Temperature control method of air-cooled PEMFC and related device

Abstract

The invention belongs to the field of fuel cell thermal management, and discloses a temperature control method of an air-cooled PEMFC and a related device, and the method comprises the steps: constructing an air-cooled PEMFC thermal management system dynamic model which comprises a cell stack model and a thermal analysis module; applying a preset step response to the cell stack model to obtain cell stack model information; constructing a first-order linear active disturbance rejection controller (ADRC); an anti-interference normal form of the first-order linear active-disturbance-rejection controller ADRC is obtained through cell stack model information correction, and preset key parameters of a linear expansion state observer in the first-order linear active-disturbance-rejection controller ADRC are obtained through particle swarm optimization; generating a temperature control quantity at the next moment based on a first-order linear active disturbance rejection controller (ADRC); inputting the temperature control quantity at the next moment into a thermal analysis module, and controlling the temperature of the air-cooled PEMFC; according to the invention, accurate control of the temperature of the air-cooled PEMFC is realized, the control effect and the anti-interference capability are ensured, and the method is easy to implement.

Description

Technical Field

[0001] This invention belongs to the field of fuel cell thermal management technology, and specifically relates to a temperature control method and related device for an air-cooled PEMFC. Background Technology

[0002] Proton exchange membrane fuel cells (PEMFCs), as efficient and clean energy conversion devices, have broad application prospects in many fields such as new energy vehicles, distributed power generation, and portable power supplies. During PEMFC operation, operating temperature is a crucial parameter, directly affecting the gas transport efficiency within the cell, the rate of chemical reactions, and the hydrothermal balance, thus significantly influencing the stack's output performance and lifespan. Therefore, to ensure stable and efficient operation of PEMFCs, researching temperature control strategies for their thermal management systems is particularly necessary. Especially in air-cooled PEMFCs, the combined design of the air supply and cooling channels, while improving system compactness, also presents greater challenges for precise temperature control.

[0003] In the field of temperature control for air-cooled PEMFCs, the most widely used technology is PID control. PID control, or proportional-integral-derivative control, is a classic control algorithm that achieves control by adjusting three parameters: proportional, integral, and derivative. However, due to the significant nonlinear characteristics of air-cooled PEMFCs, traditional PID control often suffers from problems such as limited adjustment accuracy, slow response speed, and obvious overshoot when applied. This not only affects the output performance of the PEMFC but may also shorten its service life.

[0004] To address the shortcomings of traditional PID control, some researchers have begun exploring advanced model-based control strategies, such as Model Predictive Control (MPC), Linear Quadratic Regulator (LQR), and Adaptive Control (AC). These methods have achieved good temperature control results in laboratory environments, improving the accuracy and response speed of temperature control to some extent. MPC optimizes the current control input by predicting the system state over a future period; LQR designs the optimal controller by minimizing a quadratic performance index; and AC can adjust control parameters according to real-time changes in the system to adapt to different operating conditions.

[0005] Although model-based advanced control strategies have performed well in the laboratory, they still suffer from poor control performance and high computational costs in practical engineering applications, hindering their application and maintenance. Specifically, in practical engineering applications, existing model-based advanced control strategies are highly dependent on the accuracy of the model; once there is a deviation between the model and the actual system, the control effect will be significantly reduced. Secondly, they perform poorly when dealing with changes in internal parameters of PEMFC systems and external environmental disturbances, and are prone to control failure or performance degradation. In addition, the structure of these methods is usually relatively complex, the algorithm has a large computational load, and the requirements for hardware resources are high, which is not conducive to their widespread application and maintenance in practical engineering. Summary of the Invention

[0006] To address the technical problems existing in the prior art, this invention provides a temperature control method and related device for air-cooled PEMFCs, in order to solve the technical problems of poor control effect, large computational load, and unfavorable application and maintenance in practical engineering of existing model-based advanced control strategies.

[0007] To achieve the above objectives, the technical solution adopted by the present invention is as follows: This invention provides a temperature control method for an air-cooled PEMFC, comprising: A dynamic model of the air-cooled PEMFC thermal management system is constructed; the dynamic model of the air-cooled PEMFC thermal management system includes a battery stack model and a thermal analysis module. A preset step response is applied to the battery stack model in the dynamic model of the air-cooled PEMFC thermal management system to obtain battery stack model information. Based on the battery stack model information, a first-order linear active disturbance rejection controller (ADRC) is constructed. The disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) is obtained by modifying the battery stack model information, and the preset key parameters of the linear extended state observer in the first-order linear active disturbance rejection controller (ADRC) are optimized by the particle swarm optimization algorithm. Obtain the current actual temperature and the temperature control value of the air-cooled PEMFC at the previous moment; Based on the current actual temperature of the air-cooled PEMFC and the temperature control quantity of the previous time, the temperature control quantity of the next time is generated by combining the first-order linear active disturbance rejection controller (ADRC). The temperature control value for the next moment is input into the thermal analysis module in the dynamic model of the air-cooled PEMFC thermal management system to control the temperature of the air-cooled PEMFC.

[0008] Further information regarding the battery stack model is as follows:

[0009] in, For transfer functions; For Laplace variables; All of these are undetermined parameters in the transfer function.

[0010] Furthermore, the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) is as follows:

[0011] in, This is the derivative of the battery stack temperature; All of these are undetermined parameters in the transfer function; The temperature of the battery stack; This refers to the fan's duty cycle. The total disturbance includes both internal and external disturbances; The state-space equations corresponding to the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) are as follows:

[0012] in, State variables The derivative; State variables The derivative; and All are state variables; The total disturbance includes both internal and external disturbances. The differential.

[0013] Furthermore, the first-order linear active disturbance rejection controller (ADRC) includes a linear state error feedback controller and a linear extended state observer; The linearly extended state observer is as follows:

[0014] in, For estimating parameters The derivative; For estimating parameters The derivative; and These are all adjustable parameters of the observer; and All are estimated parameters; This refers to the fan's duty cycle. The temperature of the battery stack; To estimate the temperature; By substituting the linear extended state observer into the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC), the air-cooled PEMFC thermal management system can be transformed into a single-integral control, as follows:

[0015]

[0016] in; This is the initial feedback control quantity; All of these are undetermined parameters in the transfer function; The temperature of the battery stack; This is the derivative of the battery stack temperature; This refers to the total disturbance, which includes both internal and external disturbances.

[0017] Furthermore, the preset key parameters of the linearly extended state observer include the observer's adjustable parameters. Adjustable parameters of the observer .

[0018] Furthermore, during the optimization of the preset key parameters of the linear extended state observer in the first-order linear active disturbance rejection controller (ADRC) using the particle swarm optimization algorithm, the fitness function of the particle swarm optimization algorithm is as follows:

[0019]

[0020] in, This is the fitness function for the particle swarm optimization algorithm; This is the integral of the absolute error; This is the error.

[0021] The present invention also provides a temperature control system for an air-cooled PEMFC, comprising: The model building module is used to build a dynamic model of the air-cooled PEMFC thermal management system; the dynamic model of the air-cooled PEMFC thermal management system includes a battery stack model and a thermal analysis module. The model information acquisition module is used to apply a preset step response to the battery stack model in the dynamic model of the air-cooled PEMFC thermal management system to obtain battery stack model information. The controller construction module is used to construct a first-order linear active disturbance rejection controller (ADRC) based on the battery stack model information. The disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) is obtained by correcting the battery stack model information, and the preset key parameters of the linear extended state observer in the first-order linear active disturbance rejection controller (ADRC) are obtained by optimizing the particle swarm algorithm. The data acquisition module is used to acquire the current actual temperature of the air-cooled PEMFC and the temperature control value of the previous moment. The control quantity generation module is used to generate the temperature control quantity for the next moment based on the actual temperature of the air-cooled PEMFC at the current moment and the temperature control quantity at the previous moment, combined with the first-order linear active disturbance rejection controller (ADRC). The temperature control module is used to input the temperature control value for the next moment into the thermal analysis module in the dynamic model of the air-cooled PEMFC thermal management system to control the temperature of the air-cooled PEMFC.

[0022] The present invention also provides an electronic device, comprising: A processor is used to execute computer programs; A computer-readable storage medium storing a computer program, which, when executed by the processor, performs the temperature control method of the air-cooled PEMFC.

[0023] The present invention also provides a computer-readable storage medium storing a computer program, characterized in that the computer program, when executed by a processor, implements the temperature control method of the air-cooled PEMFC.

[0024] The present invention also provides a computer program product, the computer program product comprising a computer program, which, when executed by a processor, implements the temperature control method of the air-cooled PEMFC.

[0025] Compared with the prior art, the beneficial effects of the present invention are as follows: The temperature control method for air-cooled PEMFCs provided by this invention achieves precise temperature control of the air-cooled PEMFC by introducing battery stack model information and particle swarm optimization (PSO) algorithm parameter optimization strategies on the basis of a first-order linear active disturbance rejection controller (ADRC). This ensures control effectiveness, disturbance rejection capability, and ease of implementation. Specifically, a dynamic model of the air-cooled PEMFC thermal management system, including a battery stack model and a thermal analysis module, is constructed. A preset step response is applied to the battery stack model to obtain its information, which is then used to construct the first-order linear ADRC. The disturbance rejection paradigm of the ADRC is corrected using battery stack model information, and key parameters are optimized by the PSO algorithm, effectively overcoming the shortcomings of traditional control methods, such as limited adjustment accuracy, slow response speed, and significant overshoot. Specifically, the disturbance rejection capability of the first-order linear ADRC... The paradigm is obtained by modifying the battery stack model information. Introducing the battery stack model information into the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) can reduce the total disturbance term, lower the convergence speed requirement of the linear extended state observer, thereby reducing the impact of noise and significantly improving the control effect. Secondly, the particle swarm optimization algorithm is used to optimize the preset key parameters of the linear extended state observer, ensuring the accuracy of the preset key parameter values ​​in the linear extended state observer, thereby improving the control effect. In addition, the method of this invention can reduce the over-reliance on model accuracy, performs well in dealing with changes in internal system parameters and external environmental disturbances, is less prone to control failure or performance degradation, and has a relatively simple structure, low computational load, and low hardware resource requirements, which greatly improves the control effect and is more conducive to widespread application and maintenance in practical engineering, ensuring the stable and efficient operation of the air-cooled PEMFC.

[0026] The temperature control system, electronic device, computer-readable storage medium, and computer program product of the air-cooled PEMFC provided by the present invention possess all the advantages of the temperature control method of the air-cooled PEMFC described above. Attached Figure Description

[0027] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0028] Figure 1 A flowchart of the temperature control method for an air-cooled PEMFC provided in Example 1; Figure 2 This is a schematic diagram of a typical Active Disturbance Rejection Controller (ADRC). Figure 3 This is a diagram of the current disturbance applied in Example 1; Figure 4 A comparison chart of the battery stack temperature control effects of traditional PID control and typical active disturbance rejection controller (ADRC) control. Figure 5 This is a duty cycle perturbation diagram for the fan in Example 1; Figure 6 The diagram shows the identification results and actual results of the temperature response curve of the air-cooled PEMFC in Example 1. Figure 7 A comparison of the battery stack temperature control performance between a typical Active Disturbance Rejection Controller (ADRC) control method and an ADRC control method incorporating model information. Figure 8 This is an iterative curve diagram of the particle swarm algorithm in Example 1; Figure 9 A comparison diagram of the battery stack temperature control effects of the Active Disturbance Rejection Controller (ADRC) control method that incorporates model information and the temperature control method of Example 1. Figure 10 The adjustable parameters of the observer in Example 1 Curves showing changes during different control processes; Figure 11 The adjustable parameters of the observer in Example 1 Curves showing changes during different control processes; Figure 12 This is a schematic diagram of the structure of the first-order linear active disturbance rejection controller (ADRC) in Example 1; Figure 13 This is a structural block diagram of the temperature control system for the air-cooled PEMFC provided in Example 2; Figure 14 This is a structural block diagram of the electronic device provided in Example 3. Detailed Implementation

[0029] To make the technical problems, technical solutions, and beneficial effects solved by this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of this application without creative effort are within the scope of protection of this application.

[0030] This invention provides a temperature control method for an air-cooled PEMFC, comprising the following steps: Step 100: Construct a dynamic model of the air-cooled PEMFC thermal management system; the dynamic model of the air-cooled PEMFC thermal management system includes a battery stack model and a thermal analysis module.

[0031] Step 200: Apply a preset step response to the battery stack model in the dynamic model of the air-cooled PEMFC thermal management system to obtain battery stack model information.

[0032] Step 300: Based on the battery stack model information, construct a first-order linear active disturbance rejection controller (ADRC); wherein, the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) is obtained by correcting the battery stack model information, and the preset key parameters of the linear extended state observer in the first-order linear active disturbance rejection controller (ADRC) are obtained by optimizing the particle swarm algorithm.

[0033] Step 400: Obtain the current actual temperature of the air-cooled PEMFC and the temperature control value of the previous moment.

[0034] Step 500: Based on the current actual temperature of the air-cooled PEMFC and the temperature control quantity of the previous moment, and combined with the first-order linear active disturbance rejection controller (ADRC), generate the temperature control quantity for the next moment.

[0035] Step 600: Input the temperature control value for the next moment into the thermal analysis module in the dynamic model of the air-cooled PEMFC thermal management system to control the temperature of the air-cooled PEMFC.

[0036] In the above implementation, the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) is obtained by modifying the battery stack model information. Embedding the battery stack model information into the ADRC's disturbance rejection paradigm effectively reduces the total disturbance term, lowers the requirements for the convergence speed of the linear extended state observer, and thus reduces noise impact, significantly improving control performance. Compared to traditional PID control, it shows significant optimization in overshoot, settling time, and IAE (Inter-Aspect-Effect) performance. Secondly, a particle swarm optimization algorithm is used to optimize the preset key parameters of the linear extended state observer, such as the observer's adjustable parameters. Adjustable parameters of the observer This approach effectively reduces the complexity of the air-cooled PEMFC thermal management system after incorporating ADRC, facilitating accurate analysis of the relationship between parameters and control performance. Through iterative evolution of the particle swarm optimization algorithm, it further enhances temperature control performance, achieving a further reduction in IAE based on ADRC combined with battery stack model information. Moreover, the preset key parameters of the linear expansion state observer can be automatically adjusted during the control process to achieve better control, providing an efficient and practical solution for the temperature control of air-cooled PEMFCs.

[0037] The following specific embodiments further explain the temperature control method of the air-cooled PEMFC provided by the present invention: Example 1 As attached Figure 1As shown, this embodiment 1 provides a temperature control method for an air-cooled PEMFC, including the following steps: Step 1: Construct a dynamic model of the air-cooled PEMFC thermal management system. This dynamic model includes a battery stack model and a thermal analysis module. Specifically, based on the physical characteristics of the air-cooled PEMFC thermal management system, a dynamic model is built using the Matlab / Simulink simulation platform to obtain the dynamic model of the air-cooled PEMFC thermal management system.

[0038] The battery stack model is derived using semi-empirical equations to reflect the relationship between the operating parameters of the air-cooled PEMFC and the output voltage of the battery stack, in order to calculate the output power of the battery stack. The battery stack model using semi-empirical equations has the advantages of fast calculation speed and high accuracy, and is used for simulation studies at the PEMFC system level. Specifically, the battery stack model is as follows:

[0039]

[0040]

[0041]

[0042]

[0043]

[0044]

[0045]

[0046] in, This refers to the output voltage of the battery stack. Nernst voltage; For activation loss; For ohm loss; For concentration loss; All are coefficients, calibrated through experimental data, among which... The activation loss coefficient is... This is the no-load current. This is the concentration loss coefficient; For external circuit resistance; This refers to the water content of the exchange membrane. The limiting current density; The reaction entropy; This refers to the number of electrons transferred in the reaction. It is Faraday's constant; Battery temperature; Standard temperature; It is the gas constant; This refers to the partial pressure of hydrogen gas. The partial pressure of oxygen; It is the partial pressure of water vapor; Oxygen concentration; This is the total current; This is the operating current; Total internal resistance; The internal resistance is ohmic; Resistivity; For the thickness of the exchange membrane; The area of ​​the activated reaction; denoted as current density.

[0047] The thermal analysis module analyzes the heat generation, transfer, and dissipation of various components in the PEMFC system and establishes an energy conservation model to reflect the dynamic temperature changes of the battery stack, providing a foundation for subsequent temperature control. Specifically, the thermal analysis module uses the energy conservation equation to calculate the temperature change rate of the PEMFC stack. Its main input and output energy forms are as follows:

[0048]

[0049]

[0050]

[0051]

[0052] in, The heat capacity of the air-cooled PEMFC; For time; This represents the total input energy of the air-cooled PEMFC. This represents the total output electrical energy of the air-cooled PEMFC. To remove heat from the cooling air; Heat is lost through radiation and natural convection; This represents the amount of hydrogen consumed. The enthalpy of hydrogen combustion; The number of individual cells; This refers to the voltage of the battery stack. The surface heat transfer coefficient; This represents the total area of ​​the cathode flow channel; The ambient temperature; This is the equivalent thermal resistance.

[0053] Step 2: Apply a preset step response to the battery stack model in the dynamic model of the air-cooled PEMFC thermal management system to obtain the battery stack model information. Specifically, at the preset stable operating point of the air-cooled PEMFC, apply a fan duty cycle perturbation to the battery stack model to obtain its first-order transfer function form, thus obtaining the battery stack model information.

[0054] The battery stack model information is as follows:

[0055] in, For transfer functions; For Laplace variables; All of these are undetermined parameters in the transfer function.

[0056] Step 3: Based on the battery stack model information, construct a first-order linear active disturbance rejection controller (ADRC); wherein, the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) is obtained by correcting the battery stack model information, and the preset key parameters of the linear extended state observer in the first-order linear active disturbance rejection controller (ADRC) are obtained by optimizing the particle swarm optimization algorithm.

[0057] It should be noted that typical Active Disturbance Rejection Controllers (ADRCs) are model-free controls; regardless of the type of controlled object, they can ultimately be simplified to, for example... The disturbance rejection paradigm; however, in a typical active disturbance rejection controller (ADRC), its linearly extended state observer needs to have a large bandwidth to estimate the total disturbance in a timely manner. This would increase the system's sensitivity to noise; in this embodiment 1, battery stack model information is introduced into the typical active disturbance rejection controller (ADRC) paradigm to reduce the total disturbance. By relaxing the bandwidth requirements of the linear extended state observer, the impact of noise can be reduced, thereby improving the control effect to some extent.

[0058] Specifically, the first-order linear active disturbance rejection controller (ADRC) includes a linear state error feedback controller and a linear extended state observer, as shown in the attached diagram. Figure 12 As shown; by using the battery stack model information, the typical Active Distance Rejection Controller (ADRC) is modified to obtain the disturbance rejection paradigm of the first-order linear ADRC; the disturbance rejection paradigm of the first-order linear ADRC is as follows:

[0059] in, This is the derivative of the battery stack temperature; The temperature of the battery stack; This refers to the fan's duty cycle. This refers to the total disturbance, which includes both internal and external disturbances.

[0060] At this point, the state-space equation corresponding to the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) is as follows:

[0061] in, State variables The derivative; State variables The derivative; and All are state variables; The total disturbance includes both internal and external disturbances. The differential.

[0062] A linearly extended state observer is as follows:

[0063] in, For estimating parameters The derivative; For estimating parameters The derivative; and These are all adjustable parameters of the observer; and All are estimated parameters; This refers to the fan's duty cycle. The temperature of the battery stack; To estimate the temperature.

[0064] By substituting the linear extended state observer into the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC), the air-cooled PEMFC thermal management system can be transformed into a single-integral control, as follows:

[0065]

[0066] in; This is the initial feedback control quantity; The temperature of the battery stack; This is the derivative of the battery stack temperature; This refers to the total disturbance, which includes both internal and external disturbances.

[0067] It should be noted that in the first-order linear active disturbance rejection controller (ADRC), the adjustable parameters of the observer in the linear extended state observer are... Adjustable parameters of the observer This can affect the final performance of the first-order linear active disturbance rejection controller (ADRC); therefore, in this embodiment 1, the preset key parameters of the linear extended state observer in the first-order linear ADRC, such as the adjustable parameters of the observer, are... Adjustable parameters of the observer It was obtained after optimization using the particle swarm optimization algorithm.

[0068] Since the air-cooled PEMFC thermal management system incorporates a first-order linear active disturbance rejection controller (ADRC), it becomes extremely complex, making it difficult to theoretically analyze the adjustable parameters of the observer. Adjustable parameters of the observer The precise relationship between the value of the parameter and the control effect; in this embodiment 1, the particle swarm optimization algorithm is used to adjust the adjustable parameters of the observer. Adjustable parameters of the observer Optimization is performed to continuously improve temperature control through iterative evolution of the particle swarm optimization algorithm.

[0069] In this embodiment 1, the particle swarm optimization algorithm is used to adjust the adjustable parameters of the observer. Adjustable parameters of the observer During the optimization process, the optimization objective is the temperature control effect; at this time, the fitness function of the particle swarm optimization algorithm is as follows:

[0070]

[0071] in, This is the fitness function for the particle swarm optimization algorithm; It is the integral of absolute error, an indicator used to measure the effectiveness of control. As shown in the error, a smaller IAE corresponds to a better control effect.

[0072] Step 4: Obtain the current actual temperature of the air-cooled PEMFC and the temperature control value of the previous moment.

[0073] Step 5: Based on the actual temperature of the air-cooled PEMFC at the current moment and the temperature control quantity at the previous moment, and combined with the first-order linear active disturbance rejection controller (ADRC), generate the temperature control quantity for the next moment.

[0074] Specifically, the process is as follows: Step 51: Input the current actual temperature of the air-cooled PEMFC and the temperature control value of the previous moment into the linear expansion state observer to obtain the estimated temperature and estimated total disturbance of the next moment.

[0075] Step 52: Compare the target temperature of the air-cooled PEMFC with the estimated temperature at the next moment to obtain the estimated temperature error.

[0076] Step 53: Input the estimated temperature error into the linear state error feedback controller to obtain the preliminary control quantity for the next moment.

[0077] Step 53: Use the estimated total disturbance at the next time moment to compensate for the initial control quantity at the next time moment, and obtain the temperature control quantity at the next time moment.

[0078] Step 6: Input the temperature control value for the next moment into the thermal analysis module of the dynamic model of the air-cooled PEMFC thermal management system to control the temperature of the air-cooled PEMFC.

[0079] Specifically, the temperature control value for the next moment is input into the thermal analysis module to change the air flow rate, thereby changing the surface heat transfer coefficient of the cathode channel and controlling the temperature of the air-cooled PEMFC battery stack.

[0080] It should be noted that the temperature control strategy of air-cooled PEMFCs is to adjust the fan duty cycle signal to change the airflow velocity, thereby altering the surface heat transfer coefficient of the cathode channel and achieving precise control of the PEMFC stack temperature. Based on the general structure and operating conditions of air-cooled PEMFCs, it can be determined that the airflow is within the laminar flow range. Therefore, the relationship between the airflow velocity and the surface heat transfer coefficient of the cathode channel is determined using the Zid-Tate equation, as follows:

[0081] in, The Nucher number for the cathode flow channel; It is the Reynolds number; It is a Prandtl number; For feature size; The dynamic viscosity of air; The dynamic viscosity of the wall surface; The diameter is the pipe diameter.

[0082] Method performance verification: The following example uses four different control methods to test the temperature control process of an air-cooled PEMFC, in order to verify the effectiveness of the temperature control method of the air-cooled PEMFC described in Example 1.

[0083] The first control method is the traditional PID control method (PID for short), the second control method is the typical Active Disturbance Rejection Controller (ADRC) control method (original ADRC for short), the third control method is the Active Disturbance Rejection Controller (ADRC) combined with model information (ADRC combined with model information for short), and the fourth control method is the temperature control method of the air-cooled PEMFC provided in Example 1 (PSO optimized ADRC combined with model information for short); detailed explanations are as follows: (1) First control method: In traditional PID control methods, a PID controller is used to control the temperature of an air-cooled PEMFC. The PID controller is the most widely used controller in practical engineering, characterized by its simple structure, strong robustness, and ease of implementation. The PID controller is a model-free controller that generates a corresponding control action based on the error. Specifically, based on the system error, the control action is calculated to adjust the fan's duty cycle. The process of calculating the control action is as follows:

[0084] in, The control input is the fan PWM signal; This is the proportionality coefficient; This refers to the error between the given value and the actual value, specifically the difference between the given value and the actual value of the battery stack temperature. The integral coefficient; is the differential coefficient.

[0085] It should be noted that due to the inaccuracy of modeling and the uncertain interference caused by environmental factors, the use of PID controllers to control the temperature of air-cooled PEMFCs presents certain challenges. Therefore, active disturbance rejection control technology is introduced to solve this problem. In active disturbance rejection control technology, inaccuracies and external disturbances are combined into a total disturbance term for processing, and the total disturbance term is estimated and compensated by an extended state observer.

[0086] (2) The second control method: In a typical Active Disturbance Rejection Controller (ADRC) control method, the original ADRC is used to control the temperature of an air-cooled PEMFC. ADRC, inherited from the PID controller, has advantages such as simple structure and low computational cost, making it easy to implement in practical engineering. Furthermore, ADRC exhibits good control performance and robustness through disturbance estimation and compensation. Specifically, the original first-order linear ADRC mainly includes Linear State Error Feedback (LSEF) and Linear Extended State Observer (LESO), as shown in the attached diagram. Figure 2 As shown; the original first-order linear ADRC disturbance rejection paradigm is:

[0087] in, This is the derivative of the controlled variable, specifically the derivative of the battery stack temperature. To control the gain of the action; The total disturbance includes both internal and external disturbances; This represents the fan's duty cycle.

[0088] To facilitate the design of the linear extended state observer in the original first-order linear ADRC, the disturbance rejection paradigm of the original first-order linear ADRC needs to be rewritten in the form of state-space equations. That is, the state-space equations corresponding to the disturbance rejection paradigm of the original first-order linear ADRC are as follows:

[0089]

[0090] in, State variables The derivative; State variables The derivative; and All are state variables; The total disturbance includes both internal and external disturbances. The differential.

[0091] Due to the total perturbation in the original first-order linear ADRC disturbance rejection paradigm It cannot be directly measured and needs to be estimated through a linearly extended state observer; therefore, the introduced linearly extended state observer is as follows:

[0092]

[0093]

[0094] in, For estimating parameters The derivative; These are the observed values; and All are estimated parameters. Used to estimate , Used to estimate ; This refers to the battery stack temperature; due to the battery stack temperature It is measurable, so it can be determined based on the temperature of the battery stack. The estimation error is constantly corrected by the observations. ; and Both are matrices, and the matrix sum matrix The state-space equation is the same as that corresponding to the original first-order linear ADRC disturbance rejection paradigm. Design parameters for the observer.

[0095] The introduced linearly extended state observer is expanded as follows:

[0096] By introducing a linear extended state observer, the total disturbance in the original first-order linear ADRC disturbance resistance paradigm can be accurately estimated. Substituting this into the original first-order linear ADRC disturbance rejection paradigm, the air-cooled PEMFC can be transformed into a single-integral element; the single-integral element is as follows:

[0097]

[0098] in; This is the initial feedback control quantity; The temperature of the battery stack; This is the derivative of the battery stack temperature; This refers to the total disturbance, which includes both internal and external disturbances.

[0099] In other words, by using an ADRC controller, the complex air-cooled PEMFC thermal management system can be transformed into a simple single-integral element. This significantly reduces the difficulty of controller design and achieves satisfactory control results, enabling control of a single integral element through proportional control alone.

[0100] in, The target temperature; This is an adjustable parameter.

[0101] This shows that the original first-order linear ADRC has three adjustable parameters, including the adjustable parameter. Adjustable parameters and adjustable parameters At this point, the bandwidth method is used for adjustment; to achieve LESO convergence, the linearly extended state observer needs to be optimized. If all eigenvalues ​​of the matrix are less than 0, then we can obtain:

[0102]

[0103] in, These are the eigenvalues ​​of the matrix.

[0104] Using pole placement, that is, Then we can obtain the following relation:

[0105] in, and These are two specific solutions to the eigenvalues ​​of the matrix.

[0106] To ensure that LESO has a faster convergence speed than LSEF, we generally let:

[0107] in, For the bandwidth of LSEF; This refers to the bandwidth of LESO.

[0108] Apply as attached Figure 3 The current disturbance shown is compared with the battery stack temperature control effect of the first and second control methods, as shown in the attached figure. Figure 4 As shown; from the appendix Figure 4 As can be seen from the comparison of the battery stack temperature control effects of the traditional PID control method and the typical Active Disturbance Rejection Controller (ADRC) control method, it can be found that the typical ADRC control method has a smaller overshoot and a shorter settling time compared to the traditional PID control method. As shown in Table 1 below, the IAE of the typical ADRC control method is significantly smaller throughout the entire control process, decreasing by 37.00% compared to the traditional PID control method.

[0109] Table 1. Comparison of IAE results between traditional PID control method and typical active disturbance rejection controller (ADRC) control method.

[0110] (3) The third control method: ADRC is a model-free control method; regardless of the type of the controlled object, it can ultimately be simplified to, for example... The disturbance rejection paradigm; however, in a typical active disturbance rejection controller (ADRC), its linearly extended state observer needs to have a large bandwidth to estimate the total disturbance in a timely manner. This would increase the system's sensitivity to noise; therefore, in the third control method, battery stack model information is introduced into the typical active disturbance rejection controller (ADRC) paradigm to reduce the total disturbance. By relaxing the bandwidth requirements of the linear extended state observer, the impact of noise can be reduced, thereby improving the control effect to some extent.

[0111] Specifically as follows: First, a preset step response is applied to the battery stack model to obtain its first-order transfer function form, thus acquiring the battery stack model information; the battery stack model information is as follows:

[0112] in, For transfer functions; For Laplace variables; All of these are undetermined parameters in the transfer function.

[0113] Based on the battery stack model information above, the typical Active Distance Rejection Controller (ADRC) can be modified to obtain the disturbance rejection paradigm of the first-order linear ADRC, as follows:

[0114] in, This is the derivative of the battery stack temperature; The temperature of the battery stack; This refers to the fan's duty cycle. This refers to the total disturbance, which includes both internal and external disturbances.

[0115] At this point, the state-space equation corresponding to the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) is as follows:

[0116] in, State variables The derivative; State variables The derivative; and All are state variables; The total disturbance includes both internal and external disturbances. The differential.

[0117] The linear extended state observer in a first-order linear active disturbance rejection controller (ADRC) is as follows:

[0118] in, For estimating parameters The derivative; For estimating parameters The derivative; and These are all adjustable parameters of the observer; and All are estimated parameters; This refers to the fan's duty cycle. The temperature of the battery stack; To estimate temperature To ensure the convergence of the linear extended state observer in the first-order linear active disturbance rejection controller (ADRC), pole placement of its state matrix is ​​required; the pole placement results of the state matrix are as follows:

[0119] in, These are the eigenvalues ​​of the matrix.

[0120] The pole placement results of the state matrix are expanded as follows:

[0121] in, These are the eigenvalues ​​of the matrix.

[0122] Using pole placement, that is, Then we can solve for the following relation:

[0123] in, and These are all adjustable parameters of the observer.

[0124] Similarly, the total disturbance in the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC) can be accurately estimated using a linear extended state observer. Substituting this into the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC), the air-cooled PEMFC can be transformed into a single-integral element; the single-integral element is as follows:

[0125]

[0126] in; This is the initial feedback control quantity; The temperature of the battery stack; This is the derivative of the battery stack temperature; This refers to the total disturbance, which includes both internal and external disturbances.

[0127] It should be noted that by using battery stack model information to modify a typical Active Disturbance Rejection Controller (ADRC), the battery stack model information can be embedded into the ADRC design; to obtain the battery stack model information, system identification is required; due to the total disturbance of the ADRC... It incorporates errors from inaccurate system modeling, therefore it does not require advanced model-based control (such as MPC, LQR) that necessitates system identification at every operating point. ADRC, on the other hand, only needs to perform system identification at one central operating point; see attached. Figure 3 As shown, the central operating point of the air-cooled PEMFC is 26A, therefore system identification is performed at 26A. To obtain the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC), it is only necessary to apply a fan duty cycle disturbance to the battery stack model at the stable operating point of 26A. The disturbance signal is shown in the attached figure. Figure 5 As shown; by using the Matlab System Identification Toolbox to process the input disturbance and output temperature data, the system identification result is as follows:

[0128] in, This is the derivative of the battery stack temperature; The temperature of the battery stack; This represents the fan's duty cycle.

[0129] As attached Figure 6 As shown, attached Figure 6 The figure shows the identification results and actual results of the temperature response curve of the air-cooled PEMFC; from the appendix Figure 6 As can be seen, under the same PWM signal disturbance, the temperature response curve of the identified system is basically consistent with that of the actual system, and its coefficient of determination is... Therefore, It can well describe the system dynamics of the air-cooled PEMFC thermal management system near the 26A operating point, and can be used as the ADRC controller corresponding to the disturbance rejection paradigm of the first-order linear active disturbance rejection controller (ADRC).

[0130] Apply the same attachment Figure 3 The current disturbance shown is compared with the battery stack temperature control effects of the second and third control methods, as shown in the attached figure. Figure 7 As shown; from the appendix Figure 7 As can be seen from the comparison of the battery stack temperature control effects of the typical Active Disturbance Rejection Controller (ADRC) and the ADRC combined with model information, it can be found that, under the premise that other parameters are kept the same, the ADRC combined with model information has a larger adjustment range and a shorter settling time. As shown in Table 2 below, the IAE of the ADRC combined with model information is significantly smaller throughout the entire control process, which is reduced by 42.67% compared with the typical ADRC control method.

[0131] Table 2. IAE Comparison Results of Typical Active Disturbance Rejection Controllers (ADRCs) and ADRCs Incorporating Model Information.

[0132] (4) The fourth control method (the method described in Example 1): Based on the third control method, namely ADRC combined with model information, the Particle Swarm Optimization (PSO) algorithm is used to optimize the preset key parameter values ​​of its linearly extended state observer; among which, the adjustable parameters of the observer in the linearly extended state observer... Adjustable parameters of the observer This can affect the final performance of the first-order linear active disturbance rejection controller (ADRC); therefore, the particle swarm optimization algorithm is used to optimize the adjustable parameters of the observer. Adjustable parameters of the observer The optimization was carried out to further improve the temperature control effect based on the third control method.

[0133] Because the air-cooled PEMFC thermal management system combined with the ADRC controller is very complex, it is difficult to theoretically analyze the adjustable parameters of the observer. Adjustable parameters of the observer The precise relationship between the value of the temperature swarm optimization algorithm and the control effect is considered. Therefore, the particle swarm optimization algorithm is adopted to continuously improve the temperature control effect through iterative evolution. Specifically, the optimization objective is the temperature control effect, so the fitness function of the particle swarm optimization algorithm is constructed as follows:

[0134]

[0135] in, This is the fitness function for the particle swarm optimization algorithm; It is the integral of absolute error, an indicator used to measure the effectiveness of control. As shown by the error, a smaller IAE corresponds to a better control effect. The decision variable is selected based on the adjustable parameters of the observer corresponding to each current disturbance. Adjustable parameters of the observer Apply as attached Figure 3 The current disturbance shown changes 7 times throughout the control process, therefore the total number of decision variables is 2 × 7 = 14; the particle number is selected as 10, the maximum number of iterations is 50, and the iterative curve of the resulting particle swarm optimization algorithm is shown in the attached figure. Figure 8 As shown, convergence was achieved on the 21st attempt.

[0136] Apply the same attachment Figure 3 The current disturbance shown is compared with the battery stack temperature control effects of the third and fourth control methods, as shown in the attached figure. Figure 9 As shown; from the appendix Figure 9 As can be seen from the comparison of the battery stack temperature control effect of the Active Disturbance Rejection Controller (ADRC) control method combining model information and the temperature control method of Example 1, it can be found that, based on the ADRC combined with the model, the fourth control method after optimization by the ion swarm algorithm can further reduce the overshoot and shorten the adjustment time. As shown in Table 3 below, in the entire control process, the IAE is significantly smaller after optimization by the ion swarm algorithm, which is reduced by 40.21% based on the ADRC combined with the model. The above shows that the temperature control method of the air-cooled PEMFC provided in Example 1 is an effective method for optimizing complex control systems.

[0137] Table 3. Comparison of IAE results between the Active Disturbance Rejection Controller (ADRC) incorporating model information and the temperature control method in Example 1.

[0138] As attached Figure 10-11 As shown, attached Figure 10 The adjustable parameters of the observer in Example 1 are given in the document. Variation curves for different control processes, with appendix Figure 11 The adjustable parameters of the observer in Example 1 are given in the document. Variation curves in different control processes; from the appendix Figure 10 and attached Figure 11 As can be seen from this, the adjustable parameters of the observer are optimized using the particle swarm optimization algorithm. With the adjustable parameters of the observer It will automatically adjust whenever a current disturbance occurs in order to achieve better control.

[0139] In summary, the structure of the first-order linear active disturbance rejection controller (ADRC) in Embodiment 1 is as shown in the attached figure. Figure 12 As shown; the construction process of the first-order linear active disturbance rejection controller (ADRC) is as follows: model information is obtained through system identification, the disturbance rejection paradigm of ADRC is then corrected based on this information, and finally, the adjustable parameters of the observer in the linear extended state observer are optimized using the particle swarm optimization algorithm. Adjustable parameters of the observer .

[0140] The temperature control method for air-cooled PEMFC described in Embodiment 1 embeds model information into the ADRC disturbance rejection paradigm, which can reduce the total disturbance term, lower the requirement for ESO convergence speed, thereby reducing noise impact and improving control performance to some extent; due to the adjustable parameters of the observer Adjustable parameters of the observer The value of this parameter is closely related to the final temperature control effect. A particle swarm optimization algorithm is used to adjust the adjustable parameters of the observer. Adjustable parameters of the observer Optimization allows for precise analysis of the observer's adjustable parameters. Adjustable parameters of the observer The value of affects the control effect, effectively reducing the difficulty and complexity of temperature control.

[0141] Example 2 As attached Figure 13 As shown, this embodiment 2 provides a temperature control system for an air-cooled PEMFC, including a model building module, a model information acquisition module, a controller building module, a data acquisition module, a control quantity generation module, and a temperature control module.

[0142] The system comprises the following modules: a model building module for constructing a dynamic model of the air-cooled PEMFC thermal management system, which includes a battery stack model and a thermal analysis module; a model information acquisition module for applying a preset step response to the battery stack model in the dynamic model to obtain battery stack model information; a controller building module for constructing a first-order linear active disturbance rejection controller (ADRC) based on the battery stack model information, where the disturbance rejection paradigm of the ADRC is corrected using battery stack model information, and the preset key parameters of the linear extended state observer in the ADRC are optimized using a particle swarm optimization algorithm; a data acquisition module for acquiring the current actual temperature of the air-cooled PEMFC and the temperature control quantity from the previous moment; a control quantity generation module for generating the temperature control quantity for the next moment based on the current actual temperature of the air-cooled PEMFC and the temperature control quantity from the previous moment, combined with the ADRC; and a temperature control module for inputting the temperature control quantity for the next moment into the thermal analysis module of the dynamic model to control the temperature of the air-cooled PEMFC.

[0143] Example 3 As attached Figure 4 As shown, this embodiment 3 provides an electronic device, including: a memory for storing a computer program; a processor for executing the computer program to implement the steps of the temperature control method for an air-cooled PEMFC; or, the processor executing the computer program to implement the functions of each module in the temperature control system of the air-cooled PEMFC described above.

[0144] For example, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to complete the present invention. The one or more modules / units may be a series of computer program instruction segments capable of performing a preset function, the instruction segments describing the execution process of the computer program in the electronic device.

[0145] The electronic device may be a desktop computer, laptop, handheld computer, or cloud server, etc. The electronic device may include, but is not limited to, a processor and memory. Those skilled in the art will understand that the above are examples of electronic devices and do not constitute a limitation on the electronic device. It may include more components than described above, or combine certain components, or different components. For example, the electronic device may also include input / output devices, network access devices, buses, etc.

[0146] The processor can be a central processing unit, or other general-purpose processors, digital signal processors, application-specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor, or any conventional processor, etc. The processor is the control center of the electronic device, connecting various parts of the entire electronic device through various interfaces and lines.

[0147] The memory can be used to store the computer program and / or module. The processor implements various functions of the electronic device by running or executing the computer program and / or module stored in the memory and by calling the data stored in the memory.

[0148] The memory may primarily include a program storage area and a data storage area. The program storage area may store the operating system and at least one application program required for a given function (such as sound playback, image playback, etc.). The data storage area may store data created based on the use of the mobile phone (such as audio data, phonebook, etc.). Furthermore, the memory may include high-speed random access memory and non-volatile memory, such as hard disks, RAM, plug-in hard disks, smart memory cards, secure digital cards, flash memory cards, at least one disk storage device, flash memory device, or other volatile solid-state storage devices.

[0149] Example 4 This embodiment 4 also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the temperature control method for an air-cooled PEMFC.

[0150] If the temperature control system module / unit of the air-cooled PEMFC is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0151] Based on this understanding, the present invention can implement all or part of the processes in the temperature control method of the air-cooled PEMFC, or it can be accomplished by a computer program instructing related hardware. The computer program can be stored in a computer-readable storage medium, and when executed by a processor, it can implement the steps of the temperature control method of the air-cooled PEMFC. The computer program includes computer program code, which can be in the form of source code, object code, executable file, or a preset intermediate form, etc.

[0152] The computer-readable storage medium may include any entity or device capable of carrying the computer program code, recording media, USB flash drive, portable hard drive, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electrical carrier signal, telecommunication signal, and software distribution medium, etc.

[0153] Example 5 This embodiment 5 provides a computer product, which includes a computer program stored in a computer-readable storage medium. The processor of the electronic device reads the computer program from the computer-readable storage medium and executes the computer program, so that the electronic device can execute the temperature control method of the air-cooled PEMFC described in embodiment 1, which will not be described again here.

[0154] It should be noted that those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The program can be stored in a computer-readable storage medium, and when the program is executed, it can include the processes of the embodiments of the above methods.

[0155] The above embodiments are merely one of the implementation methods for achieving the technical solution of the present invention. The scope of protection claimed by the present invention is not limited to this embodiment, but also includes any variations, substitutions and other implementation methods that can be easily conceived by those skilled in the art within the scope of the technology disclosed in the present invention.

Claims

1. A temperature control method of an air-cooled PEMFC, characterized by, The application relates to a method for controlling temperature of an air-cooled proton exchange membrane fuel cell (PEMFC), and belongs to the technical field of fuel cell control. The method comprises the following steps: A dynamic model of an air-cooled PEMFC thermal management system is constructed; wherein the dynamic model of the air-cooled PEMFC thermal management system comprises a cell stack model and a thermal analysis module; A preset step response is applied to the cell stack model in the dynamic model of the air-cooled PEMFC thermal management system, and cell stack model information is obtained; Based on the cell stack model information, a first-order linear active disturbance rejection controller (ADRC) is constructed; wherein a disturbance rejection paradigm of the first-order linear ADRC is obtained by modifying the cell stack model information, and preset key parameters of a linear extended state observer in the first-order linear ADRC are obtained by optimizing the parameters through a particle swarm algorithm; Actual temperature of the air-cooled PEMFC at a current moment and a temperature control quantity at a previous moment are obtained; Based on the actual temperature of the air-cooled PEMFC at the current moment and the temperature control quantity at the previous moment, a temperature control quantity at a next moment is generated in combination with the first-order linear ADRC; 2. The temperature control method of an air-cooled PEMFC according to claim 1, wherein The temperature control quantity at the next moment is input to the thermal analysis module in the dynamic model of the air-cooled PEMFC thermal management system, and temperature of the air-cooled PEMFC is controlled. wherein is a transfer function; is a Laplace variable; are both undetermined parameters in the transfer function.

3. The temperature control method of an air-cooled PEMFC according to claim 1, wherein The cell stack model information is as follows: wherein, is a derivative of the battery stack temperature; are both undetermined parameters in the transfer function; is the battery stack temperature; is a duty cycle of the fan; is a total disturbance including internal and external disturbances; The disturbance rejection paradigm of the first-order linear ADRC is as follows: wherein is a derivative of the state variable ; is a derivative of the state variable ; and are state variables; is a differential of the total disturbance which includes internal and external disturbances.

4. The temperature control method of an air-cooled PEMFC according to claim 1, wherein The state space equation corresponding to the disturbance rejection paradigm of the first-order linear ADRC is as follows: The first-order linear ADRC comprises a linear state error feedback controller and a linear extended state observer; wherein, is the derivative of the estimated parameter ; is the derivative of the estimated parameter ; and are adjustable parameters of the observer; and are estimated parameters; is the duty cycle of the fan; is the battery stack temperature; is the estimated temperature; The linear extended state observer is as follows: wherein; is a preliminary feedback control amount; are both undetermined parameters in a transfer function; is a battery stack temperature; is a derivative of the battery stack temperature; is a total disturbance including an internal disturbance and an external disturbance.

5. The temperature control method of an air-cooled PEMFC according to claim 4, wherein The preset key parameters of the linear extended state observer include adjustable parameters of the observer and adjustable parameters of the observer .

6. The temperature control method of an air-cooled PEMFC according to claim 1, wherein The linear extended state observer is substituted into the disturbance rejection paradigm of the first-order linear ADRC, so that the air-cooled PEMFC thermal management system is converted into a single-integral-element control, as follows: wherein is the fitness function for the particle swarm algorithm; is the absolute error integral; is the error.

7. A temperature control system for an air-cooled PEMFC, characterized by, In the process of obtaining the preset key parameters of the linear extended state observer in the first-order linear ADRC through the particle swarm algorithm optimization, the fitness function of the particle swarm algorithm is as follows: The application relates to a method for controlling temperature of an air-cooled proton exchange membrane fuel cell (PEMFC), and belongs to the technical field of fuel cell control. The method comprises the following steps: A model construction module is used for constructing a dynamic model of an air-cooled PEMFC thermal management system; wherein the dynamic model of the air-cooled PEMFC thermal management system comprises a cell stack model and a thermal analysis module; A model information acquisition module is used for applying a preset step response to the cell stack model in the dynamic model of the air-cooled PEMFC thermal management system, and obtaining cell stack model information; A controller construction module is used for constructing a first-order linear active disturbance rejection controller (ADRC) based on the cell stack model information; wherein a disturbance rejection paradigm of the first-order linear ADRC is obtained by modifying the cell stack model information, and preset key parameters of a linear extended state observer in the first-order linear ADRC are obtained by optimizing the parameters through a particle swarm algorithm; A data acquisition module is used for obtaining actual temperature of the air-cooled PEMFC at a current moment and a temperature control quantity at a previous moment; A control quantity generation module is used for generating a temperature control quantity at a next moment in combination with the first-order linear ADRC based on the actual temperature of the air-cooled PEMFC at the current moment and the temperature control quantity at the previous moment; and The temperature control module is used for inputting the temperature control amount of the next time into a thermal analysis module in the air-cooled PEMFC thermal management system dynamic model to control the temperature of the air-cooled PEMFC.

8. An electronic device, comprising: The temperature control method of the air-cooled PEMFC comprises the following steps: A processor is adapted to execute a computer program. A computer readable storage medium has a computer program stored therein, and the computer program, when executed by the processor, executes the temperature control method of the air-cooled PEMFC according to any one of claims 1-6.

9. A computer-readable storage medium storing a computer program, the computer-readable storage medium comprising: The computer program, when executed by the processor, implements the temperature control method of the air-cooled PEMFC according to any one of claims 1-6.

10. A computer program product, characterised in that, The computer program product comprises a computer program, and the computer program, when executed by the processor, implements the temperature control method of the air-cooled PEMFC according to any one of claims 1-6.

Images