Fuel cell vehicle power system SOC track rapid planning method, system, device and medium

Abstract

The invention belongs to the technical field of traffic transportation, and discloses a fuel cell vehicle power system SOC track rapid planning method, system and device, and a medium, and the method comprises the steps: obtaining the current starting and ending point coordinate data of a vehicle and the real-time traffic flow data of each road section; inputting the current starting and ending point coordinate data and the real-time traffic flow data of each road section into a driving power prediction model for classified prediction, and outputting the average driving power of each road section; according to the distribution of the average driving power of each road section, selecting the average power of the fuel cell system of each road section as a decision variable, and constructing a global optimization problem by taking the minimum fuel consumption as an optimization target; and solving the global optimization problem, and calculating the SOC variation of each road section corresponding to the average power of the fuel cell system of each road section to obtain a current global reference SOC trajectory. The SOC track rapid planning method does not depend on excessive urban traffic characteristics, and the SOC track rapid planning method is small in calculation amount and high in real-time performance.

Description

Technical Field

[0001] The present invention belongs to the technical field of transportation, and particularly relates to a method, system, device and medium for quickly planning the SOC trajectory of a fuel cell vehicle power system. Background Art

[0002] Fuel cell vehicles have the advantages of fast fuel filling and zero emissions, and are an important development direction of new energy vehicles. However, there are still problems with unreasonable energy distribution on the global time scale in the fuel cell vehicle power system. As a method for guiding the multi-time scale power distribution of the power source, in recent years, the fuel cell vehicle energy management method combined with the global reference SOC trajectory planning has received extensive attention.

[0003] At present, the main methods for planning the SOC trajectory of the fuel cell vehicle power system are as follows: dividing kinematic segments according to historical travel data, extracting kinematic segment features and clustering, and establishing a Markov state transition matrix offline; before the vehicle runs, constructing a global driving condition according to the Markov state transition matrix, and using the dynamic programming algorithm to solve the global reference SOC trajectory. However, the actual urban conditions are highly complex and random, and the constructed global conditions sometimes cannot reflect the actual condition characteristics; in addition, limited by the characteristics of the fuel cell vehicle power system, the number of state variables in the solution process of this method is usually not less than two, the number of state points is large, and the solution time is long, making it difficult to be applied in real time. Summary of the Invention

[0004] The purpose of the present invention is to provide a method, system, device and medium for quickly planning the SOC trajectory of a fuel cell vehicle power system to solve the problems existing in the above-mentioned prior art.

[0005] To achieve the above object, the present invention provides a method for quickly planning the SOC trajectory of a fuel cell vehicle power system, including: Obtaining the current starting and ending point coordinate data of the vehicle and the real-time traffic flow data of each road section; Inputting the current starting and ending point coordinate data and the real-time traffic flow data of each road section into a driving power prediction model for classification prediction, and outputting the average driving power of each road section; wherein, the driving power prediction model is constructed based on a neural network; According to the distribution of the average driving power of each road section, selecting the average power of the fuel cell system of each road section as a decision variable, taking the minimum fuel consumption as an optimization target, and constructing a global optimization problem based on the decision variable, optimization target and preset constraint conditions; Solving the global optimization problem, calculating the SOC change amount of each road section corresponding to the average power of the fuel cell system of each road section, and obtaining the current global reference SOC trajectory.

[0006] Optionally, the training process of the driving power prediction model specifically includes: Obtaining vehicle driving data and road traffic flow data under different urban working conditions, and determining the traffic characteristics of urban road sections based on the acquired driving data and road traffic flow data; Construct a fuel cell vehicle power system model to calculate the required power of the fuel cell vehicle, and construct a fuel cell vehicle power demand model based on the required power; calculate the average driving power of each historical road section based on the fuel cell vehicle power demand model, and establish a corresponding relationship between the average driving power of the road section and the traffic characteristics of the road section; According to the corresponding relationship between the average driving power of the road section and the traffic characteristics of the road section, the BP neural network is trained offline to obtain the driving power prediction model.

[0007] Optionally, the traffic characteristics of the urban road section include the average vehicle speed of the road section, the number of lanes in the road section, and the density of traffic intersections in the road section.

[0008] Optionally, the average driving power of each historical road section is calculated using the following formula: ; Where, P dem (t) express t Drive power demand at all times, t start Indicates that the vehicle is entering the road section k The corresponding time step, t end Indicates that the vehicle has exited the road section k The corresponding time step; P ave,k represents the average driving power of the road section, t k Indicates the estimated travel time of the road section.

[0009] Optionally, the global optimization problem is specifically: ; Where F is the objective function, Represents the mapping relationship between the fuel cell system output power and the fuel cell system efficiency; t k Indicates the estimated travel time of the road section. D Indicates the number of road sections. Indicates road section k The corresponding fuel cell system output power.

[0010] Optionally, the global optimization problem is solved based on a genetic algorithm.

[0011] A fuel cell vehicle power system SOC trajectory rapid planning system, comprising: A data acquisition module, configured to obtain the current starting and ending point coordinate data of the vehicle and the real-time traffic flow data of each road section; A driving power prediction module, configured to input the current starting and ending point coordinate data and the real-time traffic flow data of each road section into a driving power prediction model for classification prediction, and output the average driving power of each road section; wherein, the driving power prediction model is constructed based on a neural network; A reference SOC trajectory planning module, configured to select the average power of the fuel cell system of each road section as a decision variable according to the distribution of the average driving power of each road section, take the minimum fuel consumption as an optimization goal, and construct a global optimization problem based on the decision variable, the optimization goal and preset constraint conditions; solve the global optimization problem, calculate the SOC change amount of each road section corresponding to the average power of the fuel cell system of each road section, and obtain the current global reference SOC trajectory.

[0012] An electronic device, comprising a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the method for quickly planning the SOC trajectory of a fuel cell vehicle power system as described above.

[0013] A computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, it implements the method for quickly planning the SOC trajectory of a fuel cell vehicle power system as described above.

[0014] The technical effects of the present invention are as follows: The urban road section average driving power prediction model proposed by the present invention fully considers the influence of the actual urban road section traffic characteristics on the driving power, and at the same time requires fewer traffic characteristics, which is convenient for real-time acquisition in an intelligent transportation system; The method for quickly planning the SOC trajectory of a fuel cell vehicle power system proposed by the present invention does not depend on the constructed global working conditions, solves the problems of large state quantity dimension and long state point traversal time in the traditional global reference SOC trajectory solution, and this method has a small operation burden and good real-time performance. Description of the Drawings

[0015] 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 to be used in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained according to these drawings.

[0016] The drawings constituting a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation to this application. In the drawings: Figure 1 This is the flowchart for obtaining traffic characteristics of urban sections in the embodiments of the present invention; Figure 2 This is the schematic diagram of the average driving power prediction model for urban sections in the embodiments of the present invention; Figure 3 This is the algorithm flowchart of the method for rapid planning of the SOC trajectory of the power system of a fuel cell vehicle in the embodiments of the present invention; Figure 4 This is the flowchart of the rapid planning implementation in the embodiments of the present invention. Detailed implementation manners

[0017] Now, various exemplary implementation manners of the present invention will be described in detail. This detailed description should not be regarded as a limitation of the present invention, but should be understood as a more detailed description of certain aspects, characteristics, and implementation schemes of the present invention.

[0018] It should be understood that the terms described in the present invention are only for describing specific implementation manners and are not used to limit the present invention. Additionally, for the numerical ranges in the present invention, it should be understood that each intermediate value between the upper and lower limits of the range is also specifically disclosed. Each intermediate value within any stated value or stated range, as well as each smaller range between any other stated value or intermediate value within the stated range, is also included in the present invention. The upper and lower limits of these smaller ranges may be independently included or excluded from the range.

[0019] Without departing from the scope or spirit of the present invention, various improvements and changes can be made to the specific implementation manners of the description of the present invention, which are obvious to those skilled in the art. Other implementation manners obtained from the description of the present invention are obvious to those skilled in the art. The description and embodiments of the present application are only exemplary.

[0020] Regarding the terms "comprising", "including", "having", "containing", etc. used herein, they are all open-ended terms, that is, they are meant to include but not be limited to.

[0021] It should be noted that, without conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the drawings and in combination with the embodiments.

[0022] Such as Figure 1 - Figure 4As shown in the figure, in this embodiment, a method for quickly planning the SOC trajectory of a fuel cell vehicle power system is provided, including: obtaining the current starting and ending point coordinate data of the vehicle and the real-time traffic flow data of each road section; inputting the current starting and ending point coordinate data and the real-time traffic flow data of each road section into a driving power prediction model for classification prediction, and outputting the average driving power of each road section; wherein, the driving power prediction model is constructed based on a neural network; according to the distribution of the average driving power of each road section, selecting the average power of the fuel cell system of each road section as a decision variable, taking the minimum fuel consumption as an optimization goal, and constructing a global optimization problem based on the decision variable, the optimization goal and preset constraint conditions; solving the global optimization problem, calculating the SOC change amount of each road section corresponding to the average power of the fuel cell system of each road section, and obtaining the current global reference SOC trajectory.

[0023] This embodiment discloses an average driving power prediction model for urban road sections and a method for quickly planning the SOC trajectory of a vehicle hybrid power system. The average driving power prediction model for urban road sections is: collecting the driving data and traffic flow data of actual urban condition vehicles, and offline training a BP neural network according to the corresponding relationship between the average driving power demand of historical driving road sections and road section traffic characteristics to construct an average driving power prediction model for urban road sections; the method for quickly planning the SOC trajectory of the vehicle hybrid power system is: constructing a global optimization problem with the minimum fuel consumption as the optimization goal according to the average driving power prediction results of each road section and the characteristics of the fuel cell vehicle power system; using a global optimization algorithm to solve the average power of the fuel cell system of each road section and calculating the SOC change amount corresponding to each road section; the above SOC trajectory is the global reference SOC trajectory under real-time traffic characteristics.

[0024] This embodiment improves the rationality of the power distribution of the fuel cell vehicle power source in the global time scale range and the real-time performance of the existing global reference SOC trajectory planning method by predicting the driving power distribution of the driving road section in advance and quickly planning the global reference SOC trajectory.

[0025] This embodiment specifically includes the following steps: Step 1: Collection of urban condition driving data and road section traffic flow data: The driving data includes vehicle driving speed and longitude and latitude coordinates, and the data sampling step is 1 s; the road section traffic flow data includes road section length, road section average vehicle speed, road section lane number and road section traffic intersection number; Step 2: Establishment of a fuel cell vehicle power system model: The vehicle power system model is composed of parts such as a fuel cell system model, a lithium battery model, a drive motor, a DC / DC converter, a DC / AC converter and a mechanical transmission system; Step 3: Establishment of a fuel cell vehicle demand power model: According to the vehicle longitudinal dynamics equation, establish a motor speed torque model and a demand power model; Step 4. Select traffic characteristics of urban road segments: The selected traffic characteristics include: average speed of the road segment, number of lanes of the road segment, and traffic intersection density of the road segment; Step 5. According to the demand power model of the fuel cell vehicle, calculate the average driving power of each historical road segment, and establish the corresponding relationship between the average driving power of the road segment and the traffic characteristics of the road segment; Step 6. According to the corresponding relationship between the average driving power of the road segment and the traffic characteristics of the road segment, offline train a BP neural network to construct a prediction model for the average driving power of urban road segments; Step 7. Before the vehicle travels, input the starting and ending point coordinates, obtain the real-time traffic flow data of each road segment, and predict the average driving power of each road segment according to the prediction model of the average driving power of urban road segments; Step 8. According to the distribution of the average driving power of each road segment, select the average power of the fuel cell system of each road segment as the decision variable, and the minimum fuel consumption as the optimization goal to construct a global optimization problem; Step 9. Use a global optimization algorithm to solve the above global optimization problem, and calculate the SOC change amount of each road segment corresponding to the average power of the fuel cell system of each road segment, which is the global reference SOC trajectory under the current traffic characteristics.

[0026] Implementable, the driving data acquisition device in Step 1 above is a FDISYSTEMS high-precision inertial satellite navigation device, and the device sampling frequency is 1Hz; the traffic flow information acquisition platform selects the Baidu Map Open Platform, and the traffic flow information acquisition steps are: authenticate the developer mode for subsequent API service requests; input the longitude and latitude coordinates of the vehicle's travel starting and ending points and the road segment segmentation rules; output the traffic flow information of each road segment, including the road segment length, estimated travel time, etc.; Implementable, the fuel cell system in Step 2 above is a proton exchange membrane fuel cell system, and the hydrogen consumption of the fuel cell system is calculated by Equation (1): (1) In the formula, I FC_stack represents the stack current, N cell represents the number of monomers, represents the molar mass of hydrogen, F represents the Faraday constant, represents the hydrogen consumption rate.

[0027] The efficiency of the fuel cell system is calculated by the following formula: (2) (3) In the formula, P FCS represents the net output power of the fuel cell system, Paux Indicates the system accessory power, LHV(H 2 ) Indicates the calorific value of hydrogen; The constructed lithium battery model, the battery current is calculated by the following formula: (4) Battery SOC Calculated by the following formula: (5) Where, U oc Indicates the battery open circuit voltage, R b Represents the equivalent internal resistance of the battery, SOC 0 Indicates the initial SOC of the battery, Q b Indicates the capacity of the battery; It is feasible that the longitudinal dynamics of the vehicle in step 3 above is as follows: (6) Where, 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 (7): (7) Where, r Indicates the wheel radius; Motor speed ω m and motor torque T m Calculated from formula (8): (8) Where, η fd Indicates the transmission efficiency of the transmission device, R fd Indicates the gear ratio; Motor power P m and the required power P dem are calculated by equations (9) and (10) respectively: (9) (10) In the formula, η m represents the motor efficiency, η DC / AC represents the DC / AC converter efficiency; Implementable, in step four above, the number of lanes k Number of lanes n k takes values as: integers within the interval [1, 4]. This traffic characteristic is used to characterize the road level of urban sections. The larger the value of the section n k value, the more it indicates that the section k is the main urban road; Average vehicle speed of the section v ave,k is defined as in equation (11): (11)<x In the formula, L k represents the section length, t k represents the estimated travel time of the section; Traffic intersection density of the section λ k represents the number of traffic intersections per unit length and is defined as in equation (12): (12) m k represents the number of traffic intersections of the section.

[0028] Implementable, the average driving power of the section in step five above P ave,k is defined as in equation (13): (13) In the formula, P dem (t) represents t the driving power demand at time t start represents the time step when the vehicle enters the section k corresponding to, t end represents the time when the vehicle exits the section<x kThe corresponding time step; It is feasible that the neural network structure in the above step 6 includes: an input layer, a hidden layer, and an output layer, the number of hidden layers is 1, and the number of hidden layer nodes is 7; The calculation formula from input layer to hidden layer is feasible as shown in formula (14): (14) Where, f h (·) represents the activation function between the input layer and the hidden layer of the BP neural network, θ represents the hidden layer bias, n represents the threshold of the input layer neurons, m represents the hidden layer neuron threshold; The calculation formula from hidden layer to output layer is feasible as shown in formula (15): (15) Where, f o (·) represents the activation function between the hidden layer and the output layer of the BP neural network, λ represents the output layer bias, t represents the output layer neuron threshold; The weight iterative update is as shown in formula (16) (16) Where, E Indicates the error between the final result and the expected result. μ is the proportionality coefficient; The input variables and output variables of the above BP neural network prediction model are defined as follows: (17) (18) Where, P ave，k Indicates road section k Average drive power; It is feasible that the decision variables of the global optimization problem in the above step eight are formula (19): (19) Where, D Indicates the number of road sections. P FC_ave,k Indicates road section k The corresponding average power of the fuel cell system; The objective function of the optimization problem is formula (20): (20) Where, Represents the mapping relationship between the output power of the fuel cell system and the efficiency of the fuel cell system; Represents a decision variable, that is, the average power of the fuel cell system corresponding to section k.

[0029] The constraint conditions of the optimization problem are expressed by equations (21)-(22): (21) (22) In the formula, Represents the predicted value of the average driving power of section k; Implementable, in the above step nine, the global optimization algorithm is a genetic algorithm, the number of algorithm iterations is 100, the population size is 30, the crossover probability is 0.8, and the mutation probability is 0.1; section k corresponding SOC The change amount is expressed by equation (23): (23) In the formula, Represents the optimal value of the decision variable, that is, when the objective function value is the smallest, the average power of the fuel cell system corresponding to section k.

[0030] Compared with the existing urban section average driving power prediction model and the fuel cell vehicle power system SOC trajectory rapid planning method, the effects of this embodiment are as follows: The urban section average driving power prediction model proposed in this embodiment fully considers the influence of the actual urban section traffic characteristics on the driving power, and at the same time requires fewer traffic characteristics, which is convenient for real-time acquisition in the intelligent transportation system; the fuel cell vehicle power system SOC trajectory rapid planning method proposed in this embodiment does not rely on the constructed global working conditions, solves the problems of large state quantity dimension and long state point traversal time in the traditional global reference SOC trajectory solution, and this method has a small operation burden and good real-time performance.

[0031] Implementable, this embodiment also provides a fuel cell vehicle power system SOC trajectory rapid planning system, including: A data acquisition module for obtaining the current starting and ending point coordinate data of the vehicle and the real-time traffic flow data of each section; A driving power prediction module for inputting the current starting and ending point coordinate data and the real-time traffic flow data of each section into the driving power prediction model for classification prediction, and outputting the average driving power of each section; wherein, the driving power prediction model is constructed based on a neural network; A reference SOC trajectory planning module is used to select the average power of the fuel cell system for each section as the decision variable according to the distribution of the average driving power of each section, with the minimum fuel consumption as the optimization goal. Based on the decision variable, optimization goal, and preset constraint conditions, a global optimization problem is constructed; the global optimization problem is solved, and the SOC change amount of each section corresponding to the average power of the fuel cell system for each section is calculated to obtain the current global reference SOC trajectory.

[0032] Implementable, this embodiment also provides an electronic device, including a memory and a processor. The memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute the SOC trajectory rapid planning method for a fuel cell vehicle power system described above.

[0033] Implementable, this embodiment also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the SOC trajectory rapid planning method for a fuel cell vehicle power system described above is implemented.

[0034] As mentioned above, the above is only a preferred specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed by the present application should be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A method for rapid planning of the SOC trajectory of a fuel cell vehicle power system, characterized in that Including: Obtain the current starting and ending point coordinate data of the vehicle and the real-time traffic flow data of each road section; Input the current starting and ending point coordinate data and the real-time traffic flow data of each road section into the driving power prediction model for classification prediction, and output the average driving power of each road section; wherein, the driving power prediction model is constructed based on a neural network; According to the distribution of the average driving power of each road section, select the average power of the fuel cell system of each road section as the decision variable, take the minimum fuel consumption as the optimization goal, and construct a global optimization problem based on the decision variable, optimization goal and preset constraint conditions; Solve the global optimization problem, calculate the SOC change amount of each road section corresponding to the average power of the fuel cell system of each road section, and obtain the current global reference SOC trajectory.

2. A method for rapid planning of the SOC trajectory of a fuel cell vehicle power system according to claim 1, characterized in that, The training process of the driving power prediction model specifically includes: Obtain the driving data of the vehicle and the road section traffic flow data under different urban conditions, and determine the urban road section traffic characteristics based on the obtained driving data and road section traffic flow data; Construct a fuel cell vehicle power system model to calculate the required power of the fuel cell vehicle, and construct a fuel cell vehicle required power model based on the required power; according to the fuel cell vehicle required power model, calculate the average driving power of each historical road section, and establish the corresponding relationship between the average driving power of the road section and the road section traffic characteristics; According to the corresponding relationship between the average driving power of the road section and the road section traffic characteristics, offline train a BP neural network to obtain the driving power prediction model.

3. A method for quickly planning the SOC trajectory of a fuel cell vehicle power system according to claim 2, characterized in that, The urban road section traffic characteristics include the average vehicle speed of the road section, the number of lanes of the road section, and the traffic intersection density of the road section.

4. A method for rapid SOC trajectory planning of a fuel cell vehicle power system according to claim 2, characterized in that, The calculation of the average driving power of each historical road section, the specific calculation formula is: ； Wherein, P dem (t) represents t the driving power demand at a moment, t start represents the time step corresponding to the vehicle entering the road section k ; t end represents the time step corresponding to the vehicle leaving the road section k ; P ave,k represents the average driving power of the road section, t k represents the estimated passing time of the road section.

5. A method for rapid planning of the SOC trajectory of a fuel cell vehicle power system according to claim 1, characterized in that, The global optimization problem is specifically: ； Wherein, F is the objective function, represents the mapping relationship between the output power of the fuel cell system and the efficiency of the fuel cell system; t k represents the expected travel time of the road section, D represents the number of road sections, represents the decision variable, that is, the road section k corresponding output power of the fuel cell system.

6. The rapid SOC trajectory planning method for the power system of a fuel cell vehicle according to claim 1, wherein Solve the global optimization problem based on a genetic algorithm.

7. A rapid SOC trajectory planning system for the power system of a fuel cell vehicle, characterized in that, Including: A data acquisition module for obtaining the current starting and ending point coordinate data of the vehicle and the real-time traffic flow data of each road section; A driving power prediction module for inputting the current starting and ending point coordinate data and the real-time traffic flow data of each road section into the driving power prediction model for classification prediction, and outputting the average driving power of each road section; wherein, the driving power prediction model is constructed based on a neural network; A reference SOC trajectory planning module for selecting the average power of the fuel cell system of each road section as the decision variable according to the distribution of the average driving power of each road section, taking the minimum fuel consumption as the optimization goal, and constructing a global optimization problem based on the decision variable, optimization goal and preset constraint conditions; solving the global optimization problem, calculating the SOC change amount of each road section corresponding to the average power of the fuel cell system of each road section, and obtaining the current global reference SOC trajectory.

8. An electronic device, characterized in that, Including a memory and a processor, the memory is used to store a computer program, and the processor runs the computer program to enable the electronic device to execute a method for quickly planning the SOC trajectory of a fuel cell vehicle power system according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, It stores a computer program, and when the computer program is executed by a processor, it implements a method for quickly planning the SOC trajectory of a fuel cell vehicle power system according to any one of claims 1-6.

Images