Vehicle energy management method, device and equipment and storage medium
Through the prediction model trained by wavelet neural network and particle swarm optimization algorithm, the problem of lag in energy management response in dynamic scenarios is solved, efficient energy management is achieved, energy consumption is reduced and battery life is extended.
Patent Information
- Application Number
- CN202510609304.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-05-13
- Publication Date
- 2025-07-25
AI Technical Summary
The energy management strategy of traditional new energy vehicles lags in dynamic scenarios, resulting in increased energy loss and affects battery life.
The prediction model is trained using wavelet neural network and particle swarm optimization algorithm, combined with the model to predict vehicle speed and traffic, and energy management instructions are determined through the model prediction results to achieve efficient energy management in dynamic scenarios.
Improves the response speed and accuracy of the energy management system, reduces energy loss and extends battery life.
Smart Images
Figure CN120363738A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of intelligent control of new energy vehicles, and particularly to a vehicle energy management method, device, equipment, and storage medium. Background Art
[0002] The energy management technology of new energy vehicles is developing rapidly towards the direction of "global perception - intelligent prediction - collaborative optimization". Therefore, how to optimize the energy distribution of new energy vehicles to improve the driving range, reduce energy consumption, and extend the battery life of new energy vehicles is a key challenge.
[0003] Traditional energy management strategies for new energy vehicles mainly rely on static rules or short-term optimization algorithms. For example, threshold control based on state machines, fuzzy logic control, or equivalent fuel consumption minimization strategies are all passive response control strategies that only make decisions based on the vehicle state at the current moment and cannot perform forward-looking planning. In dynamic scenarios such as urban congestion, traffic signal changes, or complex terrains, this passive response characteristic often leads to a lag in the response of the new energy vehicle energy management system, resulting in unnecessary energy losses and affecting the service life of key components of new energy vehicles (such as batteries). Summary of the Invention
[0004] The present invention provides a vehicle energy management method, device, equipment, and storage medium to achieve efficient energy management of new energy vehicles in dynamic scenarios, reduce energy consumption during the driving process of new energy vehicles, and extend the service life of key components of new energy vehicles.
[0005] According to one aspect of the present invention, a vehicle energy management method is provided. The method includes:
[0006] Obtain vehicle data of a target vehicle; wherein, the vehicle data includes historical vehicle speed information and current environmental information;
[0007] Input the vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points; wherein, the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm;
[0008] Determine an energy management instruction corresponding to each future time point of the target vehicle according to the vehicle speed and traffic flow of the target vehicle at each future time point;
[0009] Manage the energy of the target vehicle according to the energy management instruction corresponding to each future time point of the target vehicle.
[0010] According to another aspect of the present invention, a vehicle energy management device is provided. The device includes:
[0011] A vehicle data acquisition module for acquiring vehicle data of a target vehicle; wherein the vehicle data includes historical vehicle speed information and current environment information;
[0012] A vehicle speed and traffic flow prediction module for inputting the vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points; wherein the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm;
[0013] An energy management instruction determination module for determining an energy management instruction corresponding to the target vehicle at each future time point according to the vehicle speed and traffic flow of the target vehicle at each future time point;
[0014] A vehicle energy management module for managing the energy of the target vehicle according to the energy management instruction corresponding to the target vehicle at each future time point.
[0015] According to another aspect of the present invention, there is provided an electronic device, the electronic device comprising:
[0016] At least one processor; and
[0017] A memory communicatively connected to the at least one processor; wherein,
[0018] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle energy management method of any embodiment of the present invention.
[0019] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the vehicle energy management method of any embodiment of the present invention when executed.
[0020] According to another aspect of the present invention, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the vehicle energy management method of any embodiment of the present invention.
[0021] The technical solution of the embodiment of the present invention includes obtaining vehicle data of a target vehicle, where the vehicle data includes historical vehicle speed information and current environment information; inputting the vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points, where the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm; determining an energy management instruction corresponding to each future time point of the target vehicle according to the vehicle speed and traffic flow of the target vehicle at each future time point; and managing the energy of the target vehicle according to the energy management instruction corresponding to each future time point of the target vehicle. The above technical solution predicts the future vehicle speed and traffic flow of the target vehicle with the help of a trained prediction model, which speeds up the prediction speed and accuracy of the future vehicle speed and traffic flow of the target vehicle, improves the response speed of the energy management system of the target vehicle to a certain extent, makes the energy management instruction determined according to the output result of the trained prediction model more accurate, and thus realizes the efficient energy management of the target vehicle in a dynamic scenario, reduces the energy loss caused by unnecessary acceleration (such as sudden acceleration or sudden deceleration) of the target vehicle, improves the energy recovery efficiency of the target vehicle, reduces the energy consumption during the driving of the target vehicle, and prolongs the service life of the key components of the target vehicle, especially the service life of the battery of the target vehicle.
[0022] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.
[0024] Figure 1A is a flowchart of a vehicle energy management method provided in Embodiment 1 of the present invention;
[0025] Figure 1B is a topological structure diagram of a wavelet neural network provided in Embodiment 1 of the present invention;
[0026] Figure 2 is a flowchart of a vehicle energy management method provided in Embodiment 2 of the present invention;
[0027] Figure 3 is a schematic structural diagram of a vehicle energy management device provided in Embodiment 3 of the present invention;
[0028] Figure 4 It is a schematic structural diagram of an electronic device for implementing the vehicle energy management method of the embodiment of the present invention. Detailed implementation manners
[0029] In order to enable those skilled in the art of the present technology to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying 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.
[0030] It should be noted that the terms "target", "first", "second", etc. in the specification and claims of the present invention and the above drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device including a series of steps or units does not necessarily need to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.
[0031] Embodiment 1
[0032] Figure 1A It is a flowchart of a vehicle energy management method provided in Embodiment 1 of the present invention. This embodiment is applicable to the situation of optimizing and controlling the energy of new energy vehicles in a dynamic scenario, especially applicable to the situation of optimizing and controlling the energy of hybrid electric vehicles (HEVs) or plug-in hybrid electric vehicles (PHEVs) in a dynamic scenario. This method can be executed by a vehicle energy management device, which can be implemented in the form of hardware and / or software and can be configured in an electronic device, and the electronic device can be a hybrid electric vehicle or a plug-in hybrid electric vehicle. As Figure 1A shown, the method includes:
[0033] S101. Obtain vehicle data of the target vehicle; wherein, the vehicle data includes historical vehicle speed information and current environment information.
[0034] Among them, the target vehicle refers to a new energy vehicle in a dynamic scenario; optionally, the target vehicle can be a hybrid vehicle or a plug-in hybrid vehicle in a dynamic scenario. The historical vehicle speed information refers to the historical vehicle speed sequence within a preset time before the current moment. The preset time can be set in advance according to actual business requirements or the experience of those skilled in the art. For example, the preset time can be 200 seconds, and the embodiments of the present invention do not make specific limitations on it. The current environmental information includes, but is not limited to, temperature, humidity, wind speed, air pressure, and traffic signal timing.
[0035] Specifically, the historical vehicle speed information of the target vehicle can be obtained through the vehicle speed acquisition device on the target vehicle, and the current environmental information of the target vehicle can be obtained through the vehicle networking.
[0036] S102. Input the vehicle data into the trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points.
[0037] Among them, the prediction model refers to a model used to predict the vehicle speed and traffic flow of the target vehicle in the future for a period of time; optionally, the prediction model is determined according to the wavelet neural network and the particle swarm optimization algorithm. Among them, the wavelet neural network (Wavelet Neural Network, WNN) is a feedforward neural network constructed based on the wavelet transform theory. Its most important feature is that the neuron activation function of its hidden layer is the wavelet basis function, and its topological structure diagram is shown in Figure 1B . It should be noted that Figure 1B X1, X2,..., X n are the input parameters of the wavelet neural network, Y1,..., Y m are the predicted outputs of the wavelet neural network, ω ij represents the weight from the input layer to the hidden layer, ω jk represents the weight from the hidden layer to the output layer, and ψ(x) represents the wavelet basis function. The particle swarm optimization algorithm (Particle Swarm Optimization, PSO) is an intelligent optimization algorithm, which has the advantages of fast convergence speed, few parameters, and simple and easy implementation.
[0038] Specifically, input the vehicle data into the trained prediction model. After being processed by the trained prediction model, the vehicle speed and traffic flow of the target vehicle at N future time points are obtained.
[0039] Optionally, the prediction model is determined based on a wavelet neural network and a particle swarm optimization algorithm. Specifically, it can be: through the particle swarm optimization algorithm, the network parameters of the wavelet neural network are optimized to obtain a prediction model composed of optimal network parameters. Among them, the network parameters include the weights from the input layer to the hidden layer, the weights from the hidden layer to the output layer, and the scaling factor and translation factor of the wavelet basis function. The optimal network parameters are the network parameters that make the model performance of the prediction model reach the optimal.
[0040] More specifically, the particle swarm size of the particle swarm optimization algorithm can be determined according to the actual business requirements and the actual number of input parameters of the wavelet neural network model; according to the expert experience of those skilled in the art, the maximum number of iterations, inertia weight, learning factor, and fitness function of the particle swarm optimization algorithm are determined respectively; count the total number of neurons in the hidden layer of the wavelet neural network, count the first connection number from the input layer to the hidden layer in the wavelet neural network, and count the second connection number from the hidden layer to the output layer in the wavelet neural network; according to the total number of neurons, the first connection number, and the second connection number, encode the network parameters (ω1, ω2, a, b) of the wavelet neural network into the position vector of each particle in the particle swarm, that is, for the i-th particle in the particle swarm, its position vector is as follows:
[0041]
[0042] Among them, pso(i) represents the position vector of the i-th particle in the particle swarm; ω1 represents the weight from the input layer to the hidden layer in the wavelet neural network; ω2 represents the weight from the hidden layer to the output layer in the wavelet neural network; a represents the scaling factor of the wavelet basis function; b represents the translation factor of the wavelet basis function; N1 represents the first connection number; N2 represents the second connection number; M represents the total number of neurons.
[0043] After that, initialize the velocity vector of each particle in the particle swarm; according to the particle swarm size, the maximum number of iterations, the inertia weight, the learning factor, the fitness function, and the position and velocity of each particle in the particle swarm, through the particle swarm optimization algorithm, obtain the optimal network parameters of the wavelet neural network; set the network parameters of the wavelet neural network model according to the optimal network parameters, so as to obtain the prediction model.
[0044] It can be understood that by optimizing the wavelet neural network through the particle swarm optimization algorithm, a prediction model is obtained, which improves the generalization ability of the prediction model and the accuracy of the prediction result of the prediction model.
[0045] It should be noted that generally, the particle swarm size of the particle swarm optimization algorithm is any integer value between [20, 50].
[0046] Among them, the training process of the prediction model is as follows: With the help of a model simulation tool, such as MATLAB or Simulink, a vehicle model is built for simulation experiments, and typical road conditions and actual urban road scenarios required in the simulation experiments are preset in advance; then, sample vehicle data is collected; the sample vehicle data is input into the prediction model to obtain the predicted vehicle speed value and the predicted traffic flow value; the actual vehicle speed value and the actual traffic flow value corresponding to the sample vehicle data are obtained; the vehicle speed error between the predicted vehicle speed value and the actual vehicle speed value is calculated, and the flow error between the predicted traffic flow value and the actual traffic flow value is calculated; if the vehicle speed error is less than or equal to the vehicle speed error threshold and the flow error is less than or equal to the traffic flow error threshold, the training of the prediction model is stopped, and the trained prediction model is obtained; otherwise, sample vehicle data is collected again, and the above training process is repeated until the vehicle speed error is less than or equal to the vehicle speed error threshold and the flow error is less than or equal to the traffic flow error threshold, and the training of the prediction model is stopped, and the trained prediction model is obtained. It should be noted that the data sampling period during the training of the prediction model is 100 milliseconds.
[0047] S103. Determine the energy management instruction corresponding to the target vehicle at each future time point according to the vehicle speed and traffic flow of the target vehicle at each future time point.
[0048] Among them, the energy management instruction refers to an instruction used to control the energy of the target vehicle; optionally, the energy management instruction includes but is not limited to a drive mode control instruction, a motor torque control instruction, an engine start instruction, an engine stop instruction, an engine speed control instruction, a battery SOC control instruction, a regenerative braking energy instruction, an air-fuel ratio control instruction, and a power distribution instruction.
[0049] Among them, the drive mode control instruction refers to an instruction used to control the power drive model of the target vehicle; the motor torque control instruction refers to an instruction used to control the motor torque of the target vehicle; the engine start instruction refers to an instruction used to control the start of the engine of the target vehicle; the engine stop instruction refers to an instruction used to control the engine of the target vehicle to stop working; the engine speed control instruction refers to an instruction used to control the engine speed of the target vehicle; the battery SOC control instruction refers to an instruction used to control the charge and discharge of the battery of the target vehicle; the regenerative braking energy instruction refers to an instruction used to control the proportion of electric braking of the target vehicle; the air-fuel ratio control instruction refers to an instruction used to control the fuel consumption and exhaust emissions of the target vehicle; the power distribution instruction refers to an instruction used to control the motor power and engine power in the target vehicle.
[0050] Specifically, for each future time point, according to the vehicle speed and traffic flow of the target vehicle at that future time point, with the help of the MPC algorithm (Model Predictive Control), the energy management instruction corresponding to the target vehicle at that future time point is determined. Among them, the MPC algorithm is a control strategy based on rolling optimization, which generates the optimal control instruction at the current moment by solving a finite-time optimal control problem in each control cycle.
[0051] It should be noted that the objective function in the MPC algorithm includes but is not limited to the fuel consumption function of the internal combustion engine (ICE), the battery protection function, the acceleration change rate limit function, and the ICE high-load operation time limit function; the constraint conditions in the MPC algorithm include but are not limited to the ICE power constraint condition, the motor power constraint condition, the boundary condition of the battery SOC, and the acceleration limit condition. Among them, the boundary condition of the battery SOC can be 20% ≤ SOC(k) ≤ 80%, where N represents the total number of future time points; SOC(k) represents the battery SOC of the target vehicle at the kth future time point.
[0052] It should also be noted that the objective function and constraint conditions in the MPC algorithm can be determined according to the expert experience of those skilled in the art or through simulation experiments. The embodiments of the present invention do not make specific limitations on them. The problem-solving method in the MPC algorithm can be determined according to actual business needs. For example, the problem-solving method in the MPC algorithm can be dynamic programming (DP) or convex optimization. The embodiments of the present invention do not make specific limitations on it.
[0053] S104. Manage the energy of the target vehicle according to the energy management instruction corresponding to the target vehicle at each future time point.
[0054] Specifically, for each future time point, manage the energy of the target vehicle by executing the energy management instruction corresponding to the target vehicle at that future time point.
[0055] The technical solution of the embodiment of the present invention includes obtaining vehicle data of a target vehicle, where the vehicle data includes historical vehicle speed information and current environment information; inputting the vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points, where the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm; determining an energy management instruction corresponding to each future time point of the target vehicle according to the vehicle speed and traffic flow of the target vehicle at each future time point; and managing the energy of the target vehicle according to the energy management instruction corresponding to each future time point of the target vehicle. The above technical solution predicts the future vehicle speed and traffic flow of the target vehicle with the help of a trained prediction model, which speeds up the prediction speed and accuracy of the future vehicle speed and traffic flow of the target vehicle, improves the response speed of the energy management system of the target vehicle to a certain extent, makes the energy management instruction determined according to the output result of the trained prediction model more accurate, and thus realizes the efficient energy management of the target vehicle in a dynamic scenario, reduces the energy loss caused by unnecessary acceleration of the target vehicle (such as sudden acceleration or sudden deceleration), reduces the energy consumption during the driving of the target vehicle, and extends the service life of the key components of the target vehicle, especially the service life of the battery of the target vehicle.
[0056] Embodiment 2
[0057] Figure 2 The flowchart of a vehicle energy management method provided by Embodiment 2 of the present invention. On the basis of the above embodiment, this embodiment further optimizes "determining an energy management instruction corresponding to each future time point of the target vehicle according to the vehicle speed and traffic flow of the target vehicle at each future time point" and provides an optional implementation solution. It should be noted that for the parts not detailed in the embodiments of the present invention, reference may be made to the relevant descriptions of other embodiments. As Figure 2 shown, the method includes:
[0058] S201. Obtain vehicle data of the target vehicle, where the vehicle data includes historical vehicle speed information and current environment information.
[0059] S202. Input the vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points, where the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm.
[0060] S203. For each future time point, obtain the road slope information corresponding to the future time point.
[0061] Among them, the road slope information refers to the information used to describe the inclination degree of the road; optionally, the road slope information includes but is not limited to the slope angle, slope percentage, slope direction, slope change rate, and slope length. Among them, the slope angle refers to the angle between the road surface and the horizontal plane, with the unit of degree or radian. The slope percentage is used to reflect the steepness of the road slope. The slope direction refers to the inclination direction of the slope, that is, the clockwise angle of the highest point of the slope surface relative to the due north direction, expressed by azimuth angle. The slope change rate is used to reflect the severity of the road undulation. The slope length refers to the horizontal projection distance between two adjacent grade change points on the road longitudinal section.
[0062] Specifically, for each future time point, the road slope information corresponding to the future time point can be extracted from the high-precision map obtained from the vehicle-to-everything network.
[0063] S204. Determine the road condition corresponding to the future time point according to the road slope information.
[0064] Among them, the road condition refers to the condition of the road. According to the geometric characteristics of the road, the road conditions can be divided into straight sections, curved sections, and slope sections; among them, the slope sections include uphill sections, downhill sections, and long downhill sections.
[0065] Specifically, the road condition corresponding to the future time point can be determined according to the slope angle and slope length in the road slope information corresponding to the future time point.
[0066] S205. Detect whether the road condition is a long downhill section.
[0067] Specifically, detect whether the road condition corresponding to the future time point is a long downhill section; if so, execute S206; otherwise, execute S207.
[0068] S206. Determine that the energy management instruction corresponding to the target vehicle at the future time point is the first battery state of charge (SOC) control instruction and the regenerative braking energy instruction.
[0069] Among them, the first battery SOC control instruction refers to the instruction used to control the battery charge and discharge of the target vehicle on the long downhill section. The regenerative braking energy instruction refers to the instruction used to control the proportion of electric braking of the target vehicle. It should be noted that after executing S206, execute S208.
[0070] S207. Determine the energy management instruction corresponding to the target vehicle at the future time point according to the vehicle speed, the first vehicle speed threshold, and the second vehicle speed threshold at the future time point.
[0071] Among them, the first vehicle speed threshold refers to the speed value used to determine whether the road is congested; optionally, the first vehicle speed threshold can be determined through simulation experiments. For example, the first vehicle speed threshold can be 10 km / h, that is, traveling 10 kilometers per hour. The second vehicle speed threshold refers to the speed value used to determine whether the driving mode of the target vehicle is the high-speed cruise mode; optionally, the second vehicle speed threshold can be determined through simulation experiments. For example, the second vehicle speed threshold can be 80 km / h, that is, traveling 80 kilometers per hour.
[0072] Specifically, it is detected whether the vehicle speed at this future time point is less than the first vehicle speed threshold; if so, it is determined that the energy management instruction corresponding to the target vehicle at this future time point is the drive mode control instruction and the second battery SOC control instruction; otherwise, it is detected whether the vehicle speed at this future time point is greater than the second vehicle speed threshold; if so, it is determined that the energy management instruction corresponding to the target vehicle at this future time point is the engine speed control instruction and the air-fuel ratio control instruction.
[0073] Among them, the drive mode control instruction refers to the instruction used to control the power drive model of the target vehicle. The second battery SOC control instruction refers to the instruction used to control the charging and discharging of the battery of the target vehicle in the case of road congestion. The engine speed control instruction refers to the instruction used to control the engine speed of the target vehicle. The air-fuel ratio control instruction refers to the instruction used to control the fuel consumption and exhaust emissions of the target vehicle. It should be noted that after executing S207, S208 is executed.
[0074] S208. Manage the energy of the target vehicle according to the energy management instruction corresponding to the target vehicle at each future time point.
[0075] Specifically, for each future time point, if it is determined that the energy management instruction corresponding to the target vehicle at this future time point is the first battery SOC control instruction and the regenerative braking energy recovery instruction, then control the hybrid execution unit on the target vehicle to execute the first battery SOC control instruction, adjust the battery SOC of the target vehicle to the first SOC value, and control the hybrid execution unit to execute the regenerative braking energy recovery instruction to adjust the electric braking proportion of the target vehicle; if it is determined that the energy management instruction corresponding to the target vehicle at this future time point is the drive mode control instruction and the second battery SOC control instruction, then control the hybrid execution unit to execute the drive mode control instruction, switch the power drive mode of the target vehicle to the pure electric mode, and control the hybrid execution unit to execute the second battery SOC control instruction to adjust the battery SOC of the target vehicle to the second SOC value; if it is determined that the energy management instruction corresponding to the target vehicle at this future time point is the engine speed control instruction and the air-fuel ratio control instruction, then control the hybrid execution unit to execute the engine speed control instruction, control the engine speed of the target vehicle within the target speed range, and control the hybrid execution unit to execute the air-fuel ratio control instruction to adjust the air-fuel ratio of the target vehicle.
[0076] Among them, the hybrid execution unit is a key component in a hybrid vehicle, used to coordinate and manage the energy flow and power distribution between the engine, motor, and battery. The first SOC value refers to the battery SOC value of the target vehicle on a long downhill section; the second SOC value refers to the battery SOC value of the target vehicle in a traffic congestion situation. Both the first SOC value and the second SOC value can be determined based on experimental experience. For example, the first SOC value can be 70% or 75%, and the second SOC value can be 45%. The target speed range refers to a pre-set speed range. For example, the target speed range can be [2000 rpm, 2500 rpm]. Among them, rpm (Revolutions Per minute, revolutions per minute) is the speed unit, indicating the number of revolutions per minute.
[0077] Among them, controlling the hybrid execution unit to execute the regenerative braking energy recovery instruction to adjust the electric braking proportion of the target vehicle can be specifically: controlling the hybrid execution unit to execute the regenerative braking energy recovery instruction, and adjusting the electric braking proportion of the target vehicle to 70% to ensure the highest energy recovery efficiency of the target vehicle on a long downhill section.
[0078] Among them, switching the power drive mode of the target vehicle to the pure electric mode means that at this time, the target vehicle is only driven by the motor powered by the battery, and the engine does not participate in the work, so as to avoid the high fuel consumption operation of the engine at idle speed or low speed, reduce the fuel consumption of the target vehicle in a traffic congestion situation, and reduce exhaust emissions.
[0079] The technical solution of the embodiment of the present invention includes: obtaining vehicle data of a target vehicle, where the vehicle data includes historical vehicle speed information and current environment information; inputting the vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points, where the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm; for each future time point, obtaining the road slope information corresponding to the future time point; determining the road condition corresponding to the future time point according to the road slope information; detecting whether the road condition is a long downhill condition; if so, determining that the energy management instruction corresponding to the target vehicle at the future time point is a first battery SOC control instruction and a braking energy recovery instruction; otherwise, determining the energy management instruction corresponding to the target vehicle at the future time point according to the vehicle speed, a first vehicle speed threshold, and a second vehicle speed threshold at the future time point; and managing the energy of the target vehicle according to the energy management instruction corresponding to the target vehicle at each future time point. The above technical solution predicts the future vehicle speed and traffic flow of the target vehicle with the help of a trained prediction model, which speeds up the prediction speed and accuracy of the future vehicle speed and traffic flow of the target vehicle, improves the response speed of the energy management system of the target vehicle to a certain extent, makes the energy management instruction determined according to the output result of the trained prediction model and the real-time road slope information more accurate, thereby realizing efficient energy management of the target vehicle in a dynamic scenario, reducing energy loss caused by unnecessary acceleration (such as sudden acceleration or sudden deceleration) of the target vehicle, reducing the energy consumption during the driving of the target vehicle, improving the energy recovery efficiency of the target vehicle, and prolonging the service life of the key components of the target vehicle, especially prolonging the service life of the battery of the target vehicle.
[0080] Embodiment III
[0081] Figure 3 FIG. 7 is a schematic structural diagram of a vehicle energy management device provided in Embodiment III of the present invention. This embodiment is applicable to the situation of optimizing and controlling the energy of a new energy vehicle in a dynamic scenario, especially applicable to the situation of optimizing and controlling the energy of a hybrid vehicle or a plug-in hybrid vehicle in a dynamic scenario. The device can be implemented in the form of hardware and / or software and can be configured in an electronic device, which can be a hybrid vehicle or a plug-in hybrid vehicle. As Figure 3 shown, the device includes:
[0082] A vehicle data acquisition module 301, configured to acquire vehicle data of a target vehicle, where the vehicle data includes historical vehicle speed information and current environment information;
[0083] The vehicle speed and traffic flow prediction module 302 is configured to input vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points; wherein, the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm;
[0084] The energy management instruction determination module 303 is configured to determine, according to the vehicle speed and traffic flow of the target vehicle at each future time point, the energy management instruction corresponding to the target vehicle at each future time point;
[0085] The vehicle energy management module 304 is configured to manage the energy of the target vehicle according to the energy management instruction corresponding to the target vehicle at each future time point.
[0086] The technical solution of the embodiment of the present invention obtains vehicle data of the target vehicle; wherein, the vehicle data includes historical vehicle speed information and current environment information; inputs the vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points; wherein, the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm; determines, according to the vehicle speed and traffic flow of the target vehicle at each future time point, the energy management instruction corresponding to the target vehicle at each future time point; and manages the energy of the target vehicle according to the energy management instruction corresponding to the target vehicle at each future time point. The above technical solution predicts the future vehicle speed and traffic flow of the target vehicle by means of a trained prediction model, speeds up the prediction speed and prediction accuracy of the future vehicle speed and traffic flow of the target vehicle, improves the response speed of the energy management system of the target vehicle to a certain extent, makes the energy management instruction determined according to the output result of the trained prediction model more accurate, thereby realizing efficient energy management of the target vehicle in a dynamic scenario, reducing energy loss caused by unnecessary acceleration (such as sudden acceleration or sudden deceleration) of the target vehicle, improving the energy recovery efficiency of the target vehicle, reducing the energy consumption during the driving of the target vehicle, and prolonging the service life of key components of the target vehicle, especially prolonging the service life of the battery of the target vehicle.
[0087] Optionally, the device further includes a prediction model determination module, and the prediction model determination module is specifically configured to:
[0088] Optimize the network parameters of the wavelet neural network through a particle swarm optimization algorithm to obtain a prediction model composed of optimal network parameters.
[0089] Optionally, the energy management instruction determination module 303 includes:
[0090] A road slope information acquisition unit is configured to, for each future time point, acquire the road slope information corresponding to the future time point;
[0091] A road condition determination unit, configured to determine the road condition corresponding to the future time point according to the road slope information;
[0092] A long downhill section detection unit, configured to detect whether the road condition is a long downhill section;
[0093] A first energy management instruction determination unit, configured to, if so, determine that the energy management instruction corresponding to the target vehicle at the future time point is a first battery SOC control instruction and a braking energy recovery instruction;
[0094] A second energy management instruction determination unit, configured to, otherwise, determine the energy management instruction corresponding to the target vehicle at the future time point according to the vehicle speed, a first vehicle speed threshold, and a second vehicle speed threshold at the future time point.
[0095] Optionally, the second energy management instruction determination unit is specifically configured to:
[0096] Detect whether the vehicle speed at the future time point is less than the first vehicle speed threshold;
[0097] If so, determine that the energy management instruction corresponding to the target vehicle at the future time point is a drive mode control instruction and a second battery SOC control instruction;
[0098] Otherwise, detect whether the vehicle speed at the future time point is greater than the second vehicle speed threshold;
[0099] If so, determine that the energy management instruction corresponding to the target vehicle at the future time point is an engine speed control instruction and an air-fuel ratio control instruction.
[0100] Optionally, the vehicle energy management module 304 is specifically configured to:
[0101] For each future time point, if it is determined that the energy management instruction corresponding to the target vehicle at the future time point is a first battery SOC control instruction and a braking energy recovery instruction, then control the hybrid execution unit on the target vehicle to execute the first battery SOC control instruction, adjust the battery SOC of the target vehicle to a first SOC value, and control the hybrid execution unit to execute the braking energy recovery instruction to adjust the electric braking ratio of the target vehicle;
[0102] If it is determined that the energy management instruction corresponding to the target vehicle at the future time point is a drive mode control instruction and a second battery SOC control instruction, then control the hybrid execution unit to execute the drive mode control instruction, switch the power drive mode of the target vehicle to the pure electric mode, and control the hybrid execution unit to execute the second battery SOC control instruction to adjust the battery SOC of the target vehicle to a second SOC value;
[0103] If it is determined that the energy management instructions corresponding to the target vehicle at the future time point are the engine speed control instruction and the air-fuel ratio control instruction, then control the hybrid execution unit to execute the engine speed control instruction, control the engine speed of the target vehicle within the target range, and control the hybrid execution unit to execute the air-fuel ratio control instruction to adjust the air-fuel ratio of the target vehicle.
[0104] Optionally, the training period of the prediction model is 500 milliseconds.
[0105] The vehicle energy management device provided by the embodiments of the present invention can execute the vehicle energy management method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing each vehicle energy management method.
[0106] According to an embodiment of the present invention, the present invention also provides an electronic device, a readable storage medium, and a computer program product.
[0107] Embodiment 4
[0108] Figure 4 FIG. shows a schematic structural diagram of an electronic device 10 that can be used to implement the embodiments of the present invention. The electronic device is intended to represent various forms of digital computers, such as, a laptop computer, a desktop computer, a workbench, a personal digital assistant, a server, a blade server, a mainframe computer, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as, a personal digital processor, a cellular phone, a smart phone, a wearable device (such as a helmet, glasses, a watch, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described herein and / or claimed.
[0109] As Figure 4 shown, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. Among them, the memory stores a computer program executable by at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. The input / output (I / O) interface 15 is also connected to the bus 14.
[0110] Multiple components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.
[0111] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the vehicle energy management method.
[0112] In some embodiments, the vehicle energy management method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the vehicle energy management method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the vehicle energy management method by any other suitable means (e.g., by means of firmware).
[0113] The various embodiments of the systems and technologies described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGA), application-specific integrated circuits (ASIC), application-specific standard products (ASSP), systems-on-chip (SOC), complex programmable logic devices (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a dedicated or general-purpose programmable processor, and can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit the data and instructions to the storage system, the at least one input device, and the at least one output device.
[0114] A computer program for implementing the method of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, a special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer program may be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine, or entirely on the remote machine or server.
[0115] In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium may be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
[0116] In order to provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).
[0117] The systems and techniques described herein can be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected with each other by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.
[0118] A computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs that run on respective computers and have a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system, and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.
[0119] It should be understood that various forms of the processes shown above can be used, with steps reordered, added, or deleted. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.
[0120] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.
Claims
1. A vehicle energy management method, characterized in that, Including: Obtain the vehicle data of the target vehicle; wherein, the vehicle data includes historical vehicle speed information and current environment information; Input the vehicle data into the trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points; wherein, the prediction model is determined according to the wavelet neural network and the particle swarm optimization algorithm; Determine the energy management instruction corresponding to each future time point of the target vehicle according to the vehicle speed and traffic flow of the target vehicle at each future time point; Manage the energy of the target vehicle according to the energy management instruction corresponding to each future time point of the target vehicle.
2. The method according to claim 1, characterized in that, The prediction model is determined according to the wavelet neural network and the particle swarm optimization algorithm, including: Optimize the network parameters of the wavelet neural network through the particle swarm optimization algorithm to obtain a prediction model composed of optimal network parameters.
3. The method according to claim 1, wherein The determining the energy management instruction corresponding to each future time point of the target vehicle according to the vehicle speed and traffic flow of the target vehicle at each future time point includes: For each future time point, obtain the road slope information corresponding to this future time point; Determine the road condition corresponding to this future time point according to the road slope information; Detect whether the road condition is a long downhill section; If so, determine that the energy management instruction corresponding to the target vehicle at this future time point is the first battery SOC control instruction and the braking energy recovery instruction; Otherwise, determine the energy management instruction corresponding to the target vehicle at this future time point according to the vehicle speed, the first vehicle speed threshold and the second vehicle speed threshold at this future time point.
4. The method according to claim 3, wherein The determining the energy management instruction corresponding to the target vehicle at this future time point according to the vehicle speed, the first vehicle speed threshold and the second vehicle speed threshold at this future time point includes: Detect whether the vehicle speed at this future time point is less than the first vehicle speed threshold; If so, determine that the energy management instruction corresponding to the target vehicle at this future time point is the drive mode control instruction and the second battery SOC control instruction; Otherwise, detect whether the vehicle speed at this future time point is greater than the second vehicle speed threshold; If so, determine that the energy management instruction corresponding to the target vehicle at this future time point is the engine speed control instruction and the air-fuel ratio control instruction.
5. The method according to claim 1, characterized in that, The managing the energy of the target vehicle according to the energy management instruction corresponding to each future time point of the target vehicle includes: For each future time point, if it is determined that the energy management instruction corresponding to the target vehicle at this future time point is the first battery SOC control instruction and the braking energy recovery instruction, then control the hybrid execution unit on the target vehicle to execute the first battery SOC control instruction, adjust the battery SOC of the target vehicle to the first SOC value, and control the hybrid execution unit to execute the braking energy recovery instruction to adjust the electric braking ratio of the target vehicle; If it is determined that the energy management instruction corresponding to the target vehicle at the future time point is a driving mode control instruction and a second battery SOC control instruction, then control the hybrid execution unit to execute the driving mode control instruction, switch the power driving mode of the target vehicle to the pure electric mode, and control the hybrid execution unit to execute the second battery SOC control instruction to adjust the battery SOC of the target vehicle to the second SOC value; If it is determined that the energy management instruction corresponding to the target vehicle at the future time point is an engine speed control instruction and an air-fuel ratio control instruction, then control the hybrid execution unit to execute the engine speed control instruction to control the engine speed of the target vehicle within the target speed range, and control the hybrid execution unit to execute the air-fuel ratio control instruction to adjust the air-fuel ratio of the target vehicle.
6. The method according to claim 1, wherein The data sampling period during the training of the prediction model is 100 milliseconds.
7. A vehicle energy management device, characterized in that, Including: A vehicle data acquisition module for acquiring vehicle data of a target vehicle; wherein, the vehicle data includes historical vehicle speed information and current environment information; A vehicle speed and traffic flow prediction module for inputting the vehicle data into a trained prediction model to obtain the vehicle speed and traffic flow of the target vehicle at N future time points; wherein, the prediction model is determined according to a wavelet neural network and a particle swarm optimization algorithm; An energy management instruction determination module for determining the energy management instruction corresponding to the target vehicle at each future time point according to the vehicle speed and traffic flow of the target vehicle at each future time point; A vehicle energy management module for managing the energy of the target vehicle according to the energy management instruction corresponding to the target vehicle at each future time point.
8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the vehicle energy management method according to any one of claims 1-6.
9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the vehicle energy management method according to any one of claims 1-6 when executed.
10. A computer program product including a computer program which, when executed by a processor, implements the vehicle energy management method according to any one of claims 1-6.