CN115084598A - Thermal management method of fuel cell - Google Patents
Thermal management method of fuel cell Download PDFInfo
- Publication number
- CN115084598A CN115084598A CN202210509539.4A CN202210509539A CN115084598A CN 115084598 A CN115084598 A CN 115084598A CN 202210509539 A CN202210509539 A CN 202210509539A CN 115084598 A CN115084598 A CN 115084598A
- Authority
- CN
- China
- Prior art keywords
- fuzzy
- fuzzy controller
- inlet
- particle
- outlet
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04992—Processes for controlling fuel cells or fuel cell systems characterised by the implementation of mathematical or computational algorithms, e.g. feedback control loops, fuzzy logic, neural networks or artificial intelligence
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04007—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids related to heat exchange
- H01M8/04014—Heat exchange using gaseous fluids; Heat exchange by combustion of reactants
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04007—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids related to heat exchange
- H01M8/04029—Heat exchange using liquids
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04313—Processes for controlling fuel cells or fuel cell systems characterised by the detection or assessment of variables; characterised by the detection or assessment of failure or abnormal function
- H01M8/0432—Temperature; Ambient temperature
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04694—Processes for controlling fuel cells or fuel cell systems characterised by variables to be controlled
- H01M8/04746—Pressure; Flow
- H01M8/04768—Pressure; Flow of the coolant
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04694—Processes for controlling fuel cells or fuel cell systems characterised by variables to be controlled
- H01M8/04828—Humidity; Water content
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M8/00—Fuel cells; Manufacture thereof
- H01M8/04—Auxiliary arrangements, e.g. for control of pressure or for circulation of fluids
- H01M8/04298—Processes for controlling fuel cells or fuel cell systems
- H01M8/04694—Processes for controlling fuel cells or fuel cell systems characterised by variables to be controlled
- H01M8/04858—Electric variables
- H01M8/04925—Power, energy, capacity or load
- H01M8/04947—Power, energy, capacity or load of auxiliary devices, e.g. batteries, capacitors
-
- H—ELECTRICITY
- H01—ELECTRIC ELEMENTS
- H01M—PROCESSES OR MEANS, e.g. BATTERIES, FOR THE DIRECT CONVERSION OF CHEMICAL ENERGY INTO ELECTRICAL ENERGY
- H01M2250/00—Fuel cells for particular applications; Specific features of fuel cell system
- H01M2250/20—Fuel cells in motive systems, e.g. vehicle, ship, plane
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E60/00—Enabling technologies; Technologies with a potential or indirect contribution to GHG emissions mitigation
- Y02E60/30—Hydrogen technology
- Y02E60/50—Fuel cells
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Manufacturing & Machinery (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- General Chemical & Material Sciences (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Automation & Control Theory (AREA)
- Computing Systems (AREA)
- Evolutionary Computation (AREA)
- Fuzzy Systems (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Combustion & Propulsion (AREA)
- Feedback Control In General (AREA)
Abstract
The invention discloses a thermal management method of a fuel cell. The method comprises the following steps: setting an outlet fuzzy controller and an inlet fuzzy controller aiming at a fuel cell thermal management system, wherein the fuel cell thermal management system comprises a water tank, a cooling water pump, a radiator and a galvanic pile, the outlet fuzzy controller takes the error and the error change rate of the current galvanic pile outlet temperature and the set target outlet temperature as input quantities, and takes cooling water flow as output quantities; the inlet fuzzy controller takes the error between the current temperature of the electric pile inlet and the set target inlet temperature and the change rate of the error as input quantity, and takes the fan rotating speed of the radiator as output quantity; determining membership functions, fuzzy domains and fuzzy rules of the outlet fuzzy controller and the inlet fuzzy controller; and carrying out parameterization processing on the membership function, and optimizing the membership function through a particle swarm and a genetic algorithm. The invention can accurately control the temperature in the fuel cell thermal management system.
Description
Technical Field
The invention relates to the technical field of fuel cell management, in particular to a thermal management method of a fuel cell.
Background
The hydrogen energy is secondary energy with rich source, green, low carbon and wide application, and has important significance for constructing a clean, low-carbon, safe and efficient energy system and realizing the carbon peak-to-peak carbon neutralization goal. With the rapid development of new energy automobiles, hydrogen fuel cell automobiles have attracted extensive attention with the advantages of high efficiency, cleanness and the like. Proton Exchange Membrane Fuel Cells (PEMFCs) have the advantages of high energy conversion efficiency, low-temperature operation, high reliability, zero emission, and the like, and have a wide application prospect in the field of automobiles. The PEMFC is a nonlinear complex system with multiple physical fields and multiple parameter coupling, the working temperature of the PEMFC is a key factor influencing the output performance and the service life, and liquid water can be evaporated due to overhigh working temperature to cause dry membrane failure; too low a temperature can cause flooding of the cathode channels and the failure of oxygen to pass through the gas diffusion layers. The normal working temperature range of the PEMFC is 60-80 ℃, but a large amount of heat is generated in the operation process of the PEMFC, so that the PEMFC needs to be effectively thermally managed. Improper thermal management can cause an irreversible drop in the PEMFC output voltage, accelerating its aging rate.
In the prior art, PEMFC thermal management can be divided into three ways, adjustment structure, phase change cooling, and optimal control, according to the principle. The internal structure of the fuel cell becomes complicated by changing the flow passage structure, the temperature control circulating cooling shell is added, and the volume of the fuel cell is increased. The phase change cooling uses a fluid that is expensive and not commercially viable, and both methods of application have drawbacks. At present, the PEMFC thermal management mainly controls the cooling water flow rate and the fan rotation speed on a temperature model, and the control methods include pi (projection integration) control, state feedback control, prediction control, and the like. The control methods have the advantages of simple principle and convenient use, but have the defects of slow response speed, long adjustment time and the like. Due to the inherent non-linear characteristic and parameter uncertainty of the fuel cell and the characteristic that the output performance and durability of the high-power fuel cell applied to a commercial vehicle are very sensitive to the temperature change of the electric pile, the application of the existing control method has certain difficulty. The fuzzy control has fast response speed and strong anti-interference capability, and is particularly suitable for the control of a hysteresis system. The learners design the fuzzy control method to be applied to the PEMFC thermal management, the temperature of the PEMFC is controlled by adjusting the rotating speed of the fan, and the comparison result with the control method shows that the fuzzy control has superiority. In addition, researchers consider overcoming the interference of external loads, and adopt a fuzzy controller with integral to adjust the flow of cooling water in real time, and the result shows that the method can quickly reach the target temperature under the condition of small fluctuation, controls the temperature of the PEMFC pile in a reasonable range, and has stronger robustness compared with the traditional similar model. The other existing scheme is that improved particle swarm optimization fuzzy PID control is utilized, a control strategy is set according to a control experience rule, and the method has the advantages of being strong in robustness, high in response speed and the like.
Through analysis, the existing fuzzy control design mainly depends on the experience of experts, most methods adopt a step load signal mode to verify fuzzy control, however, the hydrogen fuel cell automobile has acceleration, uniform speed, deceleration and other processes in actual running, frequent change of working conditions can make the temperature control of the fuel cell more complicated, extreme values may occur in temperature, the existing fuzzy logic has difficulty in controlling the temperature to a target value, and the fluctuation of the fuzzy logic is large at a control target temperature value.
Disclosure of Invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and to provide a method for thermal management of a fuel cell, the method comprising the steps of:
setting an outlet fuzzy controller and an inlet fuzzy controller aiming at a fuel cell thermal management system, wherein the fuel cell thermal management system comprises a water tank, a cooling water pump, a radiator and an electric pile, the outlet fuzzy controller takes the error and the error change rate of the current electric pile outlet temperature and the set target outlet temperature as input quantities, and takes cooling water flow as output quantities; the inlet fuzzy controller takes the error between the current temperature of the electric pile inlet and the set target inlet temperature and the change rate of the error as input quantity, and takes the fan rotating speed of the radiator as output quantity;
determining membership functions and fuzzy domains of the outlet fuzzy controller and the inlet fuzzy controller and setting fuzzy rules;
and carrying out parameterization processing on the membership function, taking a parameter to be optimized as a particle population, and optimizing the membership functions of the inlet fuzzy controller and the outlet fuzzy controller so as to control the current cooling water flow of the fuel cell thermal management system and the fan rotating speed of a radiator.
Compared with the prior art, the fuzzy controller has the advantages that the error between the inlet and outlet temperature of the electric pile and the target temperature value is smaller as the target, the membership function of the fuzzy controller is optimized through an algorithm with better overall performance by combining the characteristics of fuzzy control rules and membership function optimization, the optimized fuzzy controller has obvious improvement effect on stability and accuracy compared with a conventional fuzzy controller, and the defect that the particle swarm optimization algorithm is easy to fall into local optimization is overcome. Compared with the existing optimization algorithm, the method has better temperature regulation capability and smaller deviation with a set value, and can better resist the disturbance of an external load.
Other features of the present invention and advantages thereof will become apparent from the following detailed description of exemplary embodiments thereof, which proceeds with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description, serve to explain the principles of the invention.
FIG. 1 is a schematic diagram of a prior art fuel cell thermal management system;
fig. 2 is a flow chart of a method of thermal management of a fuel cell according to an embodiment of the invention;
FIG. 3 is a schematic diagram of a fuzzy control process according to one embodiment of the present invention;
FIG. 4 is a schematic diagram of a triangular membership function according to one embodiment of the present invention;
FIG. 5 is a schematic diagram of a particle swarm-genetic hybrid algorithm based optimization fuzzy controller according to one embodiment of the invention;
FIG. 6 is a flow chart of particle swarm-genetic hybrid algorithm optimization fuzzy control according to one embodiment of the present invention;
FIG. 7 is a schematic diagram of a chromosome crossing process according to one embodiment of the invention.
Detailed Description
Various exemplary embodiments of the present invention will now be described in detail with reference to the accompanying drawings. It should be noted that: the relative arrangement of the components and steps, the numerical expressions and numerical values set forth in these embodiments do not limit the scope of the present invention unless specifically stated otherwise.
The following description of at least one exemplary embodiment is merely illustrative in nature and is in no way intended to limit the invention, its application, or uses.
Techniques, methods, and apparatus known to those of ordinary skill in the relevant art may not be discussed in detail but are intended to be part of the specification where appropriate.
In all examples shown and discussed herein, any particular value should be construed as merely illustrative, and not limiting. Thus, other examples of the exemplary embodiments may have different values.
It should be noted that: like reference numbers and letters refer to like items in the following figures, and thus, once an item is defined in one figure, further discussion thereof is not required in subsequent figures.
For clarity, the PEMFC thermal management system will be described first, and referring to fig. 1, the system includes a water tank, a cooling water pump, a radiator, and a stack (i.e., a fuel cell stack) having temperature sensors at inlets and outlets of the stack, respectively. In the system, the generated heat is firstly brought to a water tank by a cooling water pump through controlling the flow of cooling water, then the heat is brought to a radiator, and the radiator discharges the heat to the air through controlling the air volume of the radiator. In the present invention, it is assumed that the temperature in the cooling water is uniform, and the stack outlet cooling water temperature is taken as the temperature at the stack outlet, and the outlet temperature of the radiator is taken as the inlet temperature of the stack.
Referring to fig. 2, a method of thermal management of a fuel cell is provided comprising the steps of:
and step S110, setting an outlet fuzzy controller and an inlet fuzzy controller by taking the galvanic pile as reference for the fuel cell thermal management system.
Aiming at the fuzzy logic design, two-dimensional fuzzy controllers are adopted to control the outlet and inlet temperatures of the galvanic pile. Setting an outlet target temperature T according to the selected electric pile tar.out Setting a target temperature T of the inlet of the cell stack tar.in And designing a fuzzy inference system by adopting a proper fuzzy control rule. After fuzzy inference, the defuzzification may employ a weighted average method.
Fuzzy control is essentially a non-linear control, which belongs to the field of intelligent control. In one embodiment, two-dimensional fuzzy controllers of the mandani type, respectively called an outlet fuzzy controller and an inlet fuzzy controller, are established for controlling the outlet temperature and the inlet temperature of the cell stack, and the fuzzy control overall framework is shown in fig. 3. Setting a target temperature T of the outlet of the electric pile aiming at the temperature control of the outlet of the electric pile tar.out Setting the current stack outlet temperature T st.out And target outlet temperature T tar.out The error and the error change rate of the electric pile are used as the input of an outlet fuzzy controller, the flow rate of cooling water is used as the output of the outlet fuzzy controller, and the heat generated by the electric pile is firstly brought to a water tank through the cooling water to reach the target temperature value of the electric pile outlet; after a part of the heat is dissipated, the residual heat reaches the radiator along with the cooling water. Setting a cell stack inlet target temperature T for cell stack inlet temperature control tar.in The current inlet temperature T of the electric pile is calculated st.in With a set target temperature T tar.in The error of (2) and the change rate of the temperature error are used as the input of an inlet fuzzy controller, and the air quantity of a radiator is used as the output of the fuzzy controllerAnd finally, the residual heat is dissipated to the environment to reach the target temperature value of the inlet of the electric pile.
And step S120, determining membership functions, fuzzy domains and fuzzy rules of the outlet fuzzy controller and the inlet fuzzy controller.
The fuzzy logic-based controller structure design relates to membership function, fuzzy domain selection, fuzzy rule formulation and the like. The membership function of the fuzzy controller has diversified forms, the selection of fuzzy domains is different, and the formulation of fuzzy rules is different according to the situation of control problems. In order to illustrate the basic principle of the control method of the present invention, in the following description, a triangular membership function is used, and the input and output quantities of a fuzzy controller are divided into 7 fuzzy subsets, and an if-then control rule is used as an example in the fuzzy controller for explanation. It should be understood that the concepts described are equally applicable to other types of membership functions or control rules.
1) Determination of membership functions
If there is a number A (x) e [0, 1] corresponding to any element x in the domain of interest U, A (x) is a function, called the membership function of A, when x varies among U. The closer the degree of membership A (x) is to 1, the higher the degree to which x belongs to A, and the closer to 0, A (x) the lower the degree to which x belongs to A. And (3) representing the degree of the X belonging to the A by using a membership function A (x) which takes a value in an interval [0, 1 ]. For example, a triangular membership function is chosen, expressed as:
the membership shape of the fuzzy subset depends on the abscissa a of the vertex of the triangular membership function and the abscissas b and c of the base, as shown in FIG. 4, the optimization of the fuzzy controller input and output linguistic variables, i.e. the parameter a characterizing the membership shape i ，b i ，c i (i represents a different fuzzy subset).
2) Determination of ambiguity domain
In the control of the stack outlet temperature, the input and output of the fuzzy control are divided into 7 fuzzy subsets, as shown in fig. 4, that is, NB (negative large), NM (negative medium), NS (negative small), ZO (zero), PS (positive small), PM (positive small), and PB (positive large). And designing a fuzzy domain of the temperature error of the outlet of the galvanic pile and the change rate of the temperature error and a fuzzy domain of the flow rate of the cooling water according to the temperature control target. Similarly, when designing the pile inlet temperature controller, the input and output of fuzzy control are divided into 7 fuzzy subsets, and the fuzzy domain of pile inlet temperature error and temperature error change rate and the fuzzy domain of radiator wind speed are designed.
3) Designing fuzzy rules
The fuzzy control rule is the core of the fuzzy controller and is part of a knowledge base in the fuzzy controller. Because the value ranges of the input and output variables are different, the basic domains are mapped to a standardized domain according to different corresponding relations. In one embodiment, standard discourse domains are equally discretized, and then fuzzy partitions are performed on the discourse domains to define fuzzy subsets. For example, if-then fuzzy control rules are adopted, fuzzy rules are respectively formulated for controlled variables:
......
wherein e represents an error value,
representing the rate of change of error and deltau representing the fuzzy controller output, see table 1. After fuzzy inference, the defuzzification may employ a weighted average method.
TABLE 1 fuzzy control rule example
And S130, optimizing membership functions of the outlet fuzzy controller and the inlet fuzzy controller by using a particle swarm and genetic hybrid algorithm to realize temperature control of the fuel cell thermal management system.
In one embodiment, the membership function of the fuzzy controller is optimized using a particle swarm-genetic hybrid algorithm, as shown in FIG. 5. When the fuzzy controller is optimized by adopting a particle swarm-genetic hybrid algorithm, parameterization is needed on input and output linguistic variables of a membership function, and finally, the optimal individuals in the final generation population are decoded by initializing all parameters, evaluating the fitness function, optimizing and updating the speed and the position of the particles and selecting, crossing and varying the individuals, and the like, so that the optimal solution for optimizing the membership function of the fuzzy controller is obtained. And inputting the optimal solution into a fuzzy controller, thereby improving the controller precision and enabling the temperature to be in a smaller fluctuation range.
Particle Swarm Optimization (PSO) is a random search algorithm based on Swarm cooperation developed by simulating the foraging behavior of a bird Swarm. Genetic Algorithm (GA) is an evolutionary Algorithm whose basic principle is to emulate the evolutionary rule of "race selection, survival of fittest" in the biological world. The particle swarm algorithm is simple in logic and high in convergence speed, but is easy to fall into local optimization; the genetic algorithm has strong global searching capability but slow searching speed, and the two algorithms have strong complementarity.
In the embodiment of the invention, the first stage of optimization is firstly carried out by utilizing the characteristic of high convergence speed of the particle swarm algorithm, so as to obtain the initial population with a certain degree of evolution. And then, optimizing the second stage by a genetic algorithm to finally obtain the optimal solution of the membership function, thereby improving the accuracy of the fuzzy controller. For simplicity, the control rules and initial states of membership function of the electric pile inlet fuzzy controller and the electric pile outlet fuzzy controller are set to be consistent, so that only the fuzzy controller for the electric pile outlet is introduced based on the particle swarm-genetic algorithm optimization process, but the optimization process is also applicable to the inlet fuzzy controller.
Referring to fig. 6, the overall process of optimizing the fuzzy controller by the particle swarm-genetic hybrid algorithm includes:
step S610, randomly generating a particle population.
For example, initializing each parameter in the objective function, randomly generating a particle population, completing real number encoding of the particles, and determining an adaptive value range of the particles.
Step S620, fitness evaluation is performed.
And (4) recording the optimal solution of the particles and the optimal solution found at present in the whole particle population through fitness function evaluation.
Step S630, the particle velocity and position are updated.
For example, the speed and position of the particle are updated according to the global optimal model loop optimization, and after the maximum iteration number is reached, an initial optimized population is output.
Step S640, performing genetic operations for the initial optimized population.
Specifically, the genetic manipulation process comprises:
in the initial optimized population, selecting individuals to be crossed according to the size of the fitness value, carrying out cross operation of a genetic algorithm according to the cross probability Pc, replacing and recombining partial structures of two parent individuals to generate a new individual;
with P m Carrying out mutation operation on the mutation probability to assist in generating new individuals to be added into the offspring population;
repeating the above genetic operations for new generation population until reaching maximum evolution generation G max Or other set termination conditions.
And step S650, when the iteration termination condition is met, the chromosome is decoded and the optimal parameters are output.
In the subsequent fuzzy control (FLC), the chromosomes are assigned to the central position and the width of the membership function, and the control system model is operated and the fitness is calculated so as to be fed back to the particle swarm algorithm to carry out fitness evaluation. The overall process of fuzzy control belongs to the prior art, and is not described in detail herein.
Specific examples of parameter initialization, fitness evaluation, updating the speed and location of particles, and genetic manipulation (including individual selection, crossing, and variation) involved in the above processes are described in detail below.
1) Initialization of parameters
Particle swarm optimization algorithms begin with randomly generated populations. Because the membership function needs to be optimized, the parameter to be optimized is determined first, and the membership function is encoded. For example, in fuzzy control, the input and output quantities are divided into 7 fuzzy subsets, and the total number of parameters to be optimized by the membership function is 17, as shown in fig. 4. To explain the initialization parameter process more intuitively, the shape of the membership function can be determined from 3 points, using real number encoding as an example, according to the number of parameters to be optimized for input and output: the abscissa a of the vertex, and the abscissas b and c of the base, which stipulates the width range of the triangle base interval, are sequentially coded as { x 1 ，x 2 ，x 3 ，x 4 ，...x 17 The center and width of the membership function can be parameterized, and the array { x } 1 ，x 2 ，...x 17 The initial particle population is obtained, and the adaptive value range is the value range [ b, d ] of the abscissa of the membership function]As in fig. 4.
2) Assessment of fitness
In the particle swarm optimization algorithm, a fitness function is a tool for producing an optimal solution, and the selection of the fitness function directly influences the convergence speed of the algorithm and whether the optimal solution can be found. The final objective of the embodiment of the invention is to adjust the width and the central position of the membership function, so that the temperature control is more accurate, the design of the fitness function is as simple as possible, and the calculation complexity is minimum. For example, the Time-Weighted Absolute Error (ITAE) performance index has the advantages of fast response speed, short adjustment Time and the like, and the ITAE performance index can be selected as a fitness function, and the optimal solution of the particle and the optimal solution found in the whole population at present are recorded by taking the minimized fitness function value as a standard. The concrete expression is as follows:
minF＝∫ 1 N t|T tar -T st |dt (2)
wherein N is the number of individuals in the population; t is time; t is tar Is the target temperature; t is st Is the current temperature of the electric pile.
3) Updating the speed and position of the particles themselves
The PSO is based on a group, so that all individuals in the group move to a region with a better position according to the change of the fitness of the environment. The PSO algorithm enables all the particles to fly at a certain speed in a search space, and all the particles dynamically adjust the flying speed according to information such as individual extremum and global extremum of the particles, so that the PSO algorithm is a parallel global random search algorithm. In the embodiment of the invention, the abscissa a of the vertex of the membership function and the abscissas b and c of the bottom edge form an array { x } 1 ，x 2 ，...x 17 And as the initialized particle population, the particle x according to the PSO algorithm i (i-1, 2.. m) at the k-th iteration, it updates the speed and position according to the global optimization model:
wherein v is id Is the flight velocity of particle i; x is the number of id Is the position of particle i; p is a radical of id Is the best position (p) experienced by the particle i best )；p gd Is the best position (g) experienced by all particles in the population best ) (ii) a Omega is an inertia weight and is responsible for adjusting the global search and local exploration capacity of the particle swarm; c. C 1 And c 2 Is the acceleration constant, indicating that the particle is pulled towards p best And g best A random value of (a); rand () is two results from 0, 1]Random numbers within a range. InitialTransformed particle population { x 1 ，x 2 ，…x 17 And obtaining an initial optimized population after multiple iterations.
4) Selection, crossing and variation of individuals
Genetic manipulation includes selection, crossover and variation of individuals. For the selection operation, the purpose of selection is to select good individuals from the current initial optimized population to have an opportunity to propagate descendants for the next generation as a parent, based on the high probability that the well-adapted individuals contribute one or more descendants for the next generation. For example, the roulette method is selected, and the roulette method determines the probability of selecting the individual according to the fitness of the individual, that is, the selection strategy based on the fitness proportion, and the probability of selecting the individual i is as follows:
wherein, F i 、F j Fitness values of the individual i and the individual j respectively; and N is the number of individuals in the population.
For crossover operations, for each individual, with a crossover probability P c Exchanging part of chromosomes among the individuals to obtain a new generation of individuals. The quality of the crossover operator directly influences the convergence speed of the genetic algorithm. Set of the abscissa a of the vertex of the membership function of the fuzzy controller and the abscissas b and c of the base { x } 1 ，x 2 ，x 3 ，x 4 …x 17 And fifthly, forming an initial optimized population, namely chromosomes, after the optimization of the particle swarm algorithm. The crossing operation adopts a real number crossing method, the alpha chromosome c α And the beta chromosome c β The method of crossing at ξ is:
wherein, P c For the cross probability, is [0, 1]]The random number of (2); c. C αξ 、c βξ Is a crossThe process of the manipulated chromosome is shown in FIG. 7.
For mutation operation, random numbers uniformly distributed in a certain range are used respectively to obtain mutation probability P m The original gene values of all loci in the individual coding strings are replaced, and the mutation is introduced to ensure that the genetic algorithm has local random searching capability. The particle swarm-genetic hybrid optimization algorithm is used for solving the abscissa a of the vertex of the membership function of the fuzzy controller and the abscissas b and c of the bottom edge, and when the optimal solution neighborhood is approached through a crossover operator, the convergence to the optimal solution can be accelerated by utilizing the local random search capability of a mutation operator.
When iteration is finished or no new change is generated in evolution, the maximum evolution algebra G is obtained max And proving that the fuzzy control membership function is optimized to be finished. Because the process of optimizing the fuzzy controller by the particle swarm-genetic hybrid algorithm is complex and online optimization is difficult to a certain extent, the existing research basically adopts an offline mode, namely, the ideal effect is obtained in a simulation system and then copied into the actual fuzzy controller. The embodiment of the invention also adopts the off-line optimization mode, the optimization result is input into the fuzzy controller after decoding, the effect of the optimized fuzzy controller and the unoptimized fuzzy controller on the temperature control of the inlet and the outlet of the fuel cell under the same working condition is compared, and the optimized fuzzy controller has higher temperature control precision compared with the unoptimized fuzzy controller.
In summary, in the particle swarm-genetic hybrid algorithm optimization, after parameterizing the fuzzy rule and the membership function, the first-stage optimization is performed by using the characteristic of high convergence speed of the particle swarm algorithm to obtain an initial population with a certain degree of evolution, then the second-stage optimization is performed by using the genetic algorithm to finally obtain the optimal solution of the membership function, and thus the accuracy of the fuzzy controller is improved.
In summary, the invention improves the accuracy of the fuel cell thermal management, and optimizes the center and the width of the membership function of the fuzzy controller by a particle swarm-genetic hybrid optimization algorithm aiming at smaller error between the outlet temperature and the target temperature value of the pile. The adopted fuzzy control has high response speed and is suitable for the control of a hysteresis system. The fuzzy controller optimized by the particle swarm-genetic hybrid algorithm can better resist the change of an external load, so that the error between the inlet and outlet temperature and the target temperature value is smaller, the fuzzy controller can be effectively applied to the thermal management of the fuel cell of the high-power hybrid electric vehicle, and the fuzzy controller has better advantages in accuracy and stability. Through computer simulation verification, the invention effectively improves the accuracy and stability of temperature control, and can be popularized to the temperature control of similar systems.
The present invention may be a system, method and/or computer program product. The computer program product may include a computer-readable storage medium having computer-readable program instructions embodied therewith for causing a processor to implement various aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be construed as transitory signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or electrical signals transmitted through electrical wires.
The computer-readable program instructions described herein may be downloaded from a computer-readable storage medium to a respective computing/processing device, or to an external computer or external storage device via a network, such as the internet, a local area network, a wide area network, and/or a wireless network. The network may include copper transmission cables, fiber optic transmission, wireless transmission, routers, firewalls, switches, gateway computers and/or edge servers. The network adapter card or network interface in each computing/processing device receives computer-readable program instructions from the network and forwards the computer-readable program instructions for storage in a computer-readable storage medium in the respective computing/processing device.
The computer program instructions for carrying out operations of the present invention may be assembler instructions, Instruction Set Architecture (ISA) instructions, machine-related instructions, microcode, firmware instructions, state setting data, or source code or object code written in any combination of one or more programming languages, including an object oriented programming language such as Smalltalk, C + +, Python, or the like, and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The computer-readable program instructions may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider). In some embodiments, aspects of the present invention are implemented by personalizing an electronic circuit, such as a programmable logic circuit, a Field Programmable Gate Array (FPGA), or a Programmable Logic Array (PLA), with state information of computer-readable program instructions, which can execute the computer-readable program instructions.
Aspects of the present invention are described herein with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and/or block diagrams, and combinations of blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer-readable program instructions.
These computer-readable program instructions may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions/acts specified in the flowchart and/or block diagram block or blocks. These computer-readable program instructions may also be stored in a computer-readable storage medium that can direct a computer, programmable data processing apparatus, and/or other devices to function in a particular manner, such that the computer-readable medium storing the instructions comprises an article of manufacture including instructions which implement the function/act specified in the flowchart and/or block diagram block or blocks.
The computer readable program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other devices to cause a series of operational steps to be performed on the computer, other programmable apparatus or other devices to produce a computer implemented process such that the instructions which execute on the computer, other programmable apparatus or other devices implement the functions/acts specified in the flowchart and/or block diagram block or blocks.
The flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of instructions, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions. It is well known to those skilled in the art that implementation by hardware, by software, and by a combination of software and hardware are equivalent.
While embodiments of the present invention have been described above, the above description is illustrative, not exhaustive, and not limited to the disclosed embodiments. Many modifications and variations will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The terminology used herein is chosen in order to best explain the principles of the embodiments, the practical application, or improvements made to the technology in the marketplace, or to enable others of ordinary skill in the art to understand the embodiments disclosed herein. The scope of the invention is defined by the appended claims.
Claims (10)
1. A method of thermal management of a fuel cell, comprising the steps of:
setting an outlet fuzzy controller and an inlet fuzzy controller aiming at a fuel cell thermal management system, wherein the fuel cell thermal management system comprises a water tank, a cooling water pump, a radiator and an electric pile, the outlet fuzzy controller takes the error and the error change rate of the current electric pile outlet temperature and the set target outlet temperature as input quantities, and takes cooling water flow as output quantities; the inlet fuzzy controller takes the error between the current temperature of the electric pile inlet and the set target inlet temperature and the change rate of the error as input quantity, and takes the fan rotating speed of the radiator as output quantity;
determining membership functions and fuzzy domains of the outlet fuzzy controller and the inlet fuzzy controller and setting fuzzy rules;
and carrying out parameterization processing on the membership function, taking a parameter to be optimized as a particle population, and optimizing the membership functions of the inlet fuzzy controller and the outlet fuzzy controller so as to control the current cooling water flow of the fuel cell thermal management system and the fan rotating speed of a radiator.
2. The method of claim 1, wherein the membership function is set as a triangular membership function that characterizes parameters with the abscissa of the vertex and the two abscissas of the base, and the input and output quantities of the outlet and inlet fuzzy controllers are divided into seven fuzzy subsets, including negative large, negative medium, negative small, zero, positive small, positive medium and positive large.
3. The method of claim 2, wherein the parameterizing of the membership functions for the parameters to be optimized as the population of particles comprises:
parameterizing fixed-point abscissas and two abscissas of the bottom edges of the triangular membership function based on the seven divided fuzzy subsets to serve as particle populations, and taking the value range of the abscissas of the triangular membership function as an adaptive value;
determining the optimal solution of the particles and the optimal solution of the whole particle population by taking the fitness function set in the minimization as a standard so as to adjust the width and the central position of the triangular membership function;
updating the speed and the position of the particles according to the global optimal model cycle optimization, and further outputting an initial optimized population;
and taking the initial optimized population as a chromosome, and performing individual selection, crossing and mutation operations by using a genetic algorithm to realize an optimization process aiming at the initial optimized population.
4. A method according to claim 3, characterized by setting the fitness function to:
wherein N is the number of individuals in the population of particles, T is the time, T tar Is a target temperature, T st Is the current temperature of the stack.
5. The method of claim 3, wherein said iteratively updating the velocity and position of the particle itself according to the global optimal model comprises: for particle i, the updated velocity and position at the kth iteration are represented as:
wherein v is id Is the velocity, x, of the particle i id Is the position of the particle i, p id Is the best position, p, experienced by the particle i gd Is the best position experienced by all particles in the population, ω is the inertial weight, c1 and c2 are acceleration constants, and rand () results from 0, 1]A random number within the range of the random number,
is the position of the particle after the update,
is the speed of the vehicle after the update,
is the speed of the particle i before it is updated,
is the position of particle i before update.
6. The method according to claim 3, characterized in that for said selection, crossing and mutation operations of individuals performed by genetic algorithm, the crossing operation uses a real number crossing method, the alpha chromosome c α And the beta chromosome c β The cross at ξ is represented as:
wherein, P c For the cross probability, is [0, 1]]Random number of (1), c on the left side of equal sign αξ 、c βξ Is the chromosome after crossover manipulation, c to the right of equal sign αξ 、c βξ Is the chromosome before the crossover operation.
7. The method of claim 3, wherein for the selection, crossover and mutation of individuals using genetic algorithms, the selection of individuals employs a fitness proportion-based selection strategy, and the probability that an individual i is selected is expressed as:
wherein, F i 、F j Fitness values of the individual i and the individual j are respectively, and N is the number of the individuals in the particle population.
8. The method of claim 1, wherein the fuzzy rule is an if-then fuzzy control rule.
9. A computer-readable storage medium, on which a computer program is stored, wherein the computer program realizes the steps of the method according to any one of claims 1 to 8 when executed by a processor.
10. A computer device comprising a memory and a processor, on which memory a computer program is stored which is executable on the processor, characterized in that the processor realizes the steps of the method according to any one of claims 1 to 8 when executing the computer program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210509539.4A CN115084598A (en) | 2022-05-11 | 2022-05-11 | Thermal management method of fuel cell |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210509539.4A CN115084598A (en) | 2022-05-11 | 2022-05-11 | Thermal management method of fuel cell |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115084598A true CN115084598A (en) | 2022-09-20 |
Family
ID=83247837
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210509539.4A Pending CN115084598A (en) | 2022-05-11 | 2022-05-11 | Thermal management method of fuel cell |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115084598A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115343966A (en) * | 2022-10-17 | 2022-11-15 | 中国汽车技术研究中心有限公司 | Simulation method of fuel cell water heat management system |
| CN116259785A (en) * | 2023-05-11 | 2023-06-13 | 上海重塑能源科技有限公司 | High-power fuel cell water inlet temperature control method, device, medium and vehicle |
| CN117239188A (en) * | 2023-11-08 | 2023-12-15 | 上海徐工智能科技有限公司 | Fuel cell thermal management system and method |
| CN117420863A (en) * | 2023-10-30 | 2024-01-19 | 上海频准激光科技有限公司 | Method, equipment and medium for determining membership function type of gain medium material |
| CN117790837A (en) * | 2023-12-29 | 2024-03-29 | 德燃(浙江)动力科技有限公司 | Controller and fuel cell heat dissipation control system |
-
2022
- 2022-05-11 CN CN202210509539.4A patent/CN115084598A/en active Pending
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115343966A (en) * | 2022-10-17 | 2022-11-15 | 中国汽车技术研究中心有限公司 | Simulation method of fuel cell water heat management system |
| CN115343966B (en) * | 2022-10-17 | 2023-01-10 | 中国汽车技术研究中心有限公司 | Simulation method of fuel cell water heat management system |
| CN116259785A (en) * | 2023-05-11 | 2023-06-13 | 上海重塑能源科技有限公司 | High-power fuel cell water inlet temperature control method, device, medium and vehicle |
| CN117420863A (en) * | 2023-10-30 | 2024-01-19 | 上海频准激光科技有限公司 | Method, equipment and medium for determining membership function type of gain medium material |
| CN117420863B (en) * | 2023-10-30 | 2024-04-19 | 上海频准激光科技有限公司 | Method, equipment and medium for determining membership function type of gain medium material |
| CN117239188A (en) * | 2023-11-08 | 2023-12-15 | 上海徐工智能科技有限公司 | Fuel cell thermal management system and method |
| CN117239188B (en) * | 2023-11-08 | 2024-02-02 | 上海徐工智能科技有限公司 | Fuel cell thermal management system and method |
| CN117790837A (en) * | 2023-12-29 | 2024-03-29 | 德燃(浙江)动力科技有限公司 | Controller and fuel cell heat dissipation control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115084598A (en) | Thermal management method of fuel cell | |
| Huynh | A modified shuffled frog leaping algorithm for optimal tuning of multivariable PID controllers | |
| CN111129548B (en) | Improved particle swarm optimization fuzzy PID fuel cell temperature control method | |
| WO2023216150A1 (en) | Thermal management method for fuel cell | |
| Chen et al. | A modified MPC-based optimal strategy of power management for fuel cell hybrid vehicles | |
| Wu et al. | Modeling a SOFC stack based on GA-RBF neural networks identification | |
| CN111179121A (en) | Power grid emergency control method based on expert system and deep reverse reinforcement learning | |
| Zhang et al. | A survey on algorithm adaptation in evolutionary computation | |
| Wong et al. | Optimal PID controller design for AVR system | |
| Zhang et al. | State-of-charge estimation of lithium-ion battery pack based on improved RBF neural networks | |
| CN115392139B (en) | Fuel cell parameter identification method | |
| Shen et al. | Nonlinear modeling and adaptive fuzzy control of MCFC stack | |
| Zhang et al. | Application of coRNA-GA based RBF-NN to model proton exchange membrane fuel cells | |
| Tao et al. | DNA Computing Based Genetic Algorithm: Applications in Industrial Process Modeling and Control | |
| Cao et al. | PSO-Stacking improved ensemble model for campus building energy consumption forecasting based on priority feature selection | |
| Li et al. | An optimal coordinated proton exchange membrane fuel cell heat management method based on large-scale multi-agent deep reinforcement learning | |
| Fu et al. | An extreme gradient boosting-based thermal management strategy for proton exchange membrane fuel cell stacks | |
| Harun et al. | Comparison of controllers design performance for underwater remotely operated vehicle (ROV) depth control | |
| Sudha et al. | GA-ANN hybrid approach for load forecasting | |
| CN110059342A (en) | A kind of method for parameter estimation of lithium ion battery P2D model | |
| Yin et al. | Improved hybrid fireworks algorithm-based parameter optimization in high-order sliding mode control of hypersonic vehicles | |
| Chopra et al. | A Neurofuzzy Learning and its Application to Control system | |
| Zheng et al. | A Data Driven Fuel Cell Life-Prediction Model for a Fuel Cell Electric City Bus | |
| Li et al. | The research on electric load forecasting based on nonlinear gray bernoulli model optimized by cosine operator and particle swarm optimization | |
| Zhou et al. | A Robust Prognostic Indicator for Renewable Energy Fuel Cells: A Hybrid Data-Driven Prediction Approach |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |