Control method, device and medium of proton exchange membrane fuel cell thermal management system

Abstract

The present invention discloses a control method, device, and medium for a proton exchange membrane fuel cell (PEMFC) thermal management system. The PEMFC thermal management system includes a fuel cell stack and a heat dissipation component. The method comprises: obtaining relevant temperature parameter values ​​of the fuel cell stack, a PEMFC system simulation model constructed based on the PEMFC thermal management system, and a controller model for the heat dissipation component; optimizing all adjustable parameters contained in the controller model using a whale optimization algorithm based on the relevant temperature parameter values ​​and the PEMFC system simulation model; processing the relevant temperature parameter values ​​using the optimized controller model to obtain an optimal control signal, and adjusting the current operating state of the heat dissipation component based on the optimal control signal. The present invention can effectively control the efficient and stable operation of a PEMFC within a safe temperature range.

Description

Technical Field

[0001] The present invention relates to the technical field of fuel cells, and in particular to a control method, equipment and medium for a proton exchange membrane fuel cell thermal management system. Background Art

[0002] The performance and lifespan of automotive PEMFCs (Proton Exchange Membrane Fuel Cells) are affected by their internal temperature distribution. While increasing the temperature of the PEMFC stack within a certain range can improve its performance, excessively high temperatures can cause the proton exchange membrane to dehydrate, resulting in a decrease in its conductivity. This deteriorates the performance of the PEMFC stack and shortens its lifespan. To ensure efficient and stable operation within a safe temperature range, the automotive PEMFC thermal management system must be controlled and coordinated for temperature regulation. Configuring a more appropriate control strategy for the automotive PEMFC thermal management system to better adapt to complex dynamic environments is a crucial issue that needs to be addressed to help improve the performance and lifespan of automotive PEMFCs. Summary of the Invention

[0003] The present invention provides a control method, device and medium for a proton exchange membrane fuel cell thermal management system to solve one or more technical problems existing in the prior art and at least provide a beneficial option or create conditions.

[0004] In a first aspect, a control method for a proton exchange membrane fuel cell thermal management system is provided, wherein the proton exchange membrane fuel cell thermal management system includes a fuel cell stack and a heat dissipation component, and the method includes:

[0005] Obtaining relevant temperature parameter values ​​of the fuel cell stack, including a current temperature error and a current temperature error change rate of the fuel cell stack's outlet cooling water, and a current temperature difference error and a current temperature difference error change rate of the fuel cell stack's inlet and outlet cooling water;

[0006] Obtaining a PEMFC system simulation model constructed based on the proton exchange membrane fuel cell thermal management system and a controller model for the heat dissipation component;

[0007] Optimizing all adjustable parameters included in the controller model using a whale optimization algorithm according to the relevant temperature parameter values ​​and the PEMFC system simulation model;

[0008] The optimized controller model is used to process the relevant temperature parameter values ​​to obtain an optimal control signal, and then the current operating state of the heat dissipation component is adjusted according to the optimal control signal.

[0009] Furthermore, the heat dissipation component includes a radiator and a cooling water pump, and the controller model includes a first PID controller, a second PID controller, a first fuzzy controller, a second fuzzy controller, a first signal synthesizer and a second signal synthesizer;

[0010] The input of the first PID controller is the outlet cooling water temperature error of the fuel cell stack, and the output is a first control signal; the input of the second PID controller is the inlet and outlet cooling water temperature difference error of the fuel cell stack, and the output is a second control signal; the first signal synthesizer is used to perform weighted summation on the first control signal and the second control signal to obtain the speed control signal of the radiator;

[0011] The input of the first fuzzy controller is the outlet cooling water temperature error and the temperature error change rate of the fuel cell stack, and the output is a third control signal; the input of the second fuzzy controller is the inlet and outlet cooling water temperature difference error and the temperature difference error change rate of the fuel cell stack, and the output is a fourth control signal; the second signal synthesizer is used to perform weighted summation on the third control signal and the fourth control signal to obtain the speed control signal of the cooling water pump.

[0012] Furthermore, the optimizing all adjustable parameters included in the controller model using the whale optimization algorithm according to the relevant temperature parameter values ​​and the PEMFC system simulation model includes:

[0013] Determine the multi-dimensional target variable according to all morphological control parameters corresponding to all key output membership functions contained in each fuzzy controller and all weight parameters contained in each signal synthesizer;

[0014] determining a fitness function related to a response state of the PEMFC system simulation model;

[0015] Iteratively optimizing the target variable using a whale optimization algorithm according to the relevant temperature parameter value, the fitness function, and the controller model to obtain an optimal target variable value;

[0016] According to the optimal target variable value, all adjustable parameters included in the controller model are updated to obtain an optimized controller model.

[0017] Furthermore, each fuzzy controller contains seven output fuzzy subsets, which are denoted as {NB ox ,NM ox ,NS ox ,ZO ox ,PS ox ,PM ox ,PB ox}, the five output fuzzy subsets arranged in the middle are recorded as the five key output fuzzy subsets, and the membership function of each key output fuzzy subset is the key output membership function.

[0018] Furthermore, each key output membership function is a triangular membership function, and all morphological control parameters corresponding to all key output membership functions contained in each fuzzy controller are determined by the following method:

[0019] For the three key output fuzzy subsets included in each fuzzy controller that are arranged in sequence and continuously, the membership function of the key output fuzzy subset arranged on the left is recorded as the first membership function, the membership function of the key output fuzzy subset arranged in the middle is recorded as the second membership function, and the membership function of the key output fuzzy subset arranged on the right is recorded as the third membership function, and the right foot point of the first membership function, the middle peak point of the second membership function, and the left foot point of the third membership function are set to keep the horizontal coordinates equal;

[0020] Set the output fuzzy subset NM ox The intermediate peak point of the membership function and the output fuzzy subset NS ox The left foot of the membership function keeps the horizontal coordinates equal, and the output fuzzy subset PS is set ox The right foot point of the membership function and the output fuzzy subset PM ox The middle peak point of the membership function keeps the horizontal coordinates equal;

[0021] The horizontal coordinates of the middle peak points of all key output membership functions contained in each fuzzy controller are used as all morphological control parameters corresponding to all key output membership functions.

[0022] Furthermore, the fitness function adopts the following expression:

[0023]

[0024] Where Z is the fitness function. When the current control signal is obtained by processing the relevant temperature parameter value using the currently updated controller model, T st.out is the cooling water temperature at the stack outlet obtained after the PEMFC system simulation model responds to the current control signal, T ref is the target temperature of the cooling water at the stack outlet, ΔT is the temperature difference between the cooling water at the stack inlet and outlet obtained after the PEMFC system simulation model responds to the current control signal, and ΔT ref The target temperature difference of the cooling water at the inlet and outlet of the stack.

[0025] Furthermore, before optimizing all adjustable parameters included in the controller model using the whale optimization algorithm according to the relevant temperature parameter values ​​and the PEMFC system simulation model, the method includes:

[0026] According to the relevant temperature parameter value, all scaling factors associated with all input fuzzy domains contained in each fuzzy controller are determined, and then each scaling factor is used to adjust the associated input fuzzy domain.

[0027] Furthermore, determining all scaling factors associated with all input fuzzy domains contained in each fuzzy controller according to the relevant temperature parameter value includes:

[0028] For each input fuzzy domain included in each fuzzy controller, a temperature parameter value associated with the input fuzzy domain is obtained from the relevant temperature parameter value, and then a scaling factor associated with the input fuzzy domain is determined by combining a preset scaling index and a width of the input fuzzy domain.

[0029] In a second aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the control method of the proton exchange membrane fuel cell thermal management system as described in the first aspect.

[0030] In a third aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the control method of the proton exchange membrane fuel cell thermal management system as described in the first aspect is implemented.

[0031] The present invention has at least the following beneficial effects: a controller model integrating PID control principle and fuzzy control principle is used to analyze in real time two important influencing factors, namely the cooling water temperature at the outlet of the stack and the temperature difference between the cooling water at the inlet and outlet of the stack, to generate relevant control signals for the heat dissipation component, and at the same time, a weight parameter is introduced to limit and adjust the relevant control signal. On the basis of ensuring that the heat dissipation component always operates within the normal range, the proton exchange membrane fuel cell can be effectively controlled to operate efficiently and stably within a safe temperature range; by introducing the whale optimization algorithm, the morphological control parameters corresponding to the relevant membership functions contained in the fuzzy controller and the weight parameters contained in the signal synthesizer are optimized, thereby solving the problem that the existing fuzzy control principle is too dependent on expert experience and practical accumulation, and the input fuzzy domain contained in the fuzzy controller is adaptively adjusted, which can reduce the impact of external disturbances on the system, thereby improving the adaptability, control accuracy and system robustness of the controller model, accelerating the error convergence speed, and reducing the malfunction of the heat dissipation component. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation to the technical solution of the present invention.

[0033] Figure 1 1 is a flow chart of a control method for a proton exchange membrane fuel cell thermal management system according to an embodiment of the present invention;

[0034] Figure 2 is a schematic diagram of the composition of the controller model in an embodiment of the present invention;

[0035] Figure 3 is a schematic diagram of all relevant membership functions contained in the first fuzzy controller in an embodiment of the present invention;

[0036] Figure 4 is a schematic diagram of all relevant membership functions contained in the second fuzzy controller in an embodiment of the present invention;

[0037] Figure 5 is an optimization effect diagram of the membership function of the third control signal u3 in an embodiment of the present invention;

[0038] Figure 6 is an optimization effect diagram of the membership function of the fourth control signal u4 in an embodiment of the present invention;

[0039] Figure 7 Schematic diagram of the hardware structure of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION

[0040] In order to make the purpose, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0041] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described can be performed in a different order than the module division in the system or the order in the flow chart. The terms "first", "second", "third", "fourth", etc. in the specification of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units inherent to these processes, methods, products or devices that are not clearly listed.

[0042] First, some of the terms involved in the present invention are explained as follows:

[0043] The PID controller is composed of three main parts: the proportional unit (P), the integral unit (I), and the differential unit (D). The proportional unit (P) is used to quickly reduce the error, the integral unit (I) is used to eliminate the accumulated error to make the system more stable, and the differential unit (D) is used to adjust the controller output according to the rate of change of the error to make the system respond more quickly and reduce overshoot. The working principle of the PID controller is as follows: first, the output value of the controlled object is measured and compared with the expected value to obtain the error. Then, the error is processed according to the proportional, integral, and differential control terms to obtain the controller output. This output is used to adjust the input of the controlled object to reduce the error so that the output value of the controlled object approaches or reaches the expected value. The corresponding mathematical model is as follows:

[0044]

[0045] Where u(t) is the output value of the controlled object, K p is the proportional gain, K i is the integral gain, K d is the differential gain, e(t) is the input error, and t is the time.

[0046] The working principle of the fuzzy controller is: first, obtain the precise input and convert it into a fuzzy input that can be recognized by the system; then, according to the fuzzy control rules formulated by expert experience, the fuzzy input is used to obtain the corresponding fuzzy output through fuzzy logic reasoning; finally, the fuzzy output is converted into a precise output using methods such as the center of gravity method (also known as the weighted average method) for actual control.

[0047] The Whale Optimization Algorithm (WOA) primarily simulates the foraging behavior of humpback whales in the natural ocean. Its core concept is to find the optimal solution by simulating the self-organization and adaptability of whale groups. That is, the position of each individual whale represents a potential solution, and the whale's position is continuously updated in the solution space through iteration to ultimately obtain the global optimal solution. The Whale Optimization Algorithm's search strategies mainly involve the prey encirclement strategy, the bubble attack strategy, and the prey search strategy, which are described below:

[0048] (1) Prey encirclement strategy: Assuming that the current optimal solution is the target prey, other whale individuals try to move towards the target prey. At this time, the position of each whale individual is updated using the following expression:

[0049] X(t+1)=X * (t)-A·D

[0050] D=|C·X * (t)-X(t)|, A=2a×r1-a, C=2×r2

[0051] Where X(t+1) is the position vector of the whale individual at the t+1th iteration, X(t) is the position vector of the whale individual at the tth iteration, and X * (t) is the position vector of the optimal whale individual obtained by evaluating the fitness function after the tth iteration of the whale population, D is the distance between the whale individual and the optimal whale individual, A and C are both coefficient vectors, a is an adjustable coefficient, and its value decreases linearly from 2 to 0 during the iteration process, r1 and r2 are control parameters with random values ​​in the range of [0, 1];

[0052] (2) Bubble attack strategy: Assuming that the current optimal solution is the target prey, other whales swim towards the target prey in a spiral shape, gradually shrinking the bubble net and continuously spitting bubbles. At this time, the position of each whale is updated using the following expression:

[0053] X(t+1)=|X * (t)-X(t)|·e bl ·cos(2πl)+X * (t)

[0054] Where X(t+1) is the position vector of the whale individual at the t+1th iteration, X(t) is the position vector of the whale individual at the tth iteration, and X * (t) is the position vector of the optimal whale individual obtained by evaluating the fitness function after the tth iteration of the whale population, e represents the exponential function with e as the base, b is the spiral shape parameter, and l is a control parameter with a random value in the range of [-1, 1];

[0055] (3) Prey search strategy: All whale individuals fully search in the solution space, that is, each whale individual randomly swims towards other whale individuals. At this time, the position of each whale individual is updated by the following expression:

[0056] X(t+1)=X rand (t)-A·|C·X rand (t)-X(t)|

[0057] A=2a×r1-a,C=2×r2

[0058] Where X(t+1) is the position vector of the whale individual at the t+1th iteration, X(t) is the position vector of the whale individual at the tth iteration, and X rand (t) is the position vector of other whales swimming randomly, A and C are coefficient vectors, a is an adjustable coefficient, and its value decreases linearly from 2 to 0 during the iteration process. r1 and r2 are control parameters with random values ​​in the range [0,1].

[0059] Please refer to Figure 1 , Figure 1 This is a flow chart of a control method for a proton exchange membrane fuel cell thermal management system provided by an embodiment of the present invention. The proton exchange membrane fuel cell thermal management system includes a fuel cell stack and a heat dissipation component provided at the fuel cell stack. The method includes the following steps:

[0060] Step S110, obtaining relevant temperature parameter values ​​of the fuel cell stack;

[0061] The relevant temperature parameter values ​​include the current temperature difference error and the current temperature difference error change rate of the inlet and outlet cooling water of the stack, and the current temperature error and the current temperature error change rate of the outlet cooling water of the stack;

[0062] Step S120: obtaining a PEMFC system simulation model constructed based on the proton exchange membrane fuel cell thermal management system and a controller model for the heat dissipation component;

[0063] Step S130: Optimizing all adjustable parameters included in the controller model using a whale optimization algorithm according to the relevant temperature parameter values ​​and the PEMFC system simulation model;

[0064] Step S140: Using the optimized controller model to process the relevant temperature parameter values ​​to obtain an optimal control signal, and then adjusting the current operating state of the heat dissipation component according to the optimal control signal.

[0065] In some embodiments, the process of obtaining the relevant temperature parameter values ​​mentioned in step S110 is described as follows:

[0066] (1) collecting the current temperature of the cooling water at the outlet and the current temperature of the cooling water at the inlet of the stack at the current moment, preferably by respectively setting temperature sensors at the location where the cooling water at the outlet and the inlet of the stack flows;

[0067] (2) Obtain the preset outlet cooling water target temperature and the outlet cooling water historical temperature error calculated at the previous moment, subtract the outlet cooling water target temperature from the outlet cooling water current temperature, and obtain the outlet cooling water current temperature error and record it as e out (t); Subtract the current temperature error of the outlet cooling water from the historical temperature error of the outlet cooling water and divide it by the corresponding acquisition time interval between the two to obtain the current temperature error change rate and record it as

[0068] (3) Obtain the preset inlet and outlet cooling water target temperature difference and the inlet and outlet cooling water historical temperature difference error calculated at the previous moment, subtract the current outlet cooling water temperature from the current inlet cooling water temperature to obtain the current inlet and outlet cooling water temperature difference; subtract the inlet and outlet cooling water target temperature difference from the current inlet and outlet cooling water temperature difference to obtain the current inlet and outlet cooling water temperature difference error and record it as e Δ (t); Subtract the current temperature difference error of the inlet and outlet cooling water from the historical temperature difference error of the inlet and outlet cooling water and divide it by the acquisition time interval to obtain the current temperature difference error change rate and record it as

[0069] In practical applications, it is preferred to set the outlet cooling water temperature of the fuel cell stack to be maintained within the range of 75±5°C, and the inlet and outlet cooling water temperature difference of the fuel cell stack to be maintained within 10°C, that is, the outlet cooling water target temperature is preferably set to 75°C, and the inlet and outlet cooling water target temperature difference is preferably set to 10°C.

[0070] In some embodiments, see Figure 2 As shown, the controller model of the heat dissipation component mentioned in the above step S120 is explained as follows:

[0071] The heat dissipation component includes a cooling water pump and a radiator, the controller model includes a first PID controller, a second PID controller, a first signal synthesizer, a first fuzzy controller, a second fuzzy controller and a second signal synthesizer, the first signal synthesizer includes two multipliers and an adder, and the second signal synthesizer also includes two multipliers and an adder; and two adjustable weight parameters are introduced into the first signal synthesizer and are respectively recorded as k1 and k2, and two adjustable weight parameters are introduced into the second signal synthesizer and are respectively recorded as k3 and k4;

[0072] The input of the first PID controller is set to the outlet cooling water temperature error e of the stack out The output of the first PID controller is set to the first control signal u1; the input of the second PID controller is set to the inlet and outlet cooling water temperature difference error e of the stack. Δ , the output of the second PID controller is set to the second control signal u2; the first control signal u1 and the second control signal u2 are weighted and summed by the first signal synthesizer, that is, the first control signal u1 is multiplied by the weight parameter k1, and the second control signal u2 is multiplied by the weight parameter k2, and then the two multiplication results are added to obtain the speed control signal u of the radiator r ;

[0073] The two inputs of the first fuzzy controller are respectively set as the outlet cooling water temperature error e of the stack out and temperature error rate of change The single output of the first fuzzy controller is set as the third control signal u3; the two inputs of the second fuzzy controller are respectively set as the inlet and outlet cooling water temperature difference error e of the stack. Δ and temperature difference error change rate The single output of the second fuzzy controller is set as the fourth control signal u4; the third control signal u3 and the fourth control signal u4 are weighted and summed by the second signal synthesizer, that is, the third control signal u3 is multiplied by the weight parameter k3, and the fourth control signal u4 is multiplied by the weight parameter k4, and then the two multiplication results are added to obtain the speed control signal u of the cooling water pump. p .

[0074] More specifically, the first fuzzy controller is set to have an error in the outlet cooling water temperature e out and temperature error rate of change The input fuzzy domain is [-12, 12], and the output fuzzy domain of the third control signal u3 is set to [0, 12], and the corresponding output physical domain is [0, 5000 rpm], where 5000 rpm is the rated speed of the cooling water pump;

[0075] Regarding the outlet cooling water temperature error e out The input fuzzy domain is divided into seven input fuzzy subsets and recorded in order as {NB i1 ,NM i1 ,NS i1 ,ZO i1 ,PS i1 ,PM i1 ,PB i1}, input fuzzy subset NB i1 The membership function adopts the Z-shaped membership function, and the input fuzzy subset PB i1 The membership function of the fuzzy subsets {NM i1 ,NS i1 ,ZO i1 ,PS i1 ,PM i1 The five membership functions corresponding to} all use triangular membership functions, see Figure 3 (a)

[0076] Regarding the temperature error change rate The input fuzzy domain is divided into seven input fuzzy subsets and recorded in order as {NB i2 ,NM i2 ,NS i2 ,ZO i2 ,PS i2 ,PM i2 ,PB i2}, input fuzzy subset NB i2 The membership function adopts the Z-shaped membership function, and the input fuzzy subset PB i2 The membership function of the fuzzy subsets {NM i2 ,NS i2 ,ZO i2 ,PS i2 ,PM i2 The five membership functions corresponding to} all use triangular membership functions, see Figure 3 (b)

[0077] For the output fuzzy domain of the third control signal u3, seven output fuzzy subsets are divided and recorded in order as {NB o1 ,NM o1 ,NS o1,ZO o1 ,PS o1 ,PM o1 ,PB o1}, output fuzzy subset NB o1 The membership function adopts Z-shaped membership function and outputs fuzzy subset PB o1 The membership function of the sigmoid membership function is adopted, and the other five output fuzzy subsets {NM o1 ,NS o1 ,ZO o1 ,PS o1 ,PM o1 The five membership functions corresponding to} all use triangular membership functions, see Figure 3 (c)

[0078] On this basis, the fuzzy control rule table that the first fuzzy controller relies on is designed using an if-then model, which is recorded as the first fuzzy control rule table, as shown in Table 1.

[0079] Table 1 The first fuzzy control rule table

[0080]

[0081]

[0082] More specifically, the second fuzzy controller is set to have an error in the inlet and outlet cooling water temperature difference e Δ and temperature difference error change rate The input fuzzy domain is [-10, 10], and the output fuzzy domain of the fourth control signal u4 is set to [0, 12], and the corresponding output physical domain is [0, 5000 rpm], where 5000 rpm is the rated speed of the cooling water pump;

[0083] Regarding the inlet and outlet cooling water temperature difference error e Δ The input fuzzy domain is divided into seven input fuzzy subsets and recorded in order as {NB i3 ,NM i3 ,NS i3 ,ZO i3 ,PS i3 ,PM i3 ,PB i3}, input fuzzy subset NB i3 The membership function adopts the Z-shaped membership function, and the input fuzzy subset PB i3 The membership function of the fuzzy subsets {NM i3 ,NS i3 ,ZO i3 ,PS i3,PM i3 The five membership functions corresponding to} all use triangular membership functions, see Figure 4 (a)

[0084] Regarding the temperature difference error change rate The input fuzzy domain is divided into seven input fuzzy subsets and recorded in order as {NB i4 ,NM i4 ,NS i4 ,ZO i4 ,PS i4 ,PM i4 ,PB i4}, input fuzzy subset NB i4 The membership function adopts the Z-shaped membership function, and the input fuzzy subset PB i4 The membership function of the fuzzy subsets {NM i4 ,NS i4 ,ZO i4 ,PS i4 ,PM i4 The five membership functions corresponding to} all use triangular membership functions, see Figure 4 (b)

[0085] For the output fuzzy domain of the fourth control signal u4, seven output fuzzy subsets are divided and recorded in order as {NB o2 ,NM o2 ,NS o2 ,ZO o2 ,PS o2 ,PM o2 ,PB o2}, output fuzzy subset NB o2 The membership function adopts Z-shaped membership function and outputs fuzzy subset PB o2 The membership function of the sigmoid membership function is adopted, and the other five output fuzzy subsets {NM o2 ,NS o2 ,ZO o2 ,PS o2 ,PM o2 The five membership functions corresponding to} all use triangular membership functions, see Figure 4 (c)

[0086] On this basis, the fuzzy control rule table that the second fuzzy controller relies on is designed using the if-then model, which is recorded as the second fuzzy control rule table, as shown in Table 2.

[0087] Table 2 Second fuzzy control rules table

[0088]

[0089]

[0090] It should be noted that in Tables 1 and 2, NB refers to negative large, NM refers to negative medium, NS refers to negative small, ZO refers to zero, PS refers to positive small, PM refers to positive medium, and PB refers to positive large.

[0091] In some embodiments, the PEMFC system simulation model mentioned in the above step S120 includes at least a vehicle PEMFC stack model and a thermal management system model consisting of a radiator model and a cooling water pump model, and is preferably built using a Simulink / Simscape platform.

[0092] In some embodiments, the implementation process of step S130 includes but is not limited to the following:

[0093] Step S131: determining a multi-dimensional target variable based on all weight parameters contained in each signal synthesizer and all morphological control parameters associated with all key output membership functions contained in each fuzzy controller;

[0094] Step S132: Considering the response state of the PEMFC system simulation model, determine the fitness function as follows:

[0095]

[0096] Where Z is the fitness function. After the controller model after the parameter update is used to analyze the relevant temperature parameter values ​​to obtain the current control signal, T st.out is the cooling water temperature at the stack outlet obtained after the PEMFC system simulation model responds to the current control signal, T ref is the preset target temperature of the cooling water at the stack outlet, ΔT is the temperature difference between the stack inlet and outlet cooling water obtained after the PEMFC system simulation model responds to the current control signal, and ΔT ref The preset target temperature difference of the cooling water at the inlet and outlet of the stack;

[0097] Step S133: Based on the controller model, the fitness function and the relevant temperature parameter value, the target variable is iteratively optimized by the whale optimization algorithm to obtain the optimal target variable value;

[0098] Step S134: Based on the optimal target variable value, all adjustable parameters contained in the controller model are updated to obtain an optimized controller model.

[0099] In some embodiments, all morphological control parameters associated with all key output membership functions contained in each fuzzy controller mentioned in step S131 are described as follows:

[0100] It is known that each fuzzy controller contains {NB ox ,NM ox ,NS ox ,ZO ox ,PS ox ,PM ox ,PB ox}These seven output fuzzy subsets will be arranged in the middle of the five output fuzzy subsets {NM ox ,NS ox ,ZO ox ,PS ox ,PM ox} is defined as five key output fuzzy subsets, and the membership function of each key output fuzzy subset is defined as the key output membership function;

[0101] For each fuzzy controller, there are three key output fuzzy subsets arranged in sequence, such as {NM ox ,NS ox ,ZO ox}、{NS ox ,ZO ox ,PS ox} and {ZO ox ,PS ox ,PM ox}, defining the membership function of the key output fuzzy subset arranged on the left as a first membership function, defining the membership function of the key output fuzzy subset arranged in the middle as a second membership function, and defining the membership function of the key output fuzzy subset arranged on the right as a third membership function, and setting the middle peak point of the second membership function, the right foot point of the first membership function, and the left foot point of the third membership function to always maintain the same horizontal coordinate;

[0102] Set output fuzzy subset NS ox The membership function has the left foot point and the output fuzzy subset NM ox The membership function has intermediate peaks with equal horizontal coordinates.

[0103] Set the output fuzzy subset PM ox The membership function has an intermediate peak point and the output fuzzy subset PS ox The membership function of has the right foot points that always keep the horizontal coordinates equal;

[0104] The horizontal coordinates of the intermediate peak points of all key output membership functions contained in each fuzzy controller are defined as all morphological control parameters associated with all key output membership functions.

[0105] More specifically, the target variable mentioned in step S131 is described as follows:

[0106] In the first fuzzy controller, see Figure 3 As shown in (c), set the output fuzzy subset NM o1 The membership function has an intermediate peak point and the output fuzzy subset NS o1 The membership function has the left foot points always keep the horizontal coordinates equal, set the output fuzzy subset NS o1 The membership function has an intermediate peak point and output fuzzy subset NM o1 The membership function has the right foot point and the output fuzzy subset ZO o1 The membership function has the left foot points always keep the horizontal coordinates equal, set the output fuzzy subset ZO o1 The membership function has an intermediate peak point and output fuzzy subset NS o1 The membership function has the right foot point and the output fuzzy subset PS o1 The membership function has the left foot points always keep the horizontal coordinates equal, set the output fuzzy subset PS o1 The membership function has an intermediate peak point and output fuzzy subset ZO o1 The membership function has the right foot point and the output fuzzy subset PM o1 The membership function has the left foot points always keep the horizontal coordinates equal, set the output fuzzy subset PM o1 The membership function has an intermediate peak point and the output fuzzy subset PS o1 The right foot points of the membership function of the first fuzzy controller always keep the same horizontal coordinates, and the horizontal coordinates {p1, p2, p3, p4, p5} of the middle peak points of all key output membership functions contained in the first fuzzy controller are defined as all morphological control parameters contained in the first fuzzy controller;

[0107] In the second fuzzy controller, see Figure 4 As shown in (c), set the output fuzzy subset NM o2 The membership function has an intermediate peak point and the output fuzzy subset NS o2 The membership function has the left foot points always keep the horizontal coordinates equal, set the output fuzzy subset NS o2 The membership function has an intermediate peak point and output fuzzy subset NM o2The membership function has the right foot point and the output fuzzy subset ZO o2 The membership function has the left foot points always keep the horizontal coordinates equal, set the output fuzzy subset ZO o2 The membership function has an intermediate peak point and output fuzzy subset NS o2 The membership function has the right foot point and the output fuzzy subset PS o2 The membership function has the left foot points always keep the horizontal coordinates equal, set the output fuzzy subset PS o2 The membership function has an intermediate peak point and output fuzzy subset ZO o2 The membership function has the right foot point and the output fuzzy subset PM o2 The membership function has the left foot points always keep the horizontal coordinates equal, set the output fuzzy subset PM o2 The membership function has an intermediate peak point and the output fuzzy subset PS o2 The right foot points of the membership function always keep the horizontal coordinates equal, and the horizontal coordinates of the middle peak points of all key output membership functions contained in the second fuzzy controller {p6,p7,p8,p9,p 10} is defined as all morphological control parameters contained in the second fuzzy controller;

[0108] On this basis, combined with the two weight parameters {k1, k2} contained in the first signal synthesizer and the two weight parameters {k3, k4} contained in the second signal synthesizer, it is determined that the target variables to be applied to the whale optimization algorithm are {p1, p2, p3, p4, p5, p6, p7, p8, p9, p 10 ,k1,k2,k3,k4}.

[0109] It should be noted that the purpose of setting the horizontal coordinates of multiple points to be equal is to avoid discontinuities or jumps at the intersections of the membership functions of adjacent triangles before and after each fuzzy controller optimization. Figure 3 (c) and Figure 5 The comparison results and Figure 4 (c) and Figure 6 The comparison results show that the smooth transition effect can reduce the oscillation of the output control amount, which helps the system provide more delicate control decisions.

[0110] In some embodiments, the implementation process of step S133 includes but is not limited to the following:

[0111] Step S133.1: Set the basic parameters required for the whale optimization algorithm, including the number of individuals N in the whale population, the maximum number of iterations T, and the number of iterations N. max and the helical shape parameter b;

[0112] Step S133.2: Initialize the whale population so that the initial position vectors of different whale individuals refer to different initial target variable values;

[0113] Step S133.3: In the tth iteration, randomly assign values ​​to the control parameters r1, r2, and l, and randomly generate a predation mechanism probability p in the range [0, 1]. Use a linear relationship to assign values ​​to the adjustable coefficient a, and then calculate the specific values ​​of the coefficient vectors A and C.

[0114] Step S133.4: Determine whether p ≥ 0.5. If so, select the bubble attack strategy to update the current position vector of each individual whale. If not, execute step S133.5.

[0115] Step S133.5: Determine whether |A|≥1 holds true; if so, select the prey search strategy to update the current position vector of each individual whale; if not, select the prey surround strategy to update the current position vector of each individual whale;

[0116] Step S133.6: Calculate the current fitness value of each whale individual, and then obtain the whale individual with the largest current fitness value and define it as the undetermined optimal whale individual;

[0117] Step S133.7: Compare the undetermined optimal whale individual with the historical optimal whale individual, and define the optimal whale individual with the larger fitness value as the current optimal whale individual determined in the tth iteration;

[0118] It should be noted that when t=1, the historical best whale individual refers to the current best whale individual determined after calculating the fitness value of the initialized whale population; when t>1, the historical best whale individual refers to the current best whale individual determined in the t-1th iteration;

[0119] Step S133.8: Determine t <T max Is it true? If so, assign t+1 to t and return to execute the above step S133.3; if not, output the value in the Tth max The optimal target variable value referred to by the position vector of the current optimal whale individual determined in the iteration.

[0120] As an optional implementation, considering that selecting an overly large fuzzy domain may cause the fuzzy control rules to become too broad and unable to accurately describe the system state and control behavior (that is, the control effect may decrease), before executing the above step S130, the following operation can be preferentially performed: based on the relevant temperature parameter value, all scaling factors associated with all input fuzzy domains contained in each fuzzy controller are determined, and then the associated input fuzzy domain is adjusted by each scaling factor.

[0121] More specifically, for each input fuzzy domain contained within each fuzzy controller, the temperature parameter value directly associated with the input fuzzy domain is first extracted from the relevant temperature parameter values. Then, the scaling factor associated with the input fuzzy domain is calculated based on the width of the input fuzzy domain and a preset scaling exponent. Finally, the scaling factor is multiplied by the input fuzzy domain to complete the adjustment of the input fuzzy domain. The calculation formula for the scaling factor is as follows:

[0122]

[0123] In the formula, α(x) is the scaling factor associated with the input fuzzy domain, x is the representation result of converting the temperature parameter value to the input fuzzy domain, γ is a preset proportional exponent and is preferably set to 0.12, and M is half the width of the input fuzzy domain; in actual application, when x is directly related to the current temperature error of the outlet cooling water or the rate of change of the current temperature error, M is set to 12; when x is directly related to the current temperature difference error of the inlet and outlet cooling water or the rate of change of the current temperature difference error, M is set to 10.

[0124] It should be noted that after adjusting the input fuzzy domain, the fuzzy controller will adaptively adjust the division of relevant fuzzy subsets without changing the number of relevant fuzzy subsets and fuzzy control rules contained therein, thereby reducing the adverse effects of external environmental disturbances on the system and improving the control accuracy of the fuzzy controller.

[0125] In some embodiments, the specific implementation of step S140 is described as follows:

[0126] Inputting the current outlet cooling water temperature error into the first PID controller for analysis to obtain an optimal first control signal, inputting the current inlet and outlet cooling water temperature difference error into the second PID controller for analysis to obtain an optimal second control signal, inputting the optimal first control signal and the optimal second control signal into the optimized first signal synthesizer for weighted summation to obtain an optimal speed control signal for the radiator, recorded as a first optimal speed control signal;

[0127] The current outlet cooling water temperature error and the current temperature error change rate are input into the optimized first fuzzy controller for analysis to obtain an optimal third control signal, the current inlet and outlet cooling water temperature difference error and the current temperature difference error change rate are input into the optimized second fuzzy controller for analysis to obtain an optimal fourth control signal, the optimal third control signal and the optimal fourth control signal are input into the optimized second signal synthesizer for weighted summation to obtain an optimal speed control signal for the cooling water pump, recorded as a second optimal speed control signal;

[0128] The first optimal speed control signal is used to adjust the current speed of the radiator, and the second optimal speed control signal is used to adjust the current speed of the cooling water pump.

[0129] In an embodiment of the present invention, a controller model integrating PID control principle and fuzzy control principle is used to analyze two important influencing factors, the cooling water temperature at the outlet of the stack and the temperature difference between the cooling water at the inlet and outlet of the stack, in real time to generate relevant control signals for the heat dissipation component. At the same time, a weight parameter is introduced to limit the relevant control signal. On the basis of ensuring that the heat dissipation component always operates within the normal range, the proton exchange membrane fuel cell can be effectively controlled to operate efficiently and stably within a safe temperature range. By introducing the whale optimization algorithm, the morphological control parameters corresponding to the relevant membership functions contained in the fuzzy controller and the weight parameters contained in the signal synthesizer are optimized, thereby solving the problem that the existing fuzzy control principle is too dependent on expert experience and practical accumulation, and the input fuzzy domain contained in the fuzzy controller is adaptively adjusted, which can reduce the impact of external disturbances on the system, thereby improving the adaptability of the controller model, control accuracy and system robustness, accelerating the error convergence speed, and reducing the malfunction of the heat dissipation component.

[0130] In addition, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the control method of a proton exchange membrane fuel cell thermal management system in the above-mentioned embodiment is implemented. The computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. In other words, a storage device includes any medium that stores or transmits information in a readable form by a device (such as a computer, mobile phone, etc.), and can be a read-only memory, a disk, or an optical disk.

[0131] also, Figure 7 2 is a schematic diagram of the hardware structure of a computer device provided in an embodiment of the present invention, wherein the computer device includes a processor 220, a memory 230, an input unit 240, a display unit 250 and other components. It can be understood by those skilled in the art that Figure 7 The device structure components shown do not constitute a limitation on all devices, and may include more or fewer components than shown, or combine certain components. The memory 230 can be used to store the computer program 210 and various functional modules, and the processor 220 runs the computer program 210 stored in the memory 230, thereby executing various functional applications and data processing of the device. The memory can be an internal memory or an external memory, or include an internal memory and an external memory. The internal memory may include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory or a random access memory. The external memory may include a hard disk, a floppy disk, a USB flash drive, a magnetic tape, etc. The memory 230 disclosed in the embodiment of the present invention includes but is not limited to the above-mentioned types of memory. The memory 230 disclosed in the embodiment of the present invention is only an example and not a limitation.

[0132] The input unit 240 is used to receive input signals and keywords entered by the user. The input unit 240 may include a touch panel and other input devices. The touch panel can detect user touch operations on or near it (e.g., operations performed by a user using a finger, stylus, or any other suitable object or accessory on or near the touch panel) and drive corresponding connected devices according to pre-set programs. Other input devices may include, but are not limited to, one or more of a physical keyboard, function keys (e.g., playback control keys, on / off keys, etc.), a trackball, a mouse, a joystick, etc. The display unit 250 can be used to display information entered by the user or provided to the user, as well as various menus of the terminal device. The display unit 250 may take the form of a liquid crystal display, an organic light-emitting diode, etc. The processor 220 is the control center of the terminal device, connecting various components of the entire device using various interfaces and circuits. It performs various functions and processes data by running or executing software programs and / or modules stored in the memory 230 and accessing data stored in the memory 230.

[0133] As an embodiment, the computer device includes a processor 220, a memory 230 and a computer program 210, wherein the computer program 210 is stored in the memory 230 and is configured to be executed by the processor 220, and the computer program 210 is configured to execute a control method of a proton exchange membrane fuel cell thermal management system in the above embodiment.

[0134] Although the description of the present application has been quite detailed and specifically describes several embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be considered to provide a broad possible interpretation of these claims by reference to the appended claims, taking into account the prior art, so as to effectively cover the intended scope of the present application. In addition, the above description of the present application is based on the embodiments foreseen by the inventors, which is intended to provide a useful description, and those non-substantial changes to the present application that have not yet been foreseen may still represent equivalent changes to the present application.

Claims

1. A control method for a proton exchange membrane fuel cell thermal management system, wherein the proton exchange membrane fuel cell thermal management system includes a fuel cell stack and a heat dissipation component, characterized in that: The method comprises: Obtaining relevant temperature parameter values ​​of the fuel cell stack, including a current temperature error and a current temperature error change rate of the fuel cell stack's outlet cooling water, and a current temperature difference error and a current temperature difference error change rate of the fuel cell stack's inlet and outlet cooling water; Obtaining a PEMFC system simulation model constructed based on the proton exchange membrane fuel cell thermal management system and a controller model for the heat dissipation component; Optimizing all adjustable parameters included in the controller model using a whale optimization algorithm according to the relevant temperature parameter values ​​and the PEMFC system simulation model; Using the optimized controller model to process the relevant temperature parameter values ​​to obtain an optimal control signal, and then adjusting the current operating state of the heat dissipation component according to the optimal control signal; The heat dissipation component includes a cooling water pump, and the controller model includes a first fuzzy controller, a second fuzzy controller, and a second signal synthesizer; the first fuzzy controller receives as input the outlet cooling water temperature error and the temperature error change rate of the fuel cell stack, and outputs a third control signal; the second fuzzy controller receives as input the inlet and outlet cooling water temperature difference error and the temperature difference error change rate of the fuel cell stack, and outputs a fourth control signal; the second signal synthesizer is used to perform weighted summation on the third control signal and the fourth control signal to obtain a speed control signal for the cooling water pump; Before optimizing all adjustable parameters included in the controller model using the whale optimization algorithm according to the relevant temperature parameter values ​​and the PEMFC system simulation model, the method includes: According to the relevant temperature parameter value, all scaling factors associated with all input fuzzy domains contained in each fuzzy controller are determined, and then each scaling factor is used to adjust the associated input fuzzy domain.

2. The control method of the proton exchange membrane fuel cell thermal management system according to claim 1, characterized in that: The heat dissipation component further includes a radiator, and the controller model further includes a first PID controller, a second PID controller and a first signal synthesizer; The input of the first PID controller is the outlet cooling water temperature error of the fuel cell stack, and the output is a first control signal; the input of the second PID controller is the inlet and outlet cooling water temperature difference error of the fuel cell stack, and the output is a second control signal; the first signal synthesizer is used to perform weighted summation on the first control signal and the second control signal to obtain the speed control signal of the radiator.

3. The control method of the proton exchange membrane fuel cell thermal management system according to claim 2, characterized in that: The optimizing of all adjustable parameters included in the controller model using the whale optimization algorithm according to the relevant temperature parameter values ​​and the PEMFC system simulation model includes: Determine the multi-dimensional target variable according to all morphological control parameters corresponding to all key output membership functions contained in each fuzzy controller and all weight parameters contained in each signal synthesizer; determining a fitness function related to a response state of the PEMFC system simulation model; Iteratively optimizing the target variable using a whale optimization algorithm according to the relevant temperature parameter value, the fitness function, and the controller model to obtain an optimal target variable value; According to the optimal target variable value, all adjustable parameters included in the controller model are updated to obtain an optimized controller model.

4. The control method of the proton exchange membrane fuel cell thermal management system according to claim 3, characterized in that: Each fuzzy controller contains seven output fuzzy subsets, which are denoted in order: , the five output fuzzy subsets arranged in the middle are recorded as the five key output fuzzy subsets, and the membership function of each key output fuzzy subset is the key output membership function.

5. The control method of the proton exchange membrane fuel cell thermal management system according to claim 4, characterized in that: Each key output membership function is a triangular membership function, and all morphological control parameters corresponding to all key output membership functions contained in each fuzzy controller are determined by the following method: For the three key output fuzzy subsets included in each fuzzy controller that are arranged in sequence and continuously, the membership function of the key output fuzzy subset arranged on the left is recorded as the first membership function, the membership function of the key output fuzzy subset arranged in the middle is recorded as the second membership function, and the membership function of the key output fuzzy subset arranged on the right is recorded as the third membership function, and the right foot point of the first membership function, the middle peak point of the second membership function, and the left foot point of the third membership function are set to keep the horizontal coordinates equal; Set output fuzzy subsets The intermediate peak point of the membership function and the output fuzzy subset The left foot of the membership function keeps the horizontal coordinates equal, and sets the output fuzzy subset The right foot point of the membership function and the output fuzzy subset The middle peak point of the membership function keeps the horizontal coordinates equal; The horizontal coordinates of the middle peak points of all key output membership functions contained in each fuzzy controller are used as all morphological control parameters corresponding to all key output membership functions.

6. The control method of the proton exchange membrane fuel cell thermal management system according to claim 3, characterized in that: The fitness function adopts the following expression: in, is the fitness function, and when the current control signal is obtained by processing the relevant temperature parameter value using the currently updated controller model, is the cooling water temperature at the stack outlet obtained after the PEMFC system simulation model responds to the current control signal, is the target temperature of cooling water at the stack outlet, is the cooling water temperature difference at the inlet and outlet of the stack obtained after the PEMFC system simulation model responds to the current control signal, The target temperature difference of the cooling water at the inlet and outlet of the stack.

7. The control method of a proton exchange membrane fuel cell thermal management system according to claim 1, characterized in that: Determining all scaling factors associated with all input fuzzy domains included in each fuzzy controller according to the relevant temperature parameter value includes: For each input fuzzy domain included in each fuzzy controller, a temperature parameter value associated with the input fuzzy domain is obtained from the relevant temperature parameter value, and then a scaling factor associated with the input fuzzy domain is determined by combining a preset scaling index and a width of the input fuzzy domain.

8. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: The processor executes the computer program to implement the control method of the proton exchange membrane fuel cell thermal management system according to any one of claims 1 to 7.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the control method of the proton exchange membrane fuel cell thermal management system according to any one of claims 1 to 7 is implemented.

Images