Fuel cell automobile energy management method, device and system and storage medium

Abstract

The invention discloses a fuel cell vehicle energy management method, device and system and a storage medium, and the method comprises the steps: S1, predicting the short-term vehicle speed through employing a long and short-term memory neural network according to the actual urban driving data; s2, according to the short-term vehicle speed, a prediction domain power demand sequence is obtained through a vehicle longitudinal dynamics model; s3, according to the prediction domain power demand sequence, a prediction domain optimization problem is constructed by taking fuel cell hydrogen consumption and life attenuation as optimization targets; and S4, solving a prediction domain optimization problem by adopting a balance optimizer EO algorithm to obtain an optimal control sequence. By the adoption of the technical scheme, the economical efficiency and the real-time performance of the fuel cell automobile energy management method can be improved, and the actual city working condition adaptability is high.

Description

Technical Field

[0001] The present invention belongs to the technical field of transportation, and particularly relates to an energy management method, device, system, and storage medium for a fuel cell vehicle. Background Art

[0002] Fuel cell vehicles have the advantages of zero emissions, long driving range, and fast fuel filling, and have become an important development direction for new energy vehicles. Under actual urban driving conditions, the operating cost of fuel cell vehicles is high, mainly including hydrogen consumption cost and power system life degradation cost. The above costs depend on the performance of the energy management method of fuel cell vehicles.

[0003] At present, the real vehicle energy management methods for fuel cell vehicles are mostly rule-based control methods. The rule parameters depend on the engineering experience of designers and are difficult to adapt to the actual complex and changeable urban traffic environment, with poor working condition adaptability. As a type of optimization-based control method, the energy management strategy combined with the MPC framework has strong working condition robustness and is widely used in the energy management technology field of fuel cell vehicles.

[0004] Traditional MPC energy management methods do not fully consider the fuel cell life attenuation cost. In addition, the optimization performance of the MPC solver affects the economy and real-time performance of the MPC energy management method. Traditional MPC solvers are mostly based on the original or simplified dynamic programming algorithm, with large computational workload for solving and potential for further improvement. Summary of the Invention

[0005] The technical problem to be solved by the present invention is to provide an energy management method, device, system, and storage medium for a fuel cell vehicle.

[0006] To achieve the above object, the present invention adopts the following technical solutions: An energy management method for a fuel cell vehicle, comprising: Step S1, predicting the short-term vehicle speed using a long short-term memory neural network according to actual urban driving data; Step S2, obtaining a predicted domain power demand sequence through a vehicle longitudinal dynamics model according to the short-term vehicle speed; Step S3, constructing a predicted domain optimization problem with fuel cell hydrogen consumption and life attenuation as optimization objectives according to the predicted domain power demand sequence; Step S4, solving the predicted domain optimization problem using the equilibrium optimizer EO algorithm to obtain an optimal control sequence.

[0007] The present invention also provides an energy management device for a fuel cell vehicle, comprising: A first processing module, configured to predict the short-term vehicle speed using a long short-term memory neural network according to actual urban driving data; A second processing module, configured to obtain a predicted-domain power demand sequence according to the short-term vehicle speed through a vehicle longitudinal dynamics model; A third processing module, configured to construct a predicted-domain optimization problem with the hydrogen consumption and life attenuation of the fuel cell as the optimization objectives according to the predicted-domain power demand sequence; A fourth processing module, configured to solve the predicted-domain optimization problem by using an Equilibrium Optimizer (EO) algorithm to obtain an optimal control sequence.

[0008] The present invention further provides a fuel cell vehicle energy management system, which is characterized by comprising a memory and a processor. A computer program is stored on the memory and run by the processor. When the computer program is run by the processor, it executes the fuel cell vehicle energy management method.

[0009] The present invention further provides a storage medium, on which a computer program is stored. When the computer program runs, it executes the fuel cell vehicle energy management method.

[0010] The present invention realizes the energy management of a fuel cell vehicle by using an Equilibrium Optimizer (EO) algorithm oriented to urban driving conditions and considering the fuel cell life, takes into account the influence of power variation on the fuel cell life, and slows down the life attenuation of the fuel cell; furthermore, it can search for an optimal control sequence under the conditions of a smaller population size and fewer iteration times, and the control method has good economy and real-time performance. Description of the Drawings

[0011] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only the embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained according to the provided drawings without creative efforts.

[0012] Figure 1 It is a flowchart of the fuel cell vehicle energy management method according to the embodiment of the present invention. Detailed Embodiments

[0013] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0014] In order to make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments.

[0015] Embodiment 1: like Figure 1 As shown, an embodiment of the present invention provides a fuel cell vehicle energy management method, comprising: Step S1: predicting short-term vehicle speed using a long short-term memory neural network based on actual urban driving data; Step S2: Obtain a prediction domain power demand sequence based on the short-term vehicle speed; Step S3: Based on the prediction domain power demand sequence, the prediction domain optimization problem is constructed with the fuel cell hydrogen consumption and life attenuation as optimization targets; Step S4: Use the balanced optimizer EO algorithm to solve the prediction domain optimization problem and obtain the optimal control sequence.

[0016] As an implementation method of the embodiment of the present invention, in step S1, the input variables of the vehicle speed prediction model are the vehicle speed at the current moment and the historical moment. The output variable of the speed prediction model is the prediction domain speed ;The vehicle speed prediction model is based on long short-term memory neural network; As an implementation method of the present invention, in step S2, the future vehicle speed is predicted based on the historical vehicle speed, and the power demand sequence of the prediction domain power system is calculated according to equations (1), (2), (3), (4) and (5). The longitudinal dynamics of the vehicle are as follows: (1) in, F t Indicates traction, m Indicates the vehicle mass, g represents the acceleration due to gravity, f represents the rolling resistance coefficient, α Indicates the road slope angle, C D represents the aerodynamic drag coefficient, A represents the frontal area of the vehicle, ρ represents the air density, v Indicates instantaneous speed; Wheel speed ω w and wheel torque T w Calculated from formula (2): (2) in, r Indicates the wheel radius; Motor speed ω m and motor torque T m Calculated from formula (3): (3) Among them η fd represents the transmission efficiency of the transmission device; R fd represents the gear transmission ratio; Motor power P m and the required power P dem are calculated by equations (4) and (5) respectively: (4) (5) Among them, η m represents the motor efficiency; η DC / AC represents DC / AC the converter efficiency.

[0017] As an implementation manner of the embodiment of the present invention, in step S3, the optimization objectives are selected as the hydrogen consumption cost, the fuel cell life degradation cost, and the prediction domain battery SOC fluctuation, corresponding to equations (6)-(8) respectively; (6) (7) (8) Among them, represents the hydrogen price; η FCS (.) represents the function of the fuel cell system efficiency with respect to the output power of the fuel cell system; C FC represents the unit power price of the fuel cell stack; P FC_rated represents the stack power; α FC_slope represents the fuel cell life attenuation rate caused by power change; U cell_limit represents the voltage attenuation threshold corresponding to the end of the service life of the fuel cell monomer; The prediction domain cost function is expressed as equation (9) (9) Select the prediction domain fuel cell system power sequence as the decision variable, and the decision variable of the prediction domain optimization problem is equation (10): (10) Among them, D is the dimension of the decision variable; The cost function of the optimization problem is given by Equation (11): (11) where θ 1 , θ 2 is a constant; The constraint condition of the optimization problem is given by Equation (12): (12) where P FC_min , P FC_max represent the minimum and maximum output powers of the fuel cell system respectively, ΔP FC_min , Δ P FC_max represent the power fluctuation limits of the fuel cell system respectively, SOC min , SOC max represent the SOC lower and upper limit values of the battery respectively; As an implementation manner of the embodiment of the present invention, the equilibrium optimizer EO algorithm in step S4 is a metaheuristic algorithm, which evaluates the dynamic state and the equilibrium state based on the control volume mass balance model.

[0018] The initial population of the algorithm is randomly generated according to the population size and the number of time steps in the prediction domain, as given by Equation (13): (13) where represents the initial fuel cell system power sequence corresponding to the individual i , C min and C max represent the minimum and maximum powers of the fuel cell system at each time step in the prediction domain respectively, r i represents a random number vector with elements in the range [0, 1], n represents the number of individuals included in the population; The randomly distributed fuel cell system power sequence is given by Equation (14): (14) The fitness value of each fuel cell system power sequence is given by Equation (15): (15) Equilibrium pool It includes the best four fuel cell system power sequences among all current fuel cell system power sequences and the arithmetic mean of the above four fuel cell system power sequences, as shown in Equation (16): (16) Where represents the arithmetic mean of the above four fuel cell system power sequences, as shown in Equation (17): (17) The exponential vector is used to balance local search and global search, as shown in Equation (18): (18) Wherein a 1 represents the global search weight coefficient, sign(.) represents the sign function, , represents a random number vector with elements in the range [0, 1], t represents a function related to the number of iterations of the prediction domain optimization problem, as shown in Equation (19): (19) Wherein a 2 is a constant, Iter represents the current number of iterations of the prediction domain optimization problem, Max_iter represents the maximum number of iterations of the prediction domain optimization problem, generating the rate vector is as shown in Equation (20): (20) Where represents the generation rate control parameter, as shown in Equation (21): (21) The fuel cell system power sequence update model is as shown in Equation (22): (22)

[0019] Example 2: The embodiment of the present invention further provides a fuel cell vehicle energy management device, including: The first processing module is used to predict the short-term vehicle speed by using a long short-term memory neural network according to the actual urban driving data; The second processing module is used to obtain the prediction domain power demand sequence through the vehicle longitudinal dynamics model according to the short-term vehicle speed; The third processing module is used to construct a prediction domain optimization problem with the fuel cell hydrogen consumption and life attenuation as the optimization objectives according to the prediction domain power demand sequence; The fourth processing module is used to solve the prediction domain optimization problem by using the Equilibrium Optimizer (EO) algorithm to obtain the optimal control sequence.

[0020] Embodiment 3: The present invention also provides a fuel cell vehicle energy management system, which is characterized by comprising a memory and a processor. A computer program run by the processor is stored on the memory, and when the computer program is run by the processor, it executes the fuel cell vehicle energy management method.

[0021] Embodiment 4: The present invention also provides a storage medium, on which a computer program is stored, and when the computer program runs, it executes the fuel cell vehicle energy management method.

[0022] The above-described embodiments are only descriptions of the preferred embodiments of the present invention, and do not limit the scope of the present invention. Without departing from the design spirit of the present invention, various deformations and improvements made by those of ordinary skill in the art to the technical solutions of the present invention shall fall within the protection scope determined by the claims of the present invention.

Claims

1. A method for energy management of a fuel cell vehicle, characterized in that, Including: Step S1: According to the actual urban driving data, use a long short-term memory neural network to predict the short-term vehicle speed; Step S2: According to the short-term vehicle speed, obtain the predicted domain power demand sequence through the vehicle longitudinal dynamics model; Step S3: According to the predicted domain power demand sequence, construct a predicted domain optimization problem with the hydrogen consumption and life attenuation of the fuel cell as the optimization objectives; Step S4: Use the Equilibrium Optimizer EO algorithm to solve the predicted domain optimization problem to obtain the optimal control sequence.

2. An energy management device for a fuel cell vehicle, characterized in that, Including: The first processing module is used to predict the short-term vehicle speed by using a long short-term memory neural network according to the actual urban driving data; The second processing module is used to obtain the predicted domain power demand sequence through the vehicle longitudinal dynamics model according to the short-term vehicle speed; The third processing module is used to construct a predicted domain optimization problem with the hydrogen consumption and life attenuation of the fuel cell as the optimization objectives according to the predicted domain power demand sequence; The fourth processing module is used to use the Equilibrium Optimizer EO algorithm to solve the predicted domain optimization problem to obtain the optimal control sequence.

3. A fuel cell vehicle energy management system, characterized in that, Including: A memory and a processor, where a computer program is stored on the memory and run by the processor, and the computer program, when run by the processor, executes the fuel cell vehicle energy management method as described in claim 1.

4. A storage medium, characterized in that, A computer program is stored on the storage medium, and the computer program, when running, executes the fuel cell vehicle energy management method as described in claim 1.

Images