Layered fuel cell temperature control method based on adaptive model-free predictive control

Abstract

The invention discloses a stratified fuel cell temperature control method based on adaptive model-free predictive control. The method comprises the steps that firstly, an upper-layer decision maker determines the optimal stack temperature under different working conditions based on a polarization curve of a stack, and the optimal stack temperature serves as the optimal reference temperature to be output to a lower-layer controller; in the lower layer controller, based on real-time input and output data of battery operation, nonlinear prediction of the stack temperature is realized by introducing an auxiliary slack variable. And then an optimal control variable is obtained by solving an optimization problem with constraints in each execution period, and a water pump and a radiator are driven to complete optimal control of the temperature of the galvanic pile. Compared with a traditional control method, the method has the advantages that the dependency on the model is reduced; compared with a traditional model prediction control method, the method has the advantages of being low in calculation complexity, low in requirement for controller hardware and the like, and the problems that the proton exchange membrane fuel cell is high in nonlinearity and coupling performance and large in control difficulty are solved to a certain extent.

Description

Technical Field

[0001] The present invention relates to a data-driven predictive control method in the field of battery thermal management, and in particular to a control method and system for a thermal management system of a layered proton exchange membrane fuel cell (PEMFC) based on adaptive model-free predictive control (AMFPC). Background Art

[0002] Among various types of fuel cells, PEMFC has the advantages of high power density, fast start-up capability, and suitability for fixed and mobile applications. During the operation of the PEMFC system, oxygen reacts with hydrogen to produce electricity, while only water and heat are produced, and ideally no polluting waste is produced, making it one of the key technologies for the development and application of hydrogen energy in the context of green and sustainable development.

[0003] In a fuel cell system, the stack temperature is one of the key parameters that affect the operating efficiency and system life of the fuel cell. The temperature of the stack is directly related to the output performance and durability of the PEMFC. When the stack temperature is too low, the activity of the catalyst is inhibited, the electrochemical reaction rate decreases, and the output efficiency of the fuel cell is significantly reduced. This not only affects the instantaneous output power of the system, but may also lead to a decrease in the overall efficiency, especially when running for a long time at a low temperature, the energy utilization of the system will be greatly reduced. In addition, low-temperature operation is also prone to imbalance in water management, causing water to accumulate inside the stack, further affecting the operating performance of the fuel cell. On the contrary, when the stack temperature is too high, the problem is equally serious. Under high temperature conditions, the electrolyte membrane will accelerate degradation, resulting in a decrease in proton conductivity and even permanent damage to the membrane. In this case, not only will the output performance of the stack decrease, but the life of the entire fuel cell system will also be greatly shortened, and it may even cause system failure. Therefore, precise control of the stack temperature is crucial in the design and operation of PEMFC.

[0004] In order to ensure that the stack can operate within the optimal temperature range, PEMFC is usually equipped with a temperature management system, which relies on two main actuators: a cooling water pump and a radiator (or fan) to adjust the temperature of the stack. The cooling water pump controls the heat dissipation of the system by adjusting the cooling water flow into the stack. By adjusting the flow of the water pump, the heat generated by the stack can be taken away in time to prevent the temperature from being too high. Secondly, the radiator is connected to the stack through a pipe, and the heat removed from the stack is dissipated into the air in time through the fan to ensure that the temperature of the stack does not exceed the safe range. The core principle of this temperature management system is to coordinate the cooling water flow and the working efficiency of the radiator through a reasonable control strategy to ensure that the heat generated by the chemical reaction inside the stack can be discharged in a timely and effective manner, thereby maintaining the stability of the stack temperature. This can not only improve the instant output performance of the fuel cell, but also extend the overall life of the system and improve the long-term reliability of the fuel cell. Therefore, the effectiveness of PEMFC temperature management largely determines the operating efficiency and life of the system, and is a crucial link in fuel cell technology.

[0005] At present, for the control of the temperature of the fuel cell stack, most control strategies adopt model-based control strategies, such as the common feedforward, feedback control strategies, model predictive control and other control methods. However, since the PEMFC thermal management system contains a large number of nonlinear dynamics and semi-empirical equations to be fitted, it is difficult to obtain system equations with high fitting accuracy, which also brings challenges to the model-based control strategy. Compared with the learning-based model-free algorithm or the traditional PID-based model-free control method, the former brings a huge computational burden and is difficult to implement and promote directly under the current hardware conditions; the latter is difficult to directly handle the strongly coupled control system with multiple inputs and multiple outputs, and there are problems such as complex parameter adjustment.

[0006] Therefore, precise temperature control of fuel cells remains a huge challenge. Summary of the invention

[0007] In view of this, in order to solve the problems existing in the background technology, the purpose of the present invention is to propose a control method of a stratified fuel cell thermal management system based on adaptive model-free predictive control.

[0008] The technical solution adopted by the present invention is as follows:

[0009] 1. A temperature control method for stratified fuel cells based on adaptive model-free predictive control

[0010] Step 1: Collect the actual stack temperature and actual control input of the stratified fuel cell, and generate the optimal stack temperature according to the current actual stack temperature;

[0011] Step 2: construct a prediction model for the stratified fuel cell, and then establish an optimization target for the stratified fuel cell based on the prediction model for the stratified fuel cell;

[0012] Step 3: Collect the historical stack temperature and corresponding control input data of the stratified fuel cell, and after periodic processing of the historical stack temperature and the corresponding control input data, obtain the historical relative data of the fuel cell and the future relative data of the fuel cell, and then combine the actual stack temperature and the actual control input and the optimal stack temperature of the stratified fuel cell. After optimizing and solving the battery temperature of the stratified fuel cell according to the optimization target of the stratified fuel cell, obtain the optimal control sequence, and finally control the thermal management system of the stratified fuel cell according to the optimal control sequence to complete the temperature control of the stratified fuel cell.

[0013] In step 1, the optimal stack temperature is generated according to the current actual stack temperature, specifically:

[0014] The stack temperature Tr corresponding to the maximum output power point is found from the voltage-current polarization curve of the stack corresponding to the current actual stack temperature, and the stack temperature Tr is used as the optimal stack temperature of the current actual stack temperature.

[0015] In step 2, the formula for the optimization target of the layered fuel cell is as follows:

[0016]

[0017] Among them, σ y represents the slack variable, g represents the decision variable, u represents the predictive control input of the thermal management system, y represents the predicted value of the stack temperature, N represents the prediction step size, and y k represents the predicted value of the stack temperature at the kth step, r t+k represents the stack reference temperature at time t+k, u k represents the control input of the kth step, the first optimization term Satisfy(||y k -r t+k || T *Q*||y k -r t+k ||) 2 , the second optimization item Satisfy(||u k || T *R*||u k ||) 2 , || ||1 represents the one-norm, T represents the transpose, R and Q represent the first coefficient matrix and the second coefficient matrix respectively, || || represents the matrix, λ g and λ y are two penalty coefficients, is the constraint set of the actual stack temperature, is the set of constraints for controlling the input; U pRepresents the historical relative control input matrix in the fuel cell historical relative data, Y p Represents the historical relative stack temperature matrix in the fuel cell historical relative data, U f represents the future relative control input matrix in the future relative data of the fuel cell, Y f Represents the future relative stack temperature matrix in the future relative data of the fuel cell, u ini represents the actual control input of the layered fuel cell, y ini Indicates the actual stack temperature of the stratified fuel cell.

[0018] In step 3, after periodic processing of the historical stack temperature and control input data, the historical relative data of the fuel cell and the future relative data of the fuel cell are obtained, specifically:

[0019] After processing the historical stack temperature and control input data using the following formula, the historical relative control input matrix U is obtained: p and historical relative stack temperature matrix Y p And form the fuel cell historical relative data, and obtain the future relative control input matrix U f and the future relative stack temperature matrix Y f And constitute the relative data of fuel cells in the future:

[0020]

[0021] Where L represents the proportionality coefficient, represents the Hankel matrix, u d is the historical control input data collected, y d For the historical stack temperature data collected, and They are the historical control input data u d The first one, the TT s +1, L and T s components, y1, y T-L+1 ,y L and T They are the historical stack temperature data y d The first one, TT s +1, Lth and Tth s Components, T s Indicates historical stack temperature data u d Data length, T ini represents the initial time, and N represents the prediction step size.

[0022] 2. A Stratified Fuel Cell Temperature Control System Based on Adaptive Model-Free Predictive Control

[0023] An upper decision maker is used to generate an optimal stack temperature according to the actual stack temperature of the stratified fuel cell collected;

[0024] The lower controller is used to collect the historical stack temperature and the corresponding control input data of the stratified fuel cell, and obtain the historical relative data of the fuel cell and the future relative data of the fuel cell after periodic processing of the historical stack temperature and the corresponding control input data. Then, the actual stack temperature, actual control input and optimal stack temperature of the stratified fuel cell are combined, and the battery temperature of the stratified fuel cell is optimized and solved according to the optimization target of the stratified fuel cell, and the optimal control sequence is obtained and acts on the thermal management system of the stratified fuel cell.

[0025] 3. A computer device

[0026] The computer device includes a memory and a processor, the memory stores a computer program, and the processor implements the steps of the stratified fuel cell temperature control method based on adaptive model-free predictive control when executing the computer program.

[0027] 4. A computer-readable storage medium

[0028] The storage medium stores a computer program, and when the computer program is executed by the processor, the steps of any one of the methods for controlling the temperature of a stratified fuel cell based on adaptive model-free predictive control are implemented.

[0029] 5. A computer program product

[0030] The product includes a computer program / instruction, which, when executed by a processor, implements the steps of the stratified fuel cell temperature control method based on adaptive model-free predictive control.

[0031] The beneficial effects of the present invention are:

[0032] (1) The present invention combines the fuel cell thermal management model and operating data, predicts the output through decision variables, and introduces relaxation variables for nonlinear compensation, thereby overcoming the defects of traditional battery temperature control methods that are limited by the strong coupling and strong nonlinearity of the system. At the same time, compared with learning algorithms (based on neural networks, deep learning, reinforcement learning, etc.), the computational burden is greatly reduced and the stability of the fuel cell operating temperature is improved.

[0033] (2) The present invention proposes a layered optimal temperature control framework to achieve dynamic tracking of the optimal temperature under different working conditions and maximize the output power of the fuel cell stack.

[0034] Therefore, compared with traditional control methods, the present invention reduces the dependence on the model; compared with traditional model predictive control methods, the present invention has the advantages of low computational complexity and low requirements for controller hardware, and to a certain extent solves the problems of strong nonlinearity, strong coupling and high control difficulty of proton exchange membrane fuel cells. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 This is a framework diagram of the hierarchical control method involved in the present invention.

[0036] Figure 2 This is a structural diagram of the AMFPC control method involved in the present invention.

[0037] Figure 3 This is a diagram to verify the effect of the AMFPC control method involved in the present invention. DETAILED DESCRIPTION

[0038] The present invention is further described below in conjunction with the accompanying drawings and specific embodiments, but the protection scope of the present invention is not limited thereto.

[0039] In the face of a fuel cell system with strong coupling, nonlinearity, and multiple input and multiple output, the present invention proposes a stratified fuel cell temperature control method based on adaptive model-free predictive control, which adopts a stratified control framework, such as Figure 1 As shown in the figure, the hierarchical control framework includes an upper decision maker and a lower controller, where the upper decision maker determines the optimal stack temperature based on the stack polarization curve, and the lower controller relies on traditional PID control for short-term data collection during the data collection stage, and then quickly switches to the AMFPC method to achieve real-time online tracking of the optimal temperature. The circulating water pump and cooling fan of the PEMFC temperature management system are used as actuators, and the stack output temperature is the control variable.

[0040] This embodiment specifically includes the following steps:

[0041] Step 1: Collect the actual stack temperature and actual control input of the stratified fuel cell, and generate the optimal stack temperature according to the current actual stack temperature, which is used as the reference stack temperature;

[0042] Among them, the optimal stack temperature is generated according to the current actual stack temperature, specifically:

[0043] like Figure 1 As shown, the stack temperature Tr corresponding to the maximum output power point is found from the voltage-current polarization curve of the stack corresponding to the current actual stack temperature, and the stack temperature Tr is used as the optimal stack temperature of the current actual stack temperature (ie, under this operating condition).

[0044] Step 2: Construct a prediction model for the stratified fuel cell, and then establish the optimization target of the stratified fuel cell based on the prediction model of the stratified fuel cell, such as Figure 2 As shown;

[0045] The prediction model of the layered fuel cell is an adaptive model-free prediction model, and its formula is as follows:

[0046]

[0047] In order to obtain the minimum error and the minimum consumption of control actions, considering the constraints of the actual industrial site, and adding the constraints on the slack variables and decision variables, the optimization objective formula of the layered fuel cell is as follows:

[0048]

[0049] Among them, σ y represents the slack variable, g represents the decision variable, u represents the predictive control input of the thermal management system, y represents the predicted value of the stack temperature, N represents the prediction step size, and y k represents the predicted value of the stack temperature at the kth step, r t+k represents the stack reference temperature at time t+k, u k represents the control input of the kth step, the first optimization term Satisfy(||y k -r t+k || T *Q*||y k -r t+k ||) 2 , the second optimization item Satisfy(||u k || T *R*||u k ||) 2 , || ||1 represents the one-norm, T represents the transpose, R and Q represent the first coefficient matrix and the second coefficient matrix respectively, || || represents the matrix, λ g and λ y are two penalty coefficients, is the constraint set of the actual stack temperature, is the set of constraints for controlling the input; U p Represents the historical relative control input matrix in the fuel cell historical relative data, Y p Represents the historical relative stack temperature matrix in the fuel cell historical relative data, U f represents the future relative control input matrix in the future relative data of the fuel cell, Y f Represents the future relative stack temperature matrix in the future relative data of the fuel cell, u ini represents the actual control input of the layered fuel cell, y ini Indicates the actual stack temperature of the stratified fuel cell.

[0050] Step 3: Before collecting the historical stack temperature and corresponding control input data of the stratified fuel cell, the controller switches to the classic fuzzy PID control method, and then collects the historical stack temperature and corresponding control input data of the stratified fuel cell. After the data collection is completed, switch to the model-free predictive control method proposed in the present invention. Then, after periodic processing of the historical stack temperature and the corresponding control input data, the historical relative data of the fuel cell and the future relative data of the fuel cell are obtained. Then, combined with the actual stack temperature and actual control input of the stratified fuel cell and the optimal stack temperature, the battery temperature of the stratified fuel cell is optimized and solved according to the optimization target of the stratified fuel cell, and the optimal control sequence is obtained, that is, Figure 1 The lower controller in the embodiment finally controls the thermal management system of the stratified fuel cell according to the optimal control sequence. Specifically, the first control amount of the optimal control sequence is applied to the thermal management system to complete the temperature control of the stratified fuel cell.

[0051] In step 3, after periodic processing of the historical stack temperature and control input data, the historical relative data of the fuel cell and the future relative data of the fuel cell are obtained, specifically:

[0052] After processing the historical stack temperature and control input data using the following formula, the historical relative control input matrix U is obtained: p and historical relative stack temperature matrix Y p And form the fuel cell historical relative data, and obtain the future relative control input matrix U f and the future relative stack temperature matrix Y f And constitute the relative data of fuel cells in the future:

[0053]

[0054] Where L represents the proportionality coefficient, represents the Hankel matrix, u d is the historical control input data collected, y d is the historical stack temperature data collected, u d and d are vectors, and They are the historical control input data u d The first one, the TT s +1, L and T s components, y1, y T-L+1 ,y L and T They are the historical stack temperature data y d The first one, TT s +1, Lth and Tth sComponents, T s Indicates historical stack temperature data u d and historical stack temperature data y d Data length, T ini represents the initial time, and N represents the prediction step size.

[0055] The present invention also proposes a stratified fuel cell temperature control system based on adaptive model-free predictive control, comprising:

[0056] An upper decision maker is used to generate an optimal stack temperature according to the actual stack temperature of the stratified fuel cell collected;

[0057] The lower controller (i.e., the AMFPC controller) is used to collect the historical stack temperature and the corresponding control input data of the stratified fuel cell, and after periodic processing of the historical stack temperature and the corresponding control input data, obtain the historical relative data of the fuel cell and the future relative data of the fuel cell, and then combine the actual stack temperature and the actual control input and the optimal stack temperature of the stratified fuel cell. After optimizing and solving the battery temperature of the stratified fuel cell according to the optimization target of the stratified fuel cell, the optimal control sequence is obtained and acts on the thermal management system of the stratified fuel cell.

[0058] The AMFPC method proposed in the present invention is verified below. The initial temperature of the fuel cell is set to 62°C, and the control effect verification diagram of the present invention is generated for different optimal temperature requirements, such as Figure 3 As shown in the figure, it can be seen that the AMFPC method designed by the present invention can control the output temperature to reach the reference temperature at a faster speed and maintain a stable state, with an absolute error of less than 0.5°C and a dynamic error of less than 2°C, so it can be proved that the AMFPC method designed by the present invention has good control performance.

[0059] Finally, it should be noted that the above embodiments and explanations are only used to illustrate the technical solution of the present invention rather than to limit it. Those skilled in the art should understand that the technical solution of the present invention can be modified or replaced by equivalents without departing from the spirit and scope disclosed in the technical solution of the present invention, which should be included in the scope of protection of the claims of the present invention.

Claims

1. A temperature control method for a stratified fuel cell based on adaptive model-free predictive control, characterized in that: The following steps are involved: Step 1: Collect the actual stack temperature and actual control input of the stratified fuel cell, and generate the optimal stack temperature according to the current actual stack temperature; Step 2: construct a prediction model for the stratified fuel cell, and then establish an optimization target for the stratified fuel cell based on the prediction model for the stratified fuel cell; Step 3: Collect the historical stack temperature and corresponding control input data of the stratified fuel cell, and after periodic processing of the historical stack temperature and the corresponding control input data, obtain the historical relative data of the fuel cell and the future relative data of the fuel cell, and then combine the actual stack temperature and the actual control input and the optimal stack temperature of the stratified fuel cell. After optimizing and solving the battery temperature of the stratified fuel cell according to the optimization target of the stratified fuel cell, obtain the optimal control sequence, and finally control the thermal management system of the stratified fuel cell according to the optimal control sequence to complete the temperature control of the stratified fuel cell.

2. The temperature control method of a stratified fuel cell based on adaptive model-free predictive control according to claim 1, characterized in that: In step 1, the optimal stack temperature is generated according to the current actual stack temperature, specifically: The stack temperature Tr corresponding to the maximum output power point is found from the voltage-current polarization curve of the stack corresponding to the current actual stack temperature, and the stack temperature Tr is used as the optimal stack temperature of the current actual stack temperature.

3. The temperature control method of a stratified fuel cell based on adaptive model-free predictive control according to claim 1, characterized in that: In step 2, the formula for the optimization target of the layered fuel cell is as follows: Among them, σ y represents the slack variable, g represents the decision variable, u represents the predictive control input of the thermal management system, y represents the predicted value of the stack temperature, N represents the prediction step size, and y k represents the predicted value of the stack temperature at the kth step, r t+k Indicates the stack reference temperature at time t+k, u k represents the control input of the kth step, the first optimization term Satisfy(||y k -r t+k || T *Q*||y k -r t+k ||) 2 , the second optimization item Satisfy(||u k || T *R*||u k ||) 2 , || ||1 represents the one-norm, T represents the transpose, R and Q represent the first coefficient matrix and the second coefficient matrix respectively, || || represents the matrix, λ g and λ y are two penalty coefficients, is the constraint set of the actual stack temperature, is the constraint set for controlling the input; U p Represents the historical relative control input matrix in the fuel cell historical relative data, Y p Represents the historical relative stack temperature matrix in the fuel cell historical relative data, U f represents the future relative control input matrix in the future relative data of the fuel cell, Y f Represents the future relative stack temperature matrix in the future relative data of the fuel cell, u ini represents the actual control input of the layered fuel cell, y ini Indicates the actual stack temperature of the stratified fuel cell.

4. The temperature control method of a stratified fuel cell based on adaptive model-free predictive control according to claim 1, characterized in that: In step 3, after periodic processing of the historical stack temperature and control input data, the historical relative data of the fuel cell and the future relative data of the fuel cell are obtained, specifically: After processing the historical stack temperature and control input data using the following formula, the historical relative control input matrix U is obtained: p and historical relative stack temperature matrix Y p And form the fuel cell historical relative data, and obtain the future relative control input matrix U f and the future relative stack temperature matrix Y f And constitute the relative data of fuel cells in the future: Where L represents the proportionality coefficient, represents the Hankel matrix, u d is the historical control input data collected, y d For the historical stack temperature data collected, and They are the historical control input data u d The first one, the TT s +1, L and T s components, y1, y T-L+1 ,y L and T They are the historical stack temperature data y d The first one, TT s +1, Lth and Tth s Components, T s Indicates historical stack temperature data u d Data length, T ini represents the initial time, and N represents the prediction step size.

5. A stratified fuel cell temperature control system based on adaptive model-free predictive control, characterized in that: include: An upper decision maker is used to generate an optimal stack temperature according to the actual stack temperature of the stratified fuel cell collected; The lower controller is used to collect the historical stack temperature and the corresponding control input data of the stratified fuel cell, and obtain the historical relative data of the fuel cell and the future relative data of the fuel cell after periodic processing of the historical stack temperature and the corresponding control input data. Then, the actual stack temperature, actual control input and optimal stack temperature of the stratified fuel cell are combined, and the battery temperature of the stratified fuel cell is optimized and solved according to the optimization target of the stratified fuel cell, and the optimal control sequence is obtained and acts on the thermal management system of the stratified fuel cell.

6. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the temperature control method of a stratified fuel cell based on adaptive model-free predictive control according to any one of claims 1 to 4 are implemented.

7. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the temperature control method of a stratified fuel cell based on adaptive model-free predictive control according to any one of claims 1 to 4 are implemented.

8. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instruction is executed by a processor, the steps of the temperature control method of a stratified fuel cell based on adaptive model-free predictive control as described in any one of claims 1 to 4 are implemented.

Images