Fuel cell temperature control method and system based on decoupling control combined with fuzzy PID (Proportion Integration Differentiation)

Abstract

The invention discloses a fuel cell temperature control method and system based on the combination of decoupling control and fuzzy PID, and the method comprises the steps: building a fuel cell thermal management system based on a Matlab / Simulink platform, and obtaining the temperature changes of a fuel cell under different working conditions; performing system identification on the built fuel cell thermal management system to obtain transfer function matrixes of different balance points; designing a feedforward decoupling controller through the transfer function matrix obtained through identification; a fuzzy PID controller is designed for the fuel cell thermal management subsystem, and PID control parameters are adjusted in a self-adaptive mode according to the error between the expected temperature and the actual temperature and the error change rate; and finally, a fuzzy membership function and a fuzzy rule in fuzzy control are optimized by adopting a PSO algorithm, so that a better temperature control effect is realized. Compared with a traditional control method, the control precision is improved, the method has the advantages of being high in robustness, small in overshoot, short in adjustment time and the like, and the problems that a fuel cell thermal management system is high in nonlinearity and coupling performance are solved to a certain extent.

Description

Technical Field

[0001] The present invention belongs to the technical field of fuel cell thermal management, and in particular relates to a fuel cell temperature control method and system based on decoupling control combined with fuzzy PID. Background Art

[0002] With the increasing severity of environmental pollution and energy crisis, the development of clean energy is in full swing. Among them, the proton exchange membrane fuel cell (PEMFC) is considered to be the most promising energy conversion device due to its advantages such as low operating temperature, high energy conversion efficiency, no pollution, and high power density. It has received extensive attention and research.

[0003] Temperature is the most important factor affecting the working performance of fuel cells. Too low stack temperature will reduce the electrochemical reaction rate and the conductivity of the exchange membrane, resulting in a decrease in output performance; however, too high temperature will cause the exchange membrane to dehydrate or even degrade, resulting in irreversible damage. At the same time, in order to reduce the damage of thermal stress to the PEMFC stack, it is necessary to maintain a suitable inlet and outlet cooling water temperature difference. In actual engineering, the PEMFC thermal management system usually adjusts the water pump and fan to achieve the inlet cooling water temperature and the inlet and outlet cooling water temperature difference to maintain efficient and stable operation of the PEMFC.

[0004] At present, the most widely used control method in PEMFC thermal management system is still classic PID control. However, the control loops of the water pump and the fan are coupled with each other, which will cause overshoot superposition and prolonged adjustment time. In order to reduce the coupling effect of the two control loops, feedforward decoupling can be used to offset the coupling effect by introducing compensation in advance. At the same time, since the control parameters Kp, Ki, and Kd of classic PID are fixed, the control effect for nonlinear systems such as PEMFC thermal management system is not ideal. Therefore, fuzzy control can be used to optimize PID so that the control parameters change adaptively according to the system state. However, the control rules and membership functions of fuzzy control are determined based on experience, and need to be changed and optimized according to specific problems to achieve the best control effect. Summary of the invention

[0005] In order to solve the problems in the prior art, the present invention provides a fuel cell temperature control method and system based on decoupling control combined with fuzzy PID, which realizes effective control of PEMFC temperature. The present invention first obtains the system transfer function matrix of the PEMFC thermal management system at different equilibrium points through system identification, and designs feedforward decoupling control based on this. Then, the present invention uses fuzzy control to optimize PID, and optimizes the fuzzy control rules and membership functions of the water pump side and the fan side respectively through the PSO algorithm, thereby further improving the temperature control effect.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: A fuel cell temperature control method based on decoupling control combined with fuzzy PID includes the following steps: S1, according to the physical characteristics of the fuel cell stack, water pump, water tank, heater, radiator and fan in the thermal management system of the proton exchange membrane fuel cell, build a dynamic model of the fuel cell PEMFC thermal management system based on the MATLAB / Simulink simulation platform; S2, according to the dynamic model of the fuel cell PEMFC thermal management system established in step S1, the system transfer function matrix of the fuel cell thermal management system at different equilibrium points is obtained through system identification, S3, using a PID controller to control the PEMFC temperature, and designing a feedforward decoupling controller according to the system transfer function matrix of the PEMFC thermal management system at different equilibrium points obtained in S2; S4, using fuzzy control to optimize the feedforward decoupling controller in S3 to obtain a fuzzy PID temperature controller; S5, the fuzzy PID temperature controller obtained in S4 is optimized by using a particle swarm algorithm, the decision variables are selected as the fuzzy control rules and membership functions on the water pump side and the fan side, and the optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller to achieve temperature control of the fuel cell.

[0007] A further improvement of the present invention is that in step S1, a dynamic model of a fuel cell PEMFC thermal management system is constructed, including: Fuel cell stack; A cooling branch, the cooling branch comprising an input port and an output port at both ends, and a water pump, a water tank, a three-way valve, a radiator and a fan connected in sequence between the input port and the output port, the input port being connected to the coolant outlet of the fuel cell stack, the output port being connected to the coolant inlet of the fuel cell stack, the three-way valve inlet being connected to the water tank, the first outlet being connected to the coolant circuit, and the second outlet being connected to the heating branch; A heating branch, wherein both ends of the heating branch are respectively connected between the outlet of the three-way valve and the pipeline after the radiator on the coolant circuit, and the heating branch comprises a water pump, a water tank, a three-way valve and a heater; A control module, the control module is connected to the water pump, the radiator and the fan respectively, and the control module is used to control the rotation speed of the radiator and the fan to achieve control of the temperature of the coolant of the fuel cell stack; the control strategy of the control module is: Start-up phase: When the fuel cell stack is in the startup phase, the first outlet of the three-way valve is controlled to be closed and the second outlet is opened, and the heater is turned on to preheat the coolant through the heating branch so that the fuel cell stack reaches a suitable operating temperature as soon as possible. Stable operation phase: When the fuel cell stack is in the stable operation phase, the second outlet of the three-way valve is controlled to be closed and the first outlet is opened, the heater is turned off, and excess heat is transferred to the environment through the heat dissipation branch to control the appropriate operating temperature of the fuel cell stack and maintain stable operation.

[0008] A further improvement of the present invention is that in step S2, according to the dynamic model of the fuel cell PEMFC thermal management system established in step S1, the system transfer function matrix of the fuel cell thermal management system at different equilibrium points is obtained through system identification, including: The input of the thermal management system is the speed of the water pump and the speed of the fan, and the output is the coolant inlet and outlet temperature difference and the cooling water inlet temperature. It is a dual-input and dual-output coupled system. Through system identification, a 2×2 system transfer function matrix is ​​obtained, which is expressed as: (1) Where: is the cooling water flow rate, is the air flow rate, is the actual temperature difference of the cooling water at the inlet and outlet of the stack, is the cooling water temperature at the stack inlet; the system identification adopts step response; in order to obtain the system transfer function matrix, firstly, five equilibrium working points are selected within the input current working range, and then step disturbances are applied to the input of the PEMFC thermal management system respectively to obtain the step response of the corresponding output, and finally the transfer function matrix at different equilibrium points is obtained through system identification; Based on the coolant inlet and outlet temperature difference and the step response of the coolant inlet temperature to the coolant flow rate and air flow rate, five operating current points were selected as the equilibrium operating points, and the transfer function matrix of the PEMFC thermal management system was identified; the transfer function of the equilibrium operating point can be identified through MATLAB's system identification toolbox.

[0009] A further improvement of the present invention is that in step S3, a PID controller is used to control the PEMFC temperature, and a feedforward decoupling controller is designed according to the system transfer function matrix of the PEMFC thermal management system at different equilibrium points obtained in S2, including: Firstly, the speed of the water pump and the fan are adjusted respectively by two independent PID controllers to control the temperature difference between the inlet and outlet of the cooling water of the fuel cell and the inlet temperature of the cooling water. Then, the feedforward compensation decoupling method is adopted, and the system transfer function is used to obtain the feedforward decoupling coefficients N21 and N12. By introducing the feedforward compensation, the coupling relationship in the thermal management system is eliminated, so that the dual-input dual-output thermal management system becomes two independent single-input single-output systems. The speed of the water pump affects the inlet and outlet temperature difference of the coolant, and the speed of the fan affects the inlet temperature of the cooling water, thereby realizing the decoupling control of the PRMFC thermal management system. The PID controller can generate the corresponding control quantity according to the error. The PID control algorithm is expressed as: (2) The error e(t)=TS(t)-T(t) between the expected temperature value TS(t) and the actual temperature value T(t) is selected as the input of the PID temperature controller, and the output control action u(t) is obtained through proportional, integral and differential operations; the temperature value on the water pump side is the temperature difference between the inlet and outlet cooling water of the stack, the expected temperature is 10K, and the control action of the PID output is the coolant flow rate; the temperature value on the fan side is the inlet cooling water temperature of the stack, the expected temperature is 333K, and the control action of the PID output is the air flow rate; The principle and method of the feedforward decoupling are as follows: adopting the system identification method, obtaining the system transfer function, calculating and obtaining the feedforward decoupling coefficients N21 and N12 according to the invariance principle, and eliminating the coupling relationship in the thermal management system by introducing the feedforward compensation amount, thereby realizing the decoupling control between the cooling water flow and the air flow; The parameters in feedforward decoupling control are defined as: Corresponding cooling water flow rate, Corresponding air flow rate, and Represent the feedforward compensation transfer function and transfer function respectively. and Respectively represent the cooling water flow rate and the temperature difference of the fuel cell cooling water inlet and outlet and fuel cell cooling water inlet temperature The impact of and Respectively represent the cooling water flow rate and the temperature difference of the fuel cell cooling water inlet and outlet and fuel cell cooling water inlet temperature In order to eliminate the coupling relationship through compensation, a feedforward decoupling controller is designed according to the invariance principle: (3) (4) The transfer function of the feedforward compensator is obtained as: (5) (6) In the above formula , , and All come from the identified transfer function matrix.

[0010] A further improvement of the present invention is that in step S4, the feedforward decoupling controller in S3 is optimized by fuzzy control to obtain a fuzzy PID temperature controller, including: Optimize PID through fuzzy control to realize the function of self-tuning control parameters. Select the fuel cell temperature error e(t) and its error change rate ec(t) as the input of the fuzzy PID temperature controller, and take the parameter adjustment ΔKp, ΔKp, ΔKd of the PID controller as the output, where ΔKp, ΔKp, ΔKd are the changes of the three parameters Kp, Ki, Kd corresponding to the proportional integral P, integral I and differential D respectively; divide the input and output of the PID temperature controller into 7 fuzzy sets, and use the triangular membership function for the membership function to fuzzify the variables and defuzzify the fuzzy variables. The membership function is expressed as: (7) Among them: a, c are the values ​​of the triangular function on the horizontal axis, and b is the vertex of the triangular function.

[0011] A further improvement of the present invention is that in step S5, the PSO algorithm is applied to optimize the fuzzy control rules and membership functions in the fuzzy PID on the water pump side and the fan side respectively; in the PSO algorithm, the speed and position of each particle are calculated based on the difference between the current position and the historical optimal position; in the D-dimensional search space, the speed and position update formula of each particle is as follows: (8) (9) Where: and are the velocity and position of the particle, and is the particle’s current position information and the particle’s historical optimal position information, , s is the inertia factor, and are two random numbers generated independently in [0,1]. and is the acceleration coefficient; the first part of formula (8) is called the memory term, which represents the influence of the last speed and direction; the second part is called the self-cognition term, which is a vector pointing from the current point to the best point of the particle itself, indicating that the action of the particle comes from its own experience; the third part is called the group cognition term, which is a vector pointing from the current point to the best point of the population, reflecting the collaboration and knowledge sharing among particles; each particle learns from its own best experience and the best experience of the population, and continuously updates its position through formula (9), thereby approaching the global optimal solution.

[0012] A further improvement of the present invention is that in step S5, the integrated absolute error of the stack temperature is selected as the fitness function, and the smaller the IAE, the better the temperature control effect: (10) Specifically, select the temperature difference of the cooling water at the inlet and outlet of the stack For preset temperature value The IAE is IAE1, and the stack inlet cooling water temperature is selected For preset temperature value The IAE is IAE2, and the fitness function of the PSO algorithm is constructed as follows: (11) The PSO algorithm will optimize the fuzzy PID in the direction of continuously reducing the fitness function, thereby achieving better control effects.

[0013] A further improvement of the present invention is that, in step S5, an improved particle swarm algorithm is used to optimize the fuzzy control rules and membership functions on the water pump side and the fan side in the fuzzy PID temperature controller, respectively, and the optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller; the input and output variables are divided into 7 fuzzy sets, and a triangular membership function is used to optimize the vertex position of each triangular membership function. There are a total of 5 input and output variables, so the membership function has 5×7=35 decision variables that need to be optimized; the fuzzy control adopts an if-then structure, so the two inputs each have 7 fuzzy sets, and every two input fuzzy sets correspond to an output fuzzy set, and there are a total of 3 outputs, so the fuzzy rules have decision variables need to be optimized; and because the water pump side and the fan side use fuzzy PID temperature controllers, they need to be optimized using the improved particle swarm algorithm. There are decision variables that need to be optimized.

[0014] Fuel cell temperature control system based on decoupling control combined with fuzzy PID, including: Dynamic model building module, based on the MATLAB / Simulink simulation platform, builds a dynamic model of the fuel cell PEMFC thermal management system according to the physical characteristics of the stack, water pump, water tank, heater, radiator and fan in the proton exchange membrane fuel cell thermal management system; The system transfer function matrix identification module is based on the dynamic model of the fuel cell PEMFC thermal management system established by the dynamic model building module. Through system identification, the system transfer function matrix of the fuel cell thermal management system at different equilibrium points is obtained. The feedforward decoupling controller design module uses a PID controller to control the PEMFC temperature, and designs a feedforward decoupling controller based on the system transfer function matrix of the PEMFC thermal management system at different equilibrium points obtained in the system transfer function matrix identification module; A fuzzy PID temperature controller obtaining module uses the fuzzy control to optimize the feedforward decoupling controller in the feedforward decoupling controller design module to obtain a fuzzy PID temperature controller; The fuel cell temperature control module uses a particle swarm algorithm to optimize the fuzzy PID temperature controller obtained in the fuzzy PID temperature controller acquisition module. The decision variables are selected as the fuzzy control rules and membership functions on the water pump side and the fan side. The optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller to achieve fuel cell temperature control.

[0015] A further improvement of the present invention is that in the dynamic model building module, a dynamic model of a fuel cell PEMFC thermal management system is built, including: Fuel cell stack; A cooling branch, the cooling branch comprising an input port and an output port at both ends, and a water pump, a water tank, a three-way valve, a radiator and a fan connected in sequence between the input port and the output port, the input port being connected to the coolant outlet of the fuel cell stack, the output port being connected to the coolant inlet of the fuel cell stack, the three-way valve inlet being connected to the water tank, the first outlet being connected to the coolant circuit, and the second outlet being connected to the heating branch; A heating branch, wherein both ends of the heating branch are respectively connected between the outlet of the three-way valve and the pipeline after the radiator on the coolant circuit, and the heating branch comprises a water pump, a water tank, a three-way valve and a heater; A control module, the control module is connected to the water pump, the radiator and the fan respectively, and the control module is used to control the rotation speed of the radiator and the fan to achieve control of the temperature of the coolant of the fuel cell stack; the control strategy of the control module is: Start-up phase: When the fuel cell stack is in the startup phase, the first outlet of the three-way valve is controlled to be closed and the second outlet is opened, and the heater is turned on to preheat the coolant through the heating branch so that the fuel cell stack reaches a suitable operating temperature as soon as possible. Stable operation phase: When the fuel cell stack is in the stable operation phase, the second outlet of the three-way valve is controlled to be closed and the first outlet is opened, the heater is turned off, and excess heat is transferred to the environment through the heat dissipation branch to control the appropriate operating temperature of the fuel cell stack and maintain stable operation.

[0016] Compared with the prior art, the present invention has at least the following beneficial technical effects: The fuel cell temperature control method and system based on decoupling control combined with fuzzy PID provided by the present invention adopt system identification to obtain the system transfer function matrix, and reduce the coupling effect of the inlet and outlet cooling water temperature difference and the inlet cooling water temperature control loop in the water-cooled PEMFC thermal management system through a feedforward decoupling control method, and simplify the mutually coupled dual-input dual-output PEMFC thermal management system into two uncoupled single-input single-output systems; the present invention adopts the PSO algorithm to optimize the fuzzy rules and membership functions of the fuzzy PID on the water pump side and the fan side respectively, and the fitness function is selected as the sum of IAE1 of the inlet and outlet temperature difference and IAE2 of the inlet cooling water temperature, thereby further improving the temperature control effect of the fuzzy PID. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 This is the structural block diagram of the PEMFC thermal management system.

[0018] Figure 2 This is the schematic diagram of feedforward decoupling control.

[0019] Figure 3 This is a schematic diagram of the temperature control algorithm in the present invention.

[0020] Figure 4 It is the PSO iteration curve.

[0021] Figure 5 This is the control effect diagram of the imported cooling water temperature (comparing feedforward + dual PID, feedforward + fuzzy dual PID, feedforward + PSO fuzzy dual PID respectively).

[0022] Figure 6 This is the control effect diagram of the inlet and outlet cooling water temperature difference (comparing feedforward + dual PID, feedforward + fuzzy dual PID, feedforward + PSO fuzzy dual PID respectively).

[0023] Figure 7 shows the membership function of the fuzzy PID before and after PSO optimization. Figure 7(a) is the membership function of the fuzzy PID input on the water pump side before PSO optimization. Figure 7(b) is the membership function of the fuzzy PID output on the water pump side before PSO optimization. Figure 7(c) is the membership function of the fuzzy PID input on the water pump side after PSO optimization. Figure 7(d) is the membership function of the fuzzy PID input on the fan side after PSO optimization. Figure 7(e) is the membership function of the fuzzy PID output on the water pump side after PSO optimization. Figure 7(f) is the membership function of the fuzzy PID output on the fan side after PSO optimization.

[0024] Figure 8 shows the fuzzy rules of fuzzy PID before and after PSO optimization. Figure 8(a) shows the fuzzy rules on the water pump side before PSO optimization, Figure 8(b) shows the fuzzy rules on the fan side before PSO optimization, Figure 8(c) shows the fuzzy rules on the water pump side after PSO optimization, and Figure 8(d) shows the fuzzy rules on the fan side after PSO optimization.

[0025] Fig. 9 It is a structural block diagram of a fuel cell temperature control system based on decoupling control combined with fuzzy PID according to the present invention. DETAILED DESCRIPTION

[0026] In the following, only some exemplary embodiments are briefly described. As those skilled in the art will appreciate, the described embodiments may be modified in various ways without departing from the spirit or scope of the present invention. Therefore, the drawings and descriptions are considered to be exemplary and non-restrictive in nature.

[0027] It should be understood that when used in this specification and the appended claims, the terms "include" and "comprises" indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.

[0028] It should also be understood that the terms used in the present specification are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the present specification and the appended claims, the singular forms "a", "an" and "the" are intended to include plural forms unless the context clearly indicates otherwise.

[0029] It should be further understood that the term "and / or" used in the present description and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.

[0030] Various structural schematic diagrams of the embodiments disclosed in the present invention are shown in the accompanying drawings. These figures are not drawn to scale, and some details are magnified and some details may be omitted for the purpose of clear expression. The shapes of various regions and layers shown in the figures and the relative sizes and positional relationships therebetween are only exemplary, and may deviate in practice due to manufacturing tolerances or technical limitations, and those skilled in the art may additionally design regions / layers with different shapes, sizes, and relative positions according to actual needs.

[0031] The embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0032] Example 1 The fuel cell temperature control method based on decoupling control combined with fuzzy PID provided by the present invention comprises the following steps: S1, according to the physical characteristics of the fuel cell stack, water pump, water tank, heater, radiator and fan in the thermal management system of proton exchange membrane fuel cells, build a fuel cell PEMFC thermal management system based on the MATLAB / Simulink simulation platform; S2, according to the dynamic model of the fuel cell PEMFC thermal management system established in step S1, obtaining the system transfer function matrix of the fuel cell thermal management system at different equilibrium points through system identification; S3, using a PID controller to control the PEMFC temperature, and designing a feedforward decoupling controller according to the system transfer function matrix of the PEMFC thermal management system at different equilibrium points obtained in S2; S4, using fuzzy control to optimize the feedforward decoupling controller in S3 to obtain a fuzzy PID temperature controller; S5, the particle swarm algorithm is used to optimize the fuzzy PID temperature controller obtained in S4, the decision variables are selected as the fuzzy control rules and membership functions on the water pump side and the fan side, and the optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller.

[0033] In step S1, the present invention provides a model of a fuel cell thermal management system, and its specific structure is referenced Figure 1 ,include: a) fuel cell stack; b) a cooling branch, the cooling branch comprising an input port and an output port at both ends, and a water pump, a water tank, a three-way valve, a radiator and a fan connected in sequence between the input port and the output port, the input port being connected to the coolant outlet of the fuel cell stack, the output port being connected to the coolant inlet of the fuel cell stack, the inlet of the three-way valve being connected to the water tank, the first outlet being connected to the coolant circuit, and the second outlet being connected to the heating branch; c) a heating branch, wherein two ends of the heating branch are respectively connected between the outlet of the three-way valve and the pipeline after the radiator on the coolant circuit, and the heating branch includes a water pump, a water tank, a three-way valve and a heater; d) a control module, the control module is connected to the water pump, the radiator and the fan respectively, and the control module is used to control the rotation speed of the radiator and the fan to control the temperature of the coolant of the fuel cell stack; the control strategy of the control module is: Startup phase: When the fuel cell stack is in the startup phase, the first outlet of the three-way valve is controlled to be closed, the second outlet is controlled to be opened, and the heater is turned on to preheat the coolant through the heating branch so that the fuel cell stack reaches a suitable operating temperature as soon as possible. Stable operation stage: When the fuel cell stack is in the stable operation stage, the second outlet of the three-way valve is controlled to be closed and the first outlet is opened, the heater is turned off, and the excess heat is transferred to the environment through the heat dissipation branch to control the appropriate operating temperature of the battery stack and maintain efficient and stable operation.

[0034] In step S2, the input of the thermal management system is the speed of the water pump and the speed of the fan, and the output is the coolant inlet and outlet temperature difference and the cooling water inlet temperature. It is a dual-input and dual-output coupling system. Through system identification, a 2×2 system transfer function matrix can be obtained, which is expressed as: (1) Where: is the cooling water flow rate, is the air flow rate, The actual stack inlet and outlet cooling transfer function matrix is ​​firstly selected within the input current working range, and then step disturbances are applied to the input of the PEMFC thermal management system to obtain the step response of the corresponding output. Finally, the transfer function matrix at different equilibrium points is obtained through system identification. Based on the coolant inlet and outlet temperature difference and the step response of the coolant inlet temperature to the coolant flow rate and the air flow rate, the present invention selects five operating current points as the equilibrium operating points to identify the transfer function matrix of the PEMFC thermal management system. The transfer function of the equilibrium operating point can be identified through the system identification toolbox of MATLAB, as shown in Table 1.

[0035] Table 1 Transfer function matrix under different current conditions

[0036] In step S3, reference Figure 2The decoupling control principle adopted by the present invention is: establish a feedforward decoupling control based on dual PID control, firstly adjust the speed of the water pump and the fan respectively through two independent PID controllers to control the temperature difference between the inlet and outlet of the cooling water of the fuel cell and the inlet temperature of the cooling water, then adopt the method of feedforward compensation decoupling, use the system transfer function, obtain the feedforward decoupling coefficients N21 and N12, and eliminate the coupling relationship in the thermal management system by introducing the feedforward compensation amount, so that the thermal management system of the dual input dual output (Dual Input Dual Output system, DIDO) becomes two independent single input single output (Single Input Single Output system, SISO) systems. The speed of the water pump only affects the inlet and outlet temperature difference of the coolant, and the speed of the fan only affects the inlet temperature of the cooling water, thereby realizing the decoupling control of the PRMFC thermal management system; The PID controller is widely used in practical engineering due to its simple structure, strong robustness and easy implementation. The PID controller can generate the corresponding control quantity according to the error. The PID control algorithm can be expressed as: (2) The present invention selects the error e(t)=TS(t)-T(t) between the expected temperature value TS(t) and the actual temperature value T(t) as the input of the PID temperature controller, and obtains the output control action u(t) through proportional, integral and differential operations; the temperature value on the water pump side is the temperature difference between the inlet and outlet cooling water of the stack, the expected temperature is 10K, and the control action of the PID output is the coolant flow rate; the temperature value on the fan side is the inlet cooling water temperature of the stack, the expected temperature is 333K, and the control action of the PID output is the air flow rate; The principle and method of the feedforward decoupling are as follows: adopting the system identification method, obtaining the system transfer function, calculating and obtaining the feedforward decoupling coefficients N21 and N12 according to the invariance principle, and eliminating the coupling relationship in the thermal management system by introducing the feedforward compensation amount, thereby realizing the decoupling control between the cooling water flow and the air flow; If the PEMFC thermal management system is completely decoupled, the design of the decoupling controller will be very complicated, which will affect its practical use to a certain extent. Therefore, the present invention first adopts feedforward decoupling. If feedforward decoupling can achieve stable control of PEMFC temperature and reduce the coupling effect of different control loops, then feedforward decoupling can simplify the design of the decoupling controller and has high practical application value.

[0037] The parameters in feedforward decoupling control are defined as: Corresponding cooling water flow rate, Corresponding air flow rate, and Represent the feedforward compensation transfer function and transfer function respectively. and Respectively represent the cooling water flow rate and the temperature difference of the fuel cell cooling water inlet and outlet and fuel cell cooling water inlet temperature The impact of and Respectively represent the cooling water flow rate and the temperature difference of the fuel cell cooling water inlet and outlet and fuel cell cooling water inlet temperature In order to eliminate the coupling relationship through compensation, a feedforward decoupling controller is designed according to the invariance principle: (3) (4) The transfer function of the feedforward compensator can be obtained as: (5) (6) In the above formula , , and All of them come from the identified transfer function matrix; let s=0 in the feedforward compensation transfer function to obtain the static feedforward decoupling coefficient, as shown in Table 2: Table 2 Static feedforward decoupling coefficients under different current conditions

[0038] In step S4, since the control parameters Kp, Ki, Kd of the traditional PID control algorithm are fixed and cannot be adaptively changed according to the system state, it is not suitable for a strong nonlinear system such as a PEMFC thermal management system. Fuzzy control is a control method that uses human knowledge and experience and is often used in complex nonlinear systems. By optimizing PID through fuzzy control, the function of self-tuning of control parameters can be realized, thereby improving the control effect of traditional PID; the fuel cell temperature error e(t) and its error change rate ec(t) are selected as the input of the fuzzy PID temperature controller, and the parameter adjustment amounts ΔKp, ΔKp, ΔKd of the PID controller are used as the output, wherein: ΔKp, ΔKp, ΔKd are the changes of three parameters Kp, Ki, Kd corresponding to the proportional integral P, the integral I and the differential D respectively; the input and output of the PID temperature controller are divided into 7 fuzzy sets: NB (negative large), NM (negative medium), NS (negative small), ZE (zero), PS (positive small), PM (positive medium), PB (positive large), the present invention adopts a triangular membership function for the membership function to fuzzify the variables and defuzzify the fuzzy variables, and its membership function is expressed as: (7) Among them: a, c are the values ​​of the triangular function on the horizontal axis, and b is the vertex of the triangular function.

[0039] In step S5, reference Figure 3 The thermal management system of the present invention is feedforward decoupling control, wherein the temperature control algorithm principle is: the PSO algorithm is used to optimize the fuzzy control rules and membership functions in the fuzzy PID on the water pump side and the fan side respectively; the particle swarm optimization (PSO) algorithm is a group optimization algorithm with the advantages of fast algorithm convergence and strong versatility; in the PSO algorithm, the speed and position of each particle are calculated based on the difference between the current position and the historical optimal position; in the D-dimensional search space, the speed and position update formula of each particle is as follows: (8) (9) Where: and are the velocity and position of the particle, and is the particle’s current position information and the particle’s historical optimal position information, , s is the inertia factor, and are two random numbers generated independently in [0,1]. and is the acceleration coefficient; the first part of formula (8) is called the memory term, which represents the influence of the last speed and direction; the second part is called the self-cognition term, which is a vector pointing from the current point to the best point of the particle itself, indicating that the particle's action comes from its own experience; the third part is called the group cognition term, which is a vector pointing from the current point to the best point of the population, reflecting the collaboration and knowledge sharing between particles. Each particle can learn from its own best experience and the best experience in the population, and continuously update its position through formula (9), thereby approaching the global optimal solution; In step S5, the integral absolute error (IAE) of the stack temperature is selected as the fitness function, and the smaller the IAE, the better the temperature control effect.

[0040] (10) Specifically, select the temperature difference of the cooling water at the inlet and outlet of the stack For preset temperature value The IAE is IAE1, and the stack inlet cooling water temperature is selected For preset temperature value The IAE is IAE2, and the fitness function of the PSO algorithm is constructed as follows: (11) The PSO algorithm will optimize the fuzzy PID in the direction of continuously reducing the fitness function, thereby achieving better control effects.

[0041] Referring to Table 3, the IAE of the two variables, the inlet cooling water temperature and the inlet and outlet cooling water temperature difference, are compared under different control methods. It can be seen that the introduction of feedforward decoupling can improve the control effect of dual PID. The control effect can be further enhanced by optimizing PID through fuzzy control. Finally, the best control effect can be achieved by optimizing fuzzy control rules and membership functions through PSO algorithm. Each of the above optimization steps has achieved the improvement of control effect.

[0042] Table 3 Control effects under different control methods

[0043] refer to Figure 4 , the fitness function of the PSO algorithm adopted by the present invention continues to decrease with the increase of the number of iterations, indicating that the fuzzy rules and membership functions are continuously optimized during the iteration process, and the final fitness function is reduced to 73.44% of the initial value, and the temperature control effect is significantly improved; refer to Figure 5 , the present invention compares the control effects of the inlet cooling water temperature under different control methods. It can be seen that the proposed feedforward decoupling combined with PSO algorithm to optimize the fuzzy PID controller, compared with the feedforward decoupling combined with PID controller and the feedforward decoupling combined with fuzzy PID controller, has a smaller overshoot and a shorter adjustment time, that is, the optimization method has a better control effect on the inlet cooling water temperature; refer to Figure 6 , the present invention compares the control effects of the inlet and outlet cooling water temperature difference under different control methods. It can be seen that the proposed feedforward decoupling combined with PSO algorithm to optimize the fuzzy PID controller, the feedforward decoupling combined with PID controller and the feedforward decoupling combined with fuzzy PID controller, that is, the optimization method has a better control effect on the inlet and outlet cooling water temperature difference control effect; In step S5, an improved particle swarm algorithm is used to optimize the fuzzy control rules and membership functions of the water pump side and the fan side in the fuzzy PID temperature controller, and the optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller; the input and output variables are divided into 7 fuzzy sets, and a triangular membership function is used to optimize the vertex position of each triangular membership function. There are 5 input and output variables in total, so the membership function has 5×7=35 decision variables to be optimized; the fuzzy control adopts an if-then structure, so there are 7 fuzzy sets for each of the two inputs, and every two input fuzzy sets correspond to one output fuzzy set, and there are 3 outputs in total, so the fuzzy rules have decision variables need to be optimized; and because the water pump side and the fan side use fuzzy PID temperature controllers, they need to be optimized using the improved particle swarm algorithm. decision variables need to be optimized; The present invention adopts the PSO algorithm to optimize the membership function of the fuzzy PID controller, which includes two input variables e and ec and three output variables ΔKp, ΔKi, ΔKd on both sides of the water pump and the fan, and each variable has 7 membership functions respectively; referring to FIG7 , it can be seen that the vertex position of each triangular membership function is shifted after optimization, that is, the PSO algorithm achieves the goal of improving the temperature control effect by optimizing the membership function; The present invention uses the PSO algorithm to optimize the fuzzy rules of the fuzzy PID controller, including the fuzzy rules of the three output variables ΔKp, ΔKi, and ΔKd jointly determined by the two input variables e and ec on both sides of the water pump and the fan; in order to intuitively reflect the changes in the fuzzy rules, the present invention uses a fuzzy rule surface representation, and one fuzzy rule surface corresponds to 49 fuzzy rules. Referring to Figure 8, it can be seen that each fuzzy rule surface has changed after optimization, that is, the PSO algorithm achieves the goal of improving the temperature control effect by optimizing the fuzzy rules.

[0044] Example 2 refer to Fig. 9 The fuel cell temperature control system based on decoupling control combined with fuzzy PID provided by the present invention comprises: Dynamic model building module, based on the MATLAB / Simulink simulation platform, builds a dynamic model of the fuel cell PEMFC thermal management system according to the physical characteristics of the stack, water pump, water tank, heater, radiator and fan in the proton exchange membrane fuel cell thermal management system; The system transfer function matrix identification module is based on the dynamic model of the fuel cell PEMFC thermal management system established by the dynamic model building module. Through system identification, the system transfer function matrix of the fuel cell thermal management system at different equilibrium points is obtained. The feedforward decoupling controller design module uses a PID controller to control the PEMFC temperature, and designs a feedforward decoupling controller based on the system transfer function matrix of the PEMFC thermal management system at different equilibrium points obtained in the system transfer function matrix identification module; A fuzzy PID temperature controller obtaining module uses the fuzzy control to optimize the feedforward decoupling controller in the feedforward decoupling controller design module to obtain a fuzzy PID temperature controller; The fuel cell temperature control module uses a particle swarm algorithm to optimize the fuzzy PID temperature controller obtained in the fuzzy PID temperature controller acquisition module. The decision variables are selected as the fuzzy control rules and membership functions on the water pump side and the fan side. The optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller to achieve fuel cell temperature control.

[0045] In this embodiment, in the dynamic model building module, a dynamic model of a fuel cell PEMFC thermal management system is built, including: Fuel cell stack; A cooling branch, the cooling branch comprising an input port and an output port at both ends, and a water pump, a water tank, a three-way valve, a radiator and a fan connected in sequence between the input port and the output port, the input port being connected to the coolant outlet of the fuel cell stack, the output port being connected to the coolant inlet of the fuel cell stack, the three-way valve inlet being connected to the water tank, the first outlet being connected to the coolant circuit, and the second outlet being connected to the heating branch; A heating branch, wherein both ends of the heating branch are respectively connected between the outlet of the three-way valve and the pipeline after the radiator on the coolant circuit, and the heating branch comprises a water pump, a water tank, a three-way valve and a heater; A control module, the control module is connected to the water pump, the radiator and the fan respectively, and the control module is used to control the rotation speed of the radiator and the fan to achieve control of the temperature of the coolant of the fuel cell stack; the control strategy of the control module is: Start-up phase: When the fuel cell stack is in the startup phase, the first outlet of the three-way valve is controlled to be closed and the second outlet is opened, and the heater is turned on to preheat the coolant through the heating branch so that the fuel cell stack reaches a suitable operating temperature as soon as possible. Stable operation phase: When the fuel cell stack is in the stable operation phase, the second outlet of the three-way valve is controlled to be closed and the first outlet is opened, the heater is turned off, and excess heat is transferred to the environment through the heat dissipation branch to control the appropriate operating temperature of the fuel cell stack and maintain stable operation.

[0046] The above shows and describes the basic principles and main features of the present invention and the advantages of the present invention. It is obvious to those skilled in the art that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic features of the present invention. Therefore, no matter from which point of view, the embodiments should be regarded as exemplary and non-restrictive. The scope of the present invention is defined by the attached claims rather than the above description, and it is intended that all changes falling within the meaning and scope of the equivalent elements of the claims are included in the present invention. Any figure mark in the claims should not be regarded as limiting the claims involved.

[0047] In addition, it should be understood that although this specification is described in accordance with the implementation modes, not every implementation mode contains only one independent technical solution. This description of the specification is only for the sake of clarity. Those skilled in the art should regard the specification as a whole. The technical solutions in each embodiment can also be appropriately combined to form other implementation modes that can be understood by those skilled in the art. The above content is only to illustrate the technical idea of ​​the present invention, and cannot be used to limit the protection scope of the present invention. Any changes made on the basis of the technical solution according to the technical idea proposed by the present invention shall fall within the protection scope of the claims of the present invention.

Claims

1. A fuel cell temperature control method based on decoupling control combined with fuzzy PID, characterized in that: The following steps are involved: S1, according to the physical characteristics of the fuel cell stack, water pump, water tank, heater, radiator and fan in the thermal management system of the proton exchange membrane fuel cell, build a dynamic model of the fuel cell PEMFC thermal management system based on the MATLAB / Simulink simulation platform; S2, according to the dynamic model of the fuel cell PEMFC thermal management system established in step S1, the system transfer function matrix of the fuel cell thermal management system at different equilibrium points is obtained through system identification, S3, using a PID controller to control the PEMFC temperature, and designing a feedforward decoupling controller according to the system transfer function matrix of the PEMFC thermal management system at different equilibrium points obtained in S2; S4, using fuzzy control to optimize the feedforward decoupling controller in S3 to obtain a fuzzy PID temperature controller; S5, the fuzzy PID temperature controller obtained in S4 is optimized by using a particle swarm algorithm, the decision variables are selected as the fuzzy control rules and membership functions on the water pump side and the fan side, and the optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller to achieve temperature control of the fuel cell.

2. The fuel cell temperature control method based on decoupling control combined with fuzzy PID according to claim 1, characterized in that: In the step S1, a dynamic model of a fuel cell PEMFC thermal management system is constructed, including: Fuel cell stack; A cooling branch, the cooling branch comprising an input port and an output port at both ends, and a water pump, a water tank, a three-way valve, a radiator and a fan connected in sequence between the input port and the output port, the input port being connected to the coolant outlet of the fuel cell stack, the output port being connected to the coolant inlet of the fuel cell stack, the three-way valve inlet being connected to the water tank, the first outlet being connected to the coolant circuit, and the second outlet being connected to the heating branch; A heating branch, wherein both ends of the heating branch are respectively connected between the outlet of the three-way valve and the pipeline after the radiator on the coolant circuit, and the heating branch comprises a water pump, a water tank, a three-way valve and a heater; A control module, the control module is connected to the water pump, the radiator and the fan respectively, and the control module is used to control the rotation speed of the radiator and the fan to achieve control of the temperature of the coolant of the fuel cell stack; the control strategy of the control module is: Start-up phase: When the fuel cell stack is in the startup phase, the first outlet of the three-way valve is controlled to be closed and the second outlet is opened, and the heater is turned on to preheat the coolant through the heating branch so that the fuel cell stack reaches a suitable operating temperature as soon as possible. Stable operation phase: When the fuel cell stack is in the stable operation phase, the second outlet of the three-way valve is controlled to be closed and the first outlet is opened, the heater is turned off, and excess heat is transferred to the environment through the heat dissipation branch to control the appropriate operating temperature of the fuel cell stack and maintain stable operation.

3. The fuel cell temperature control method based on decoupling control combined with fuzzy PID according to claim 2, characterized in that: In step S2, according to the dynamic model of the fuel cell PEMFC thermal management system established in step S1, the system transfer function matrix of the fuel cell thermal management system at different equilibrium points is obtained through system identification, including: The input of the thermal management system is the speed of the water pump and the speed of the fan, and the output is the coolant inlet and outlet temperature difference and the cooling water inlet temperature. It is a dual-input and dual-output coupled system. Through system identification, a 2×2 system transfer function matrix is ​​obtained, which is expressed as: (1) Where: is the cooling water flow rate, is the air flow rate, is the actual temperature difference of the cooling water at the inlet and outlet of the stack, is the cooling water temperature at the stack inlet; the system identification adopts step response; in order to obtain the system transfer function matrix, firstly, five equilibrium working points are selected within the input current working range, and then step disturbances are applied to the input of the PEMFC thermal management system respectively to obtain the step response of the corresponding output, and finally the transfer function matrix at different equilibrium points is obtained through system identification; Based on the coolant inlet and outlet temperature difference and the step response of the coolant inlet temperature to the coolant flow rate and air flow rate, five operating current points were selected as the equilibrium operating points, and the transfer function matrix of the PEMFC thermal management system was identified; the transfer function of the equilibrium operating point can be identified through MATLAB's system identification toolbox.

4. The fuel cell temperature control method based on decoupling control combined with fuzzy PID according to claim 3 is characterized in that: In step S3, a PID controller is used to control the PEMFC temperature, and a feedforward decoupling controller is designed according to the system transfer function matrix of the PEMFC thermal management system at different equilibrium points obtained in step S2, including: Firstly, the speed of the water pump and the fan are adjusted respectively by two independent PID controllers to control the temperature difference between the inlet and outlet of the cooling water of the fuel cell and the inlet temperature of the cooling water. Then, the feedforward compensation decoupling method is adopted, and the system transfer function is used to obtain the feedforward decoupling coefficients N21 and N12. By introducing the feedforward compensation, the coupling relationship in the thermal management system is eliminated, so that the dual-input dual-output thermal management system becomes two independent single-input single-output systems. The speed of the water pump affects the inlet and outlet temperature difference of the coolant, and the speed of the fan affects the inlet temperature of the cooling water, thereby realizing the decoupling control of the PRMFC thermal management system. The PID controller can generate the corresponding control quantity according to the error. The PID control algorithm is expressed as: (2) The error e(t)=TS(t)-T(t) between the expected temperature value TS(t) and the actual temperature value T(t) is selected as the input of the PID temperature controller, and the output control action u(t) is obtained through proportional, integral and differential operations; the temperature value on the water pump side is the temperature difference between the inlet and outlet cooling water of the stack, the expected temperature is 10K, and the control action of the PID output is the coolant flow rate; the temperature value on the fan side is the inlet cooling water temperature of the stack, the expected temperature is 333K, and the control action of the PID output is the air flow rate; The principle and method of the feedforward decoupling are as follows: adopting the system identification method, obtaining the system transfer function, calculating and obtaining the feedforward decoupling coefficients N21 and N12 according to the invariance principle, and eliminating the coupling relationship in the thermal management system by introducing the feedforward compensation amount, thereby realizing the decoupling control between the cooling water flow and the air flow; The parameters in feedforward decoupling control are defined as: Corresponding cooling water flow rate, Corresponding air flow rate, and Represent the feedforward compensation transfer function and transfer function respectively. and Respectively represent the cooling water flow rate and the temperature difference of the fuel cell cooling water inlet and outlet and fuel cell cooling water inlet temperature The impact of and Respectively represent the cooling water flow rate and the temperature difference of the fuel cell cooling water inlet and outlet and fuel cell cooling water inlet temperature In order to eliminate the coupling relationship through compensation, a feedforward decoupling controller is designed according to the invariance principle: (3) (4) The transfer function of the feedforward compensator is obtained as: (5) (6) In the above formula , , and All come from the identified transfer function matrix.

5. The fuel cell temperature control method based on decoupling control combined with fuzzy PID according to claim 4 is characterized in that: In step S4, the feedforward decoupling controller in step S3 is optimized by fuzzy control to obtain a fuzzy PID temperature controller, including: Optimize PID through fuzzy control to realize the function of self-tuning control parameters. Select the fuel cell temperature error e(t) and its error change rate ec(t) as the input of the fuzzy PID temperature controller, and take the parameter adjustment ΔKp, ΔKp, ΔKd of the PID controller as the output, where ΔKp, ΔKp, ΔKd are the changes of the three parameters Kp, Ki, Kd corresponding to the proportional integral P, integral I and differential D respectively; divide the input and output of the PID temperature controller into 7 fuzzy sets, and use the triangular membership function for the membership function to fuzzify the variables and defuzzify the fuzzy variables. The membership function is expressed as: (7) Among them: a, c are the values ​​of the triangular function on the horizontal axis, and b is the vertex of the triangular function.

6. The fuel cell temperature control method based on decoupling control combined with fuzzy PID according to claim 5, characterized in that: In step S5, the PSO algorithm is applied to optimize the fuzzy control rules and membership functions in the fuzzy PID on the water pump side and the fan side respectively; in the PSO algorithm, the speed and position of each particle are calculated based on the difference between the current position and the historical optimal position; in the D-dimensional search space, the speed and position update formula of each particle is as follows: (8) (9) Where: and are the velocity and position of the particle, and is the particle’s current position information and the particle’s historical optimal position information, , s is the inertia factor, and are two random numbers generated independently in [0,1]. and is the acceleration coefficient; the first part of formula (8) is called the memory term, which represents the influence of the last speed and direction; the second part is called the self-cognition term, which is a vector pointing from the current point to the best point of the particle itself, indicating that the action of the particle comes from its own experience; the third part is called the group cognition term, which is a vector pointing from the current point to the best point of the population, reflecting the collaboration and knowledge sharing among particles; each particle learns from its own best experience and the best experience of the population, and continuously updates its position through formula (9), thereby approaching the global optimal solution.

7. The fuel cell temperature control method based on decoupling control combined with fuzzy PID according to claim 6, characterized in that: In step S5, the integrated absolute error of the stack temperature is selected as the fitness function, and the smaller the IAE, the better the temperature control effect: (10) Specifically, select the temperature difference of the cooling water at the inlet and outlet of the stack For preset temperature value The IAE is IAE1, and the stack inlet cooling water temperature is selected For preset temperature value The IAE is IAE2, and the fitness function of the PSO algorithm is constructed as follows: (11) The PSO algorithm will optimize the fuzzy PID in the direction of continuously reducing the fitness function, thereby achieving better control effects.

8. The fuel cell temperature control method based on decoupling control combined with fuzzy PID according to claim 7, characterized in that: In the step S5, the improved particle swarm algorithm is used to optimize the fuzzy control rules and membership functions of the water pump side and the fan side in the fuzzy PID temperature controller respectively, and the optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller; The input and output variables are divided into 7 fuzzy sets, and a triangular membership function is used to optimize the vertex position of each triangular membership function. There are 5 input and output variables in total, so the membership function has 5×7=35 decision variables to be optimized; fuzzy control uses an if-then structure, so there are 7 fuzzy sets for each of the two inputs, and every two input fuzzy sets correspond to an output fuzzy set. There are 3 outputs in total, so the fuzzy rules are decision variables need to be optimized; and because the water pump side and the fan side use fuzzy PID temperature controllers, they need to be optimized using the improved particle swarm algorithm. There are decision variables that need to be optimized.

9. A fuel cell temperature control system based on decoupling control combined with fuzzy PID, characterized in that: include: Dynamic model building module, based on the MATLAB / Simulink simulation platform, builds a dynamic model of the fuel cell PEMFC thermal management system according to the physical characteristics of the stack, water pump, water tank, heater, radiator and fan in the proton exchange membrane fuel cell thermal management system; The system transfer function matrix identification module is based on the dynamic model of the fuel cell PEMFC thermal management system established by the dynamic model building module. Through system identification, the system transfer function matrix of the fuel cell thermal management system at different equilibrium points is obtained. The feedforward decoupling controller design module uses a PID controller to control the PEMFC temperature, and designs a feedforward decoupling controller based on the system transfer function matrix of the PEMFC thermal management system at different equilibrium points obtained in the system transfer function matrix identification module; A fuzzy PID temperature controller obtaining module uses the fuzzy control to optimize the feedforward decoupling controller in the feedforward decoupling controller design module to obtain a fuzzy PID temperature controller; The fuel cell temperature control module uses a particle swarm algorithm to optimize the fuzzy PID temperature controller obtained in the fuzzy PID temperature controller acquisition module. The decision variables are selected as the fuzzy control rules and membership functions on the water pump side and the fan side. The optimized fuzzy control rules and membership functions are assigned to the fuzzy PID temperature controller to achieve fuel cell temperature control.

10. The fuel cell temperature control system based on decoupling control combined with fuzzy PID according to claim 9, characterized in that: In the dynamic model building module, a dynamic model of a fuel cell PEMFC thermal management system is built, including: Fuel cell stack; A cooling branch, the cooling branch comprising an input port and an output port at both ends, and a water pump, a water tank, a three-way valve, a radiator and a fan connected in sequence between the input port and the output port, the input port being connected to the coolant outlet of the fuel cell stack, the output port being connected to the coolant inlet of the fuel cell stack, the three-way valve inlet being connected to the water tank, the first outlet being connected to the coolant circuit, and the second outlet being connected to the heating branch; A heating branch, wherein both ends of the heating branch are respectively connected between the outlet of the three-way valve and the pipeline after the radiator on the coolant circuit, and the heating branch comprises a water pump, a water tank, a three-way valve and a heater; A control module, the control module is connected to the water pump, the radiator and the fan respectively, and the control module is used to control the rotation speed of the radiator and the fan to achieve control of the temperature of the coolant of the fuel cell stack; the control strategy of the control module is: Start-up phase: When the fuel cell stack is in the startup phase, the first outlet of the three-way valve is controlled to be closed and the second outlet is opened, and the heater is turned on to preheat the coolant through the heating branch so that the fuel cell stack reaches a suitable operating temperature as soon as possible. Stable operation phase: When the fuel cell stack is in the stable operation phase, the second outlet of the three-way valve is controlled to be closed and the first outlet is opened, the heater is turned off, and excess heat is transferred to the environment through the heat dissipation branch to control the appropriate operating temperature of the fuel cell stack and maintain stable operation.

Images