Energy Management Method and Device for Fuel Cell Vehicles Based on Snake Optimization Algorithm

Abstract

This invention provides a method and apparatus for energy management of fuel cell vehicles based on a snake optimization algorithm. The method constructs a two-layer fuzzy controller for energy management allocation in the hybrid vehicle based on its dynamic model. Then, a multi-objective cost function model is established based on fuel cell lifespan degradation, fuel cell power degradation, and the equivalent fuel consumption of the power battery. Next, the membership function parameters to be optimized in the two-layer fuzzy controller are obtained, and the membership function is optimized using a snake optimization algorithm to obtain the energy management scheme for the fuel cell vehicle. This invention can reduce the average power output of the fuel cell, reduce fuel cell degradation, and optimize the fuel cell energy management scheme, improving vehicle durability while meeting economic requirements.

Description

Technical Field

[0001] This invention relates to the field of new energy vehicle technology, specifically to a method and device for energy management of fuel cell vehicles based on snake optimization algorithm. Background Technology

[0002] Currently, environmental and energy issues are receiving increasing attention, and new energy vehicles fueled by clean energy are becoming the future development trend of the automotive industry. Due to the advantages of fuel cells, such as high efficiency and zero pollution, fuel cell hybrid vehicles (FCHEVs) are gaining increasing attention from automakers. However, pure fuel cell systems suffer from drawbacks such as long start-up times and slow dynamic response, thus requiring the coupling of multiple power sources to drive the vehicle.

[0003] Fuel cell vehicles suffer from drawbacks such as high cost, fuel cell performance degradation, and short lifespan, which currently prevent large-scale commercialization. Furthermore, the lifespan of fuel cells is significantly affected by large variations in power load and frequent start-stop cycles.

[0004] To improve energy efficiency while reducing fuel cell losses, a multi-objective problem needs to be addressed. Therefore, how to improve the energy efficiency of electric vehicles while reducing fuel cell losses has become a pressing issue for engineers in the field. Summary of the Invention

[0005] In view of this, it is necessary to provide a method and device for energy management of fuel cell vehicles based on snake optimization algorithm, so as to solve the problem that it is impossible to simultaneously improve the energy utilization rate of existing fuel cell vehicles and keep the fuel cell loss low.

[0006] To address the aforementioned technical problems, this invention provides a fuel cell vehicle energy management method based on a snake optimization algorithm, comprising:

[0007] A dynamic model of a fuel cell vehicle is obtained, and a two-layer fuzzy controller for energy management and distribution of hybrid electric vehicles is constructed based on the dynamic model of the fuel cell vehicle. The two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time.

[0008] A multi-objective cost function model is established based on the fuel cell life decay, fuel cell power decay, and equivalent fuel consumption of the power battery, and the multi-objective cost modulus model is defined as the fitness function of the snake optimization algorithm.

[0009] The membership function parameters to be optimized in the two-layer fuzzy controller are obtained, and the membership function is optimized based on the snake optimization algorithm to obtain the energy management scheme of fuel cell vehicle.

[0010] In one possible implementation, the dynamic model of a fuel cell vehicle is expressed as follows:

[0011]

[0012] P req =P fc +P batt ;

[0013] Among them, P req The vehicle's required power is represented by u, and its speed is represented by η. m η represents the motor efficiency. t The vector represents the transmission system efficiency, m represents the vehicle weight, g represents the acceleration due to gravity, f represents the rolling resistance coefficient, α represents the road slope angle, and C represents the road surface angle. D The value represents the air drag coefficient, A represents the vehicle's frontal area, and δ represents the rotational mass conversion factor. P represents the vehicle's acceleration. fc P represents the output power of the fuel cell system. batt This indicates the battery power.

[0014] In one possible implementation, constructing a two-layer fuzzy controller for energy management and allocation of hybrid vehicles based on the dynamics model of fuel cell vehicles includes:

[0015] The first-layer fuzzy controller is constructed based on the vehicle's required power and the state of charge of the power battery, and a fuzzy subset of the first-layer fuzzy controller is obtained.

[0016] A second-layer fuzzy controller is constructed based on the difference between the vehicle's output power and the target efficiency power of the fuel cell and the state of charge of the power battery, thus obtaining a fuzzy subset of the second-layer fuzzy controller.

[0017] Empirical rule reasoning is performed based on fuzzy subsets of the first-layer fuzzy controller and fuzzy subsets of the second-layer fuzzy controller to form a fuzzy rule base.

[0018] In one possible implementation, a first-layer fuzzy controller is constructed based on the vehicle's power demand and the state of charge of the power battery, resulting in a fuzzy subset of the first-layer fuzzy controller, including:

[0019] The vehicle's power demand and the battery's state of charge are used as input variables for the first-layer fuzzy controller, and the fuel cell's output power is used as the output variable for the first-layer fuzzy controller.

[0020] The power demand intervals of the vehicle are fuzzified to obtain several first fuzzy subsets in the discrete domain of power demand.

[0021] The state of charge interval of the power battery is fuzzified to obtain several second fuzzy subsets in the discrete domain of the state of charge of the power battery.

[0022] The output power intervals of the fuel cell are fuzzified to obtain several third fuzzy subsets in the discrete domain of the fuel cell output power.

[0023] In one possible implementation, a second-layer fuzzy controller is constructed based on the difference between the vehicle's output power and the fuel cell's target efficiency power, and the state of charge of the power battery. This results in a fuzzy subset of the second-layer fuzzy controller, including:

[0024] The difference between the fuel cell's output power and the fuel cell's target efficiency power, along with the power battery's state of charge, are used as input variables for the second-layer fuzzy controller, while the fuel cell's output power correction coefficient is used as the output variable for the second-layer fuzzy controller.

[0025] The difference between the output power of the vehicle fuel cell and the target efficiency power of the fuel cell is divided into intervals and fuzzified to obtain several fourth fuzzy subsets in the discrete domain of demand power.

[0026] The state of charge interval of the power battery is fuzzified to obtain several fifth fuzzy subsets in the discrete domain of the state of charge of the power battery.

[0027] The correction coefficient range of fuel cell output power is fuzzified to obtain several sixth fuzzy subsets in the discrete domain of fuel cell output power.

[0028] In one possible implementation, the expression for the multi-objective cost modulus model is:

[0029]

[0030] Where fitness represents the multi-objective cost function, D represents the vehicle's equivalent hydrogen consumption. fc C1 represents the cost coefficient of equivalent hydrogen consumption, C2 represents the cost coefficient of fuel cell system degradation, and m represents the fuel cell system degradation rate. fc The amount of hydrogen consumed by the fuel cell system, m batt The value of D represents the equivalent hydrogen consumption of the power battery, μ represents the adjustment coefficient, and D represents the equivalent hydrogen consumption of the power battery. fcThe values ​​represent the degradation rate of the fuel cell system, where P represents the maximum permissible degradation rate, P1 represents the degradation rate caused by the start-stop cycle of the fuel cell system, P2 represents the degradation rate caused by the load change of the fuel cell system, P3 represents the degradation rate caused by the idling of the fuel cell system, P4 represents the degradation rate caused by the high power load of the fuel cell system, n1 represents the number of start-stop cycles of the fuel cell system, n2 represents the number of start-stop cycles of the fuel cell system, t3 represents the idling time, t4 represents the high power load time, and β represents the natural degradation rate.

[0031] In one possible implementation, the membership functions to be optimized in the two-layer fuzzy controller include:

[0032] The fourth membership function corresponding to the difference between the output power of the vehicle fuel cell and the target efficiency power of the fuel cell is determined based on several fourth fuzzy subsets.

[0033] The fifth membership function corresponding to the state of charge of the power battery is determined based on several fifth fuzzy subsets;

[0034] The sixth membership function corresponding to the fuel cell output power correction coefficient is determined based on several sixth fuzzy subsets.

[0035] In one possible implementation, the membership function is optimized based on the snake optimization algorithm to obtain an energy management scheme for fuel cell vehicles, including:

[0036] The unknown variables belonging to the fourth, fifth, and sixth membership functions are determined based on the intersection of the segment lines of the fourth, fifth, and sixth membership functions.

[0037] Initialize the basic parameters of the snake optimization algorithm, including the number of snakes, the number of females, the number of males, the maximum number of iterations, and the boundary of the objective variable;

[0038] Based on the boundary of the target variable, the position of each individual in the initial snake population is determined, so that each individual snake represents a different target variable;

[0039] Based on working condition data, and combined with snake optimization algorithm, the current position of each individual snake in the snake population is updated iteratively to obtain the optimal target variable value;

[0040] The optimal target variable value is used to optimize the membership function parameters to be optimized in the two-layer fuzzy controller, and the target control result of the fuzzy controller output is obtained.

[0041] In one possible implementation, the target variable includes unknown variables of the fourth membership function, the fifth membership function, and the sixth membership function.

[0042] To address the aforementioned problems, this invention also provides a fuel cell vehicle energy management device based on a snake optimization algorithm, comprising:

[0043] The fuzzy controller module is used to obtain the dynamic model of the fuel cell vehicle. Based on the dynamic model of the fuel cell vehicle, a two-layer fuzzy controller for energy management and distribution of hybrid vehicles is constructed. The two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time.

[0044] The multi-objective cost function module is used to establish a multi-objective cost function model based on the fuel cell life decay, fuel cell power decay, and equivalent fuel consumption of the power battery, and the multi-objective cost modulus model is defined as the fitness function of the snake optimization algorithm;

[0045] The optimization module is used to obtain the membership function parameters to be optimized in the two-layer fuzzy controller, and optimize the membership function based on the snake optimization algorithm to obtain the energy management scheme of fuel cell vehicle.

[0046] The beneficial effects of the above embodiments are as follows: By constructing a two-layer fuzzy controller for energy management and allocation of hybrid vehicles based on the dynamic model of fuel cell vehicles, the two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time, thereby reducing the average power output of the fuel cell and reducing the degradation of the fuel cell; then, a multi-objective cost function model is established based on the fuel cell life degradation, the fuel cell power degradation and the equivalent fuel consumption of the power battery, and the membership function parameters to be optimized in the two-layer fuzzy controller are obtained, and the membership function is optimized based on the snake optimization algorithm, thereby realizing the optimization of the fuel cell energy management scheme, improving the vehicle's durability while satisfying the economic requirements. Attached Figure Description

[0047] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0048] Figure 1 A flowchart illustrating an embodiment of the energy management method for fuel cell vehicles based on the snake optimization algorithm provided by the present invention;

[0049] Figure 2 A flowchart illustrating another embodiment of the energy management method for fuel cell vehicles based on the snake optimization algorithm provided by the present invention;

[0050] Figure 3A schematic diagram of the fourth membership function to be optimized provided by the present invention;

[0051] Figure 4 A schematic diagram of the fifth membership function to be optimized provided by the present invention;

[0052] Figure 5 A schematic diagram of the sixth membership function to be optimized provided by the present invention;

[0053] Figure 6 This is a schematic diagram of a sub-implementation of the energy management device for fuel cell vehicles based on the snake optimization algorithm provided by the present invention. Detailed Implementation

[0054] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0055] Some of the block diagrams shown in the accompanying drawings are functional entities and do not necessarily correspond to physically or logically independent entities. These functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor systems and / or microcontroller systems.

[0056] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of the invention. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a mutually exclusive, independent, or alternative embodiment. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0057] This invention provides a method and apparatus for energy management of fuel cell vehicles based on the snake optimization algorithm, which will be described below.

[0058] Figure 1 This is a flowchart illustrating an embodiment of the energy management method for fuel cell vehicles based on the snake optimization algorithm provided by the present invention. Figure 2 This is a flowchart illustrating another embodiment of the energy management method for fuel cell vehicles based on the snake optimization algorithm provided by the present invention.

[0059] Reference Figure 1 This invention provides a fuel cell vehicle energy management method based on the snake optimization algorithm, comprising:

[0060] S101. Obtain the dynamic model of the fuel cell vehicle, and construct a two-layer fuzzy controller for energy management and distribution of the hybrid vehicle based on the dynamic model of the fuel cell vehicle. The two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time.

[0061] S102. Establish a multi-objective cost function model based on the fuel cell life decay, fuel cell power decay and equivalent fuel consumption of the power battery, and define the multi-objective cost modulus model as the fitness function of the snake optimization algorithm.

[0062] S103. Obtain the membership function parameters to be optimized in the two-layer fuzzy controller, optimize the membership function based on the snake optimization algorithm, and obtain the energy management scheme of fuel cell vehicle.

[0063] The embodiments of the present invention have the following beneficial effects: a two-layer fuzzy controller for energy management and allocation of hybrid vehicles is constructed based on the dynamic model of fuel cell vehicles. The two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time, thereby reducing the average power output of the fuel cell and reducing the degradation of the fuel cell. Then, a multi-objective cost function model is established based on the fuel cell life degradation, the fuel cell power degradation and the equivalent fuel consumption of the power battery. After obtaining the membership function parameters to be optimized in the two-layer fuzzy controller, the membership function is optimized based on the snake optimization algorithm, thereby optimizing the fuel cell energy management scheme and improving the vehicle's durability while satisfying the economic requirements.

[0064] The embodiments of the present invention will be described in detail below.

[0065] In one embodiment, in S101, the expression for the dynamic model of the fuel cell vehicle is:

[0066]

[0067] P req =P fc +P batt ;

[0068] Among them, P req The vehicle's required power is represented by u, and its speed is represented by η. m Indicates motor efficiency, η t The vector represents the transmission system efficiency, m represents the vehicle weight, g represents the acceleration due to gravity, f represents the rolling resistance coefficient, α represents the road slope angle, and C represents the road surface angle. D The value represents the air drag coefficient, A represents the vehicle's frontal area, and δ represents the rotational mass conversion factor. P represents the vehicle's acceleration. fc P represents the output power of the fuel cell system.batt Indicates battery power.

[0069] It should be explained that the output power of the aforementioned fuel cell system should be kept within the target power range to avoid the vehicle operating under high load, and the power battery can perform energy recovery during braking.

[0070] In one embodiment, the two-layer fuzzy controller for energy management and allocation of hybrid vehicles based on the dynamic model of fuel cell vehicles in S101 includes:

[0071] The first-layer fuzzy controller is constructed based on the vehicle's required power and the state of charge of the power battery, and a fuzzy subset of the first-layer fuzzy controller is obtained.

[0072] A second-layer fuzzy controller is constructed based on the difference between the vehicle's output power and the target efficiency power of the fuel cell and the state of charge of the power battery, thus obtaining a fuzzy subset of the second-layer fuzzy controller.

[0073] Empirical rule reasoning is performed based on fuzzy subsets of the first-layer fuzzy controller and fuzzy subsets of the second-layer fuzzy controller to form a fuzzy rule base.

[0074] Furthermore, a first-layer fuzzy controller is constructed based on the vehicle's required power and the state of charge of the power battery, resulting in a fuzzy subset of the first-layer fuzzy controller, including:

[0075] The vehicle's power demand and the battery's state of charge are used as input variables for the first-layer fuzzy controller, and the fuel cell's output power is used as the output variable for the first-layer fuzzy controller.

[0076] The power demand intervals of the vehicle are fuzzified to obtain several first fuzzy subsets in the discrete domain of power demand.

[0077] The state of charge interval of the power battery is fuzzified to obtain several second fuzzy subsets in the discrete domain of the state of charge of the power battery.

[0078] The output power intervals of the fuel cell are fuzzified to obtain several third fuzzy subsets in the discrete domain of the fuel cell output power.

[0079] For example, in a scenario where a two-layer fuzzy controller is being built, the construction process of the first-layer fuzzy controller includes:

[0080] The vehicle's power demand and the battery's state of charge are used as input variables for the first-layer fuzzy controller, and the fuel cell's output power is used as the output variable for the first-layer fuzzy controller.

[0081] Power demand P of the vehicle reThe intervals are fuzzified, and the discrete domain is determined to be [0,80], resulting in several first fuzzy subsets, which are very low (SS), very low (SM), relatively low (SL), moderately low (MS), moderately high (ML) and high (L).

[0082] The state of charge (SOC) interval of the power battery is fuzzified, and the discrete domain is determined to be [0,1]. Several second fuzzy subsets are obtained, namely low (LL), lower (L), medium (M), medium-high (ML), and high (H).

[0083] For the output power P of the fuel cell fc The intervals are fuzzified, and the discrete domain is determined to be [0,60]. Several third fuzzy subsets are obtained, namely very low (SS), relatively low (SL), moderately low (MS), moderately high (ML), and high (L).

[0084] Empirical reasoning was performed on several first fuzzy subsets, several second fuzzy subsets, and several third fuzzy subsets to obtain a fuzzy rule base, as shown in Table 1 below;

[0085]

[0086] Table 1 First-layer fuzzy rule base

[0087] In one embodiment, a second-layer fuzzy controller is constructed based on the difference between the vehicle's output power and the fuel cell's target efficiency power, and the state of charge of the power battery, resulting in a fuzzy subset of the second-layer fuzzy controller, including:

[0088] The difference between the fuel cell's output power and the fuel cell's target efficiency power, along with the power battery's state of charge, are used as input variables for the second-layer fuzzy controller, while the fuel cell's output power correction coefficient is used as the output variable for the second-layer fuzzy controller.

[0089] The difference between the output power of the vehicle fuel cell and the target efficiency power of the fuel cell is divided into intervals and fuzzified to obtain several fourth fuzzy subsets in the discrete domain of demand power.

[0090] The state of charge interval of the power battery is fuzzified to obtain several fifth fuzzy subsets in the discrete domain of the state of charge of the power battery.

[0091] The correction coefficient range of fuel cell output power is fuzzified to obtain several sixth fuzzy subsets in the discrete domain of fuel cell output power.

[0092] The process of constructing the first-layer fuzzy controller includes:

[0093] The difference between the fuel cell output power and the fuel cell target efficiency power, and the state of charge of the power battery are used as input variables of the second-layer fuzzy controller, and the fuel cell output power correction coefficient is used as the output variable of the second-layer fuzzy controller.

[0094] The output power P of the vehicle fuel cell fc The difference ΔP between the target efficiency and power of the fuel cell fc The intervals are fuzzified to determine the discrete domain as [-24.5, 36.5], resulting in several fourth fuzzy subsets, namely NL (negative large), NM (negative medium), NS (negative small), Z (zero), PS (positive small), PM (positive medium), PB (positive large), and PL (positive large).

[0095] The state of charge (SOC) intervals of the power battery are fuzzified, and the discrete domain is determined to be [0,1], resulting in several fifth fuzzy subsets, namely L (low), M (medium), and H (high);

[0096] Correction factor k for fuel cell output power modify The intervals are fuzzified, and the discrete domain is determined to be [0,1], resulting in several sixth fuzzy subsets: SS (very small), SL (smaller), M (medium), and L (large).

[0097] Empirical reasoning was performed on several fourth, fifth, and sixth fuzzy subsets to obtain a fuzzy rule base, as shown in Table 2 below:

[0098]

[0099] Table 2 Second-layer fuzzy rule base

[0100] Reference Figure 2 , Figure 2 This is a flowchart illustrating a two-layer fuzzy controller. The control process of this two-layer fuzzy control system is carried out in two steps:

[0101] The first step is the first layer of fuzzy inference, which involves collecting the vehicle power demand P. re The state of charge (SOC) of the power battery is used as the input variable of the first-layer fuzzy controller and fuzzified to obtain fuzzy state variables; the fuel cell output power P is obtained by inferring from the fuzzy rule base established in Table 1. fc Fuzzy state variables; the output variables are defuzzified and used as the basic input variables of the two-layer fuzzy controller.

[0102] The second step is the second layer of fuzzy inference. First, the output result of the first layer, the fuel cell output power P, is... fc The difference ΔP between the power and the target output efficiency fcThe state of charge (SOC) of the power battery is fuzzified to obtain fuzzy state variables; the fuel cell output power correction coefficient k is obtained by inference from the two-layer fuzzy rule base established in Table 2 above. modify The fuzzy state variables are then defuzzified to obtain the final fuel cell output power correction coefficient value.

[0103] It should be noted that the maximum correction amount for fuel cell output power is 10kW.

[0104] In one embodiment, the expression for the multi-objective cost modulus model is:

[0105]

[0106] Where fitness represents the multi-objective cost function. D represents the vehicle's equivalent hydrogen consumption. fc C1 represents the cost coefficient of equivalent hydrogen consumption, C2 represents the cost coefficient of fuel cell system degradation, and m represents the fuel cell system degradation rate. fc The amount of hydrogen consumed by the fuel cell system, m batt The value of D represents the equivalent hydrogen consumption of the power battery, μ represents the adjustment coefficient, and D represents the equivalent hydrogen consumption of the power battery. fc The values ​​represent the degradation rate of the fuel cell system, where P represents the maximum permissible degradation rate, P1 represents the degradation rate caused by the start-stop cycle of the fuel cell system, P2 represents the degradation rate caused by the load change of the fuel cell system, P3 represents the degradation rate caused by the idling of the fuel cell system, P4 represents the degradation rate caused by the high power load of the fuel cell system, n1 represents the number of start-stop cycles of the fuel cell system, n2 represents the number of start-stop cycles of the fuel cell system, t3 represents the idling time, t4 represents the high power load time, and β represents the natural degradation rate.

[0107] Figure 3 This is a schematic diagram of the fourth membership function to be optimized provided by the present invention. Figure 4 This is a schematic diagram of the fifth membership function to be optimized provided by the present invention. Figure 5 This is a schematic diagram of the sixth membership function to be optimized provided by the present invention.

[0108] Wherein, PFC distance represents the difference ΔP between the vehicle's fuel cell output power and the fuel cell's optimal efficiency power. fc The degree of membership indicates the degree of membership.

[0109] In one embodiment, the membership function to be optimized in the two-layer fuzzy controller includes:

[0110] The fourth membership function corresponding to the difference between the output power of the vehicle fuel cell and the target efficiency power of the fuel cell is determined based on several fourth fuzzy subsets.

[0111] The fifth membership function corresponding to the state of charge of the power battery is determined based on several fifth fuzzy subsets;

[0112] The sixth membership function corresponding to the fuel cell output power correction coefficient is determined based on several sixth fuzzy subsets.

[0113] Furthermore, the function acquisition process in the fuzzy controller is as follows:

[0114] Based on several fourth fuzzy subsets, the membership function corresponding to each fuzzy subset is determined in the discrete domain [-24.5, 36.5], which is the difference ΔP between the vehicle fuel cell output power and the fuel cell optimal efficiency power. fc The corresponding fourth membership function is as follows: Figure 3 As shown;

[0115] Based on several fifth fuzzy subsets, the membership function corresponding to each fuzzy subset is determined in the discrete domain [0,1]. That is, the fifth membership function corresponding to the state of charge (SOC) of the power battery, specifically as follows: Figure 4 As shown;

[0116] Based on several sixth fuzzy subsets, the membership function corresponding to each fuzzy subset is determined in the discrete domain [0,1], which is the fuel cell output power correction coefficient k. modify The corresponding sixth membership function is as follows: Figure 5 As shown.

[0117] Before optimizing the membership functions, it is necessary to determine the optimization variables corresponding to each membership function. The specific steps are as follows:

[0118] (1) According to Figure 3 The intersection of the piecewise lines of the fourth membership function shown determines several first unknown variables, specifically including x1, x2, x3, x4, x5, x6, x7, x8, x9, and x 10 x 11 x 12 x 13 x 14 There are 14 unknown variables, and range constraints are applied to these 14 unknown variables as follows:

[0119]

[0120] (2) According to Figure 4 The intersection of the piecewise lines of the fifth membership function shown determines several second unknown variables, specifically including x. 15 x16 x 17 x 18 There are four second unknown variables, and range constraints are applied to these four unknown variables as follows:

[0121]

[0122] (3) According to Figure 5 The intersection of the piecewise lines of the sixth membership function shown determines several third unknown variables, specifically including x. 19 x 20 x 21 x 22 x 23 x 23 There are six third unknown variables, and range constraints are applied to these six third unknown variables as follows:

[0123]

[0124] In one embodiment, the membership function is optimized based on the snake optimization algorithm to obtain an energy management scheme for fuel cell vehicles, including:

[0125] The unknown variables belonging to the fourth, fifth, and sixth membership functions are determined based on the intersection of the segment lines of the fourth, fifth, and sixth membership functions.

[0126] Initialize the basic parameters of the snake optimization algorithm, including the number of snakes, the number of females, the number of males, the maximum number of iterations, and the boundary of the objective variable;

[0127] Based on the boundary of the target variable, the position of each individual in the initial snake population is determined, so that each individual snake represents a different target variable;

[0128] Based on working condition data, and combined with snake optimization algorithm, the current position of each individual snake in the snake population is updated iteratively to obtain the optimal target variable value;

[0129] The optimal target variable value is used to optimize the membership function parameters to be optimized in the two-layer fuzzy controller, and the target control result of the fuzzy controller output is obtained.

[0130] Furthermore, the target variable includes the unknown variables of the fourth membership function, the fifth membership function, and the sixth membership function.

[0131] Before optimizing the membership function, let's briefly explain the principle of the snake optimization algorithm. The snake optimization algorithm is mainly an optimization algorithm formed by simulating the foraging and mating behavior of snake groups, as detailed below:

[0132] The mating behavior of male and female snakes is influenced by food availability and ambient temperature; mating occurs when the temperature is low and food is plentiful. Based on this, the specific steps of the snake optimization algorithm are explained below:

[0133] a. Randomly assign positions to individuals in the initial population using the following formula:

[0134] X i =X min +r×(X max -X min );

[0135] Among them, X i X represents the initial position of each individual. max X min Let r be the boundary between the maximum and minimum positions, and r be a random number between 0 and 1.

[0136] b. The number of male and female individuals in the population is generally divided at a 1:1 ratio;

[0137] c. Define the values ​​of temperature and food as they are updated iteratively. The update formula for these values ​​is:

[0138]

[0139]

[0140] Where Temp and Q represent the values ​​of temperature and food, respectively, t represents the current iteration number, T is the maximum iteration number, and c1 is a constant of 0.5.

[0141] d. Define the thresholds for food and temperature, and define the relationship between snake group position updates under different conditions, as follows:

[0142] When food quantity Q is less than the threshold, i.e., when food is insufficient:

[0143] X i，m (t+1)=X rand,m ±c2×A m ×((X max -X min )×rand+X min );

[0144] X i，f (t+1)=X rand,f ±c2×A f ×((X max -X min )×rand+X min );

[0145]

[0146]

[0147] Among them, X i，m and X i，f X represents the positions of the male and female individuals in the current iteration. rand,m and X rand,f These represent the positions of random male and female individuals, respectively, where rand is a random number between 0 and 1, and f... rand,m and f rand,f These are the fitness function values ​​f, corresponding to the positions of the aforementioned random male and female individuals. i,m and f i,m c1 and c2 are the fitness function values ​​corresponding to the positions of male and female individuals in the current iteration, respectively, and c2 is a constant of 0.05.

[0148] When food Q is greater than a threshold, and temperature Temp is also greater than a threshold:

[0149] X i，j (t+1)=X food ±c3×Temp×rand×(X food -X i，j (t));

[0150] Among them, X i，j For the location of a single individual, X food The optimal position for the individual is given by c3, which is a constant of 2.

[0151] When the food quantity Q is greater than the threshold and the temperature is less than the threshold, i.e., when mating conditions are met, there are two modes: combat mode and mating mode.

[0152] Battle mode position update formula:

[0153] X i，m (t+1)=X i，m (t)±c3×FM×rand×(Q×X best，f -X i，m (t));

[0154] X i，f (t+1)=X i，f (t)±c3×FF×rand×(Q×X best，m -X i，f (t));

[0155]

[0156]

[0157] Among them, Xi，m and X i，f X represents the position corresponding to the current iteration number in both male and female individuals. best，f and X best，m These represent the optimal individual positions in the female and male populations, respectively. best，f and f best，m f represents the fitness function value corresponding to the optimal individual position in the female and male populations, respectively. i，m and f i，f These are the fitness function values ​​corresponding to the current iteration number and individual position of the male and female individuals, respectively.

[0158] Mating pattern location update formula:

[0159] X i，m (t+1)=X i，m (t)±c3×M m ×rand×(Q×X i，f (t)-X i，m (t));

[0160] X i，f (t+1)=X i，f (t)±c3×M f ×rand×(Q×X i，m (t)-X i，f (t));

[0161]

[0162]

[0163] Among them, X i，m and X i，f f represents the position corresponding to the current iteration number in both male and female individuals. i，m and f i，f These are the fitness function values ​​corresponding to the current iteration number and individual position of the male and female individuals, respectively.

[0164] e. After mating, determine the egg-laying pattern, identify the worst egg-laying location, and replace it with the following formula:

[0165] X worst，m =X min +rand×(X max -X min );

[0166] X worst，f =X min +rand×(X max -X min );

[0167] Among them, Xworst，m and X worst，f These represent the worst individual positions in both the male and female populations.

[0168] The above process is the basic principle of the snake optimization algorithm.

[0169] Furthermore, in one scenario, the number of target variables is set to 24, meaning that the boundary values ​​for the corresponding target variables need to be set separately.

[0170] The vehicle's basic parameters and road condition data include the vehicle's required power, the state of charge of the power battery, and the basic parameters corresponding to the fitness function.

[0171] Specifically, the execution process of iteratively updating the position of individual snakes is as follows:

[0172] Step a: Based on the cost function for multi-objectives mentioned above, initialize the snake population to obtain the fitness function value corresponding to the position of each individual in the initial state snake population;

[0173] Step b: Find the snake individuals with the lowest fitness values ​​in both the male and female populations, and take them as the best positions for the two populations respectively. Calculate the best fitness value for each position. At the same time, compare the best positions in the two populations to obtain the overall best position and calculate the best fitness value.

[0174] Step c: When food is scarce, both male and female populations update their positions by moving to the best food location, thus obtaining a new position for each individual and a new fitness value corresponding to that position.

[0175] Step d: When the food requirement is met, but the temperature requirement is not met, both male and female individuals move closer to the overall optimal individual position obtained in step b.

[0176] Step e: When both food and temperature conditions are met, the two modes of fighting and mating will randomly occur, with male and female individuals approaching each other.

[0177] Step f: After mating, query the worst individual and replace it with the new position update formula to obtain the new position;

[0178] Step g: Determine if the iteration count t meets the maximum iteration count; if it does, proceed to step h; if not, return to step b.

[0179] Step h: Output the optimal individual snake positions after iterative updates.

[0180] The fitness value determination process in step a is as follows: First, the variable array corresponding to each individual is obtained after initializing the position, and the variable array is the parameter array of the membership function; then, the independent variable values ​​of the multi-objective cost function model are obtained through simulation; finally, the fitness value under the variable array at different positions is obtained through function calculation.

[0181] In the above-described embodiments of the present invention, the membership function parameters of the fuzzy controller are optimized using the snake optimization algorithm. Considering the decay of the fuel cell and the equivalent hydrogen consumption, a fitness function based on a multi-objective Chen function model is established, thereby obtaining a reasonable output result. This invention is beneficial for improving the lifespan of the vehicle and reducing hydrogen consumption, thereby improving energy utilization and reducing operating costs.

[0182] Figure 6 This is a schematic diagram of a sub-implementation of the energy management device for fuel cell vehicles based on the snake optimization algorithm provided by the present invention.

[0183] Reference Figure 6 The present invention also provides a fuel cell vehicle energy management device based on the snake optimization algorithm, comprising:

[0184] The fuzzy controller module 601 is used to acquire the dynamic model of the fuel cell vehicle and construct a two-layer fuzzy controller for energy management and allocation of the hybrid vehicle based on the dynamic model of the fuel cell vehicle. The two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time.

[0185] The multi-objective cost function module 602 is used to establish a multi-objective cost function model based on the fuel cell life decay, fuel cell power decay and equivalent fuel consumption of the power battery, and defines the multi-objective cost module model as the fitness function of the snake optimization algorithm;

[0186] The optimization module 603 is used to obtain the membership function parameters to be optimized in the two-layer fuzzy controller, optimize the membership function based on the snake optimization algorithm, and obtain the energy management scheme of fuel cell vehicle.

[0187] The beneficial effects of the above embodiments are as follows: the fuzzy controller module 601 constructs a two-layer fuzzy controller for energy management and allocation of hybrid electric vehicles based on the dynamic model of fuel cell vehicles. The two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time, thereby reducing the average power output of the fuel cell and reducing the degradation of the fuel cell. The multi-objective cost function module 602 establishes a multi-objective cost function model based on the fuel cell life degradation, the fuel cell power degradation and the equivalent fuel consumption of the power battery. The optimization module 603 obtains the membership function parameters to be optimized in the two-layer fuzzy controller and optimizes the membership function based on the snake optimization algorithm, thereby optimizing the fuel cell energy management scheme and improving the vehicle's durability while meeting the requirements of economy.

[0188] Accordingly, this application also provides a computer-readable storage medium for storing computer-readable programs or instructions. When the programs or instructions are executed by a processor, they can implement the steps or functions of the fuel cell vehicle energy management method based on the snake optimization algorithm provided in the above-described method embodiments.

[0189] The above embodiments provide a fuel cell vehicle energy management method based on the snake optimization algorithm, which can realize the technical solutions described in the above embodiments of the fuel cell vehicle energy management device based on the snake optimization algorithm. The specific implementation principles of each module or unit can be found in the corresponding content of the rolling bearing fault diagnosis device embodiment, which will not be repeated here.

[0190] The energy management device for fuel cell vehicles based on the snake optimization algorithm provided by the present invention has been described in detail above. Specific examples have been used to illustrate the principle and implementation of the present invention. The description of the above embodiments is only for the purpose of helping to understand the method and core idea of ​​the present invention. At the same time, for those skilled in the art, there will be changes in the specific implementation and application scope based on the idea of ​​the present invention. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for energy management of fuel cell vehicles based on snake optimization algorithm, characterized in that, include: A dynamic model of a fuel cell vehicle is obtained, and a two-layer fuzzy controller for energy management and distribution of hybrid electric vehicles is constructed based on the dynamic model of the fuel cell vehicle. The two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time. A multi-objective cost function model is established based on the fuel cell life decay, fuel cell power decay, and equivalent fuel consumption of the power battery, and the multi-objective cost modulus model is defined as the fitness function of the snake optimization algorithm. Obtain the membership function parameters to be optimized in the two-layer fuzzy controller, optimize the membership function based on the snake optimization algorithm, and obtain the energy management scheme of the fuel cell vehicle; The two-layer fuzzy controller for energy management and distribution of hybrid vehicles, constructed based on the dynamic model of the fuel cell vehicle, includes: The first-layer fuzzy controller is constructed based on the vehicle's required power and the state of charge of the power battery, and a fuzzy subset of the first-layer fuzzy controller is obtained. A second-layer fuzzy controller is constructed based on the difference between the vehicle's output power and the target efficiency power of the fuel cell and the state of charge of the power battery, thus obtaining a fuzzy subset of the second-layer fuzzy controller. Empirical rule reasoning is performed based on the fuzzy subsets of the first-layer fuzzy controller and the fuzzy subsets of the second-layer fuzzy controller to form a fuzzy rule base; The first-layer fuzzy controller is constructed based on the vehicle's power demand and the state of charge of the power battery, resulting in a fuzzy subset of the first-layer fuzzy controller, including: The vehicle's power demand and the battery's state of charge are used as input variables for the first-layer fuzzy controller, and the fuel cell's output power is used as the output variable for the first-layer fuzzy controller. The required power interval of the vehicle is fuzzified to obtain several first fuzzy subsets in the discrete domain of required power; The state of charge interval of the power battery is fuzzified to obtain several second fuzzy subsets in the discrete domain of the state of charge of the power battery. The output power interval of the fuel cell is fuzzified to obtain several third fuzzy subsets in the discrete domain of the fuel cell output power. A second-layer fuzzy controller is constructed based on the difference between the vehicle's output power and the fuel cell's target efficiency power, and the state of charge of the power battery. This results in a fuzzy subset of the second-layer fuzzy controller, including: The difference between the output power of the fuel cell and the target efficiency power of the fuel cell and the state of charge of the power battery are used as input variables of the second-layer fuzzy controller, and the fuel cell output power correction coefficient is used as the output variable of the second-layer fuzzy controller. The difference between the output power of the fuel cell and the target efficiency power of the fuel cell is divided into intervals and fuzzified to obtain several fourth fuzzy subsets in the discrete domain of demand power. The state of charge interval of the power battery is fuzzified to obtain several fifth fuzzy subsets in the discrete domain of the state of charge of the power battery. The correction coefficient range of fuel cell output power is fuzzified to obtain several sixth fuzzy subsets in the discrete domain of fuel cell output power.

2. The energy management method for fuel cell vehicles based on snake optimization algorithm according to claim 1, characterized in that, The expression for the dynamic model of the fuel cell vehicle is as follows: ； ； in, Indicates the vehicle's required power. Indicates the vehicle's speed. Indicates motor efficiency. Indicates the efficiency of the transmission system. Indicates vehicle weight. Represents gravitational acceleration. Indicates the rolling resistance coefficient. Indicates the road slope angle. The value represents the air resistance coefficient, and A represents the vehicle's frontal area. This represents the rotational mass conversion factor. Indicates vehicle acceleration. Indicates the output power of the fuel cell system. This indicates the power of the battery.

3. The energy management method for fuel cell vehicles based on snake optimization algorithm according to claim 1, characterized in that, Its features are, The membership functions to be optimized in the two-layer fuzzy controller include: The fourth membership function corresponding to the difference between the output power of the fuel cell and the target efficiency power of the fuel cell is determined based on the aforementioned several fourth fuzzy subsets; The fifth membership function corresponding to the state of charge of the power battery is determined based on the aforementioned plurality of fifth fuzzy subsets; The sixth membership function corresponding to the fuel cell output power correction coefficient is determined based on the aforementioned sixth fuzzy subsets.

4. The energy management method for fuel cell vehicles based on the snake optimization algorithm according to claim 3, characterized in that, The optimization of the membership function based on the snake optimization algorithm to obtain the energy management scheme for the fuel cell vehicle includes: Based on the intersection of the segment lines of the fourth, fifth, and sixth membership functions, determine the unknown variables belonging to the fourth, fifth, and sixth membership functions. Initialize the basic parameters of the snake optimization algorithm, including the number of snakes, the number of females, the number of males, the maximum number of iterations, and the boundary of the objective variable; Based on the boundary of the target variable, the position of each individual in the initial snake population is determined, so that each individual snake represents a different target variable; Based on working condition data, and combined with snake optimization algorithm, the current position of each individual snake in the snake population is updated iteratively to obtain the optimal target variable value; The optimal target variable value is used to optimize the membership function parameters to be optimized in the two-layer fuzzy controller, and the target control result of the fuzzy controller output is obtained.

5. The energy management method for fuel cell vehicles based on snake optimization algorithm according to claim 4, characterized in that, The target variable includes the unknown variables of the fourth membership function, the unknown variables of the fifth membership function, and the unknown variables of the sixth membership function.

6. A fuel cell vehicle energy management device based on snake optimization algorithm, characterized in that, include: A fuzzy controller module is used to acquire the dynamic model of the fuel cell vehicle and construct a two-layer fuzzy controller for energy management and allocation of the hybrid vehicle based on the dynamic model of the fuel cell vehicle. The two-layer fuzzy controller is used to allocate the output power of the fuel cell system and the power battery system in real time. The multi-objective cost function module is used to establish a multi-objective cost function model based on the fuel cell life decay, fuel cell power decay, and equivalent fuel consumption of the power battery, and the multi-objective cost modulus model is defined as the fitness function of the snake optimization algorithm. An optimization module is used to obtain the membership function parameters to be optimized in the two-layer fuzzy controller, optimize the membership function based on the snake optimization algorithm, and obtain the energy management scheme of the fuel cell vehicle. The two-layer fuzzy controller for energy management and distribution of hybrid vehicles, constructed based on the dynamic model of the fuel cell vehicle, includes: The first-layer fuzzy controller is constructed based on the vehicle's required power and the state of charge of the power battery, and a fuzzy subset of the first-layer fuzzy controller is obtained. A second-layer fuzzy controller is constructed based on the difference between the vehicle's output power and the target efficiency power of the fuel cell and the state of charge of the power battery, thus obtaining a fuzzy subset of the second-layer fuzzy controller. Empirical rule reasoning is performed based on the fuzzy subsets of the first-layer fuzzy controller and the fuzzy subsets of the second-layer fuzzy controller to form a fuzzy rule base; The first-layer fuzzy controller is constructed based on the vehicle's power demand and the state of charge of the power battery, resulting in a fuzzy subset of the first-layer fuzzy controller, including: The vehicle's power demand and the battery's state of charge are used as input variables for the first-layer fuzzy controller, and the fuel cell's output power is used as the output variable for the first-layer fuzzy controller. The required power interval of the vehicle is fuzzified to obtain several first fuzzy subsets in the discrete domain of required power; The state of charge interval of the power battery is fuzzified to obtain several second fuzzy subsets in the discrete domain of the state of charge of the power battery. The output power interval of the fuel cell is fuzzified to obtain several third fuzzy subsets in the discrete domain of the fuel cell output power. A second-layer fuzzy controller is constructed based on the difference between the vehicle's output power and the fuel cell's target efficiency power, and the state of charge of the power battery. This results in a fuzzy subset of the second-layer fuzzy controller, including: The difference between the output power of the fuel cell and the target efficiency power of the fuel cell and the state of charge of the power battery are used as input variables of the second-layer fuzzy controller, and the fuel cell output power correction coefficient is used as the output variable of the second-layer fuzzy controller. The difference between the output power of the fuel cell and the target efficiency power of the fuel cell is divided into intervals and fuzzified to obtain several fourth fuzzy subsets in the discrete domain of demand power. The state of charge interval of the power battery is fuzzified to obtain several fifth fuzzy subsets in the discrete domain of the state of charge of the power battery. The correction coefficient range of fuel cell output power is fuzzified to obtain several sixth fuzzy subsets in the discrete domain of fuel cell output power.

Images