0095] The embodiments of the present invention have been described above. The above description is exemplary and not exhaustive, and is also not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The choice of terms used herein is intended to best explain the principles of the embodiments, the practical application, or the improvement of the technology in the market, or to enable other ordinary skilled persons in the art to understand the embodiments disclosed herein. The scope of the present invention is defined by the appended claims.

Claims

1. A thermal management method for a fuel cell, comprising the following steps: For the fuel cell thermal management system, an outlet fuzzy controller and an inlet fuzzy controller are set. Among them, the fuel cell thermal management system includes a water tank, a cooling water pump, a radiator, and an electric stack. The outlet fuzzy controller takes the error between the current electric stack outlet temperature and the set target outlet temperature and the error change rate as input quantities, and takes the cooling water flow rate as the output quantity; the inlet fuzzy controller takes the error between the current electric stack inlet temperature and the set target inlet temperature and the change rate of the error as input quantities, and takes the fan speed of the radiator as the output quantity; Determine the membership functions, fuzzy universes of the outlet fuzzy controller and the inlet fuzzy controller, and set fuzzy rules; Perform parameterization processing on the membership functions, use the parameters to be optimized as the particle population, and optimize the membership functions of the inlet fuzzy controller and the outlet fuzzy controller to control the current cooling water flow rate of the fuel cell thermal management system and the fan speed of the radiator; Among them, the membership function is set as a triangular membership function, and this triangular membership function is characterized by the abscissa of the vertex and the two abscissas of the base, and the input quantities and output quantities of the outlet fuzzy controller and the inlet fuzzy controller are divided into seven fuzzy subsets, including negative large, negative medium, negative small, zero, positive small, positive medium, and positive large; Among them, the parameterization processing of the membership function, using the parameters to be optimized as the particle population, and optimizing the membership functions of the inlet fuzzy controller and the outlet fuzzy controller includes: Perform parameterization processing on the fixed-point abscissa and the two abscissas of the base of the triangular membership function based on the seven divided fuzzy subsets as the particle population, and use the value range of the abscissa of the triangular membership function as the fitness value; Taking the minimization of the set fitness function as the criterion, determine the optimal solution of the particle itself and the optimal solution of the entire particle population to adjust the width and center position of the triangular membership function; According to the global optimal model, cycle and optimize to update the velocity and position of the particle itself, and then output the initial optimized population; Taking the initial optimized population as the chromosome, use the genetic algorithm to perform operations of individual selection, crossover, and mutation to realize the optimization process for the initial optimized population.

2. The method according to claim 1, characterized in that, Set the fitness function as: minF = ∫1 N t|T tar -T st |dt Among them, N is the number of individuals in the particle population, t is the time, and T tar is the target temperature, and T st is the current temperature of the fuel cell stack.

3. The method according to claim 1, characterized in that The cycle of optimizing and updating the velocity and position of the particle itself according to the global optimal model includes: for particle i, the updated velocity and position at the kth iteration are expressed as: Among them, v id is the velocity of particle i, x id is the position of particle i, p id is the best position experienced by particle i, p gd is the best position experienced by all particles in the swarm, ω is the inertia weight, c1 and c2 are acceleration constants, rand() is a random number generated in the range [0, 1], is the position of the particle after update, is the velocity after update, is the velocity of particle i before update, is the position of particle i before update.

4. The method according to claim 1, characterized in that For the selection, crossover, and mutation operations of individuals performed using a genetic algorithm, the crossover operation adopts a real number crossover method. The α-th chromosome c α and the β-th chromosome c β crossing at ξ is represented as: Among them, P c is the crossover probability, which is a random number in [0, 1]. The c αξ , c βξ on the left side of the equal sign are the chromosomes after the crossover operation, and the c αξ , c βξ on the right side of the equal sign are the chromosomes before the crossover operation.

5. The method according to claim 1, characterized in that For the operations of individual selection, crossover, and mutation using the genetic algorithm, the individual selection adopts a selection strategy based on fitness proportion, and the probability that individual i is selected is expressed as: where, F i and F j are the fitness values of individual i and individual j respectively, and N is the number of individuals in the particle population.

6. The method according to claim 1, characterized in that, Adopt the if-then fuzzy control rule for the fuzzy rules.

7. A computer-readable storage medium having a computer program stored thereon, wherein, When the computer program is executed by the processor, it realizes the steps of the method according to any one of claims 1 to 6.

8. A computer device, comprising a memory and a processor, wherein a computer program capable of running on the processor is stored on the memory, and is characterized in that When the processor executes the computer program, it realizes the steps of the method according to any one of claims 1 to 6.

Images