Extended-range hybrid light truck energy management control method and device and electronic equipment

Abstract

The invention provides an extended-range hybrid light truck energy management control method and device and electronic equipment, and the method comprises the steps: obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of a hybrid light truck, and obtaining the predicted energy demand data of the light truck through reinforcement learning and energy consumption prediction; obtaining unloading point information, cargo information and charging facility information of each unloading point, and determining a charging analysis result of each unloading point based on the information and the predicted energy demand data; based on the predicted energy demand data and the charging analysis result, constructing an extended-range hybrid light truck power system MLD model; and in combination with the model, an MPC architecture is introduced to design a hybrid light truck energy management strategy which comprehensively considers the operation cost and the charging cost, and energy management control of the hybrid light truck is carried out. The invention relates to an energy management mode of an extended-range hybrid light truck based on unloading point energy supplementation, which can improve the energy utilization efficiency and economical efficiency of the truck.

Description

Technical Field

[0001] The present application relates to the field of intelligent driving technology, and in particular to an energy management control method, device and electronic equipment for an extended-range hybrid light truck. Background Art

[0002] With the development of urban logistics, light trucks are increasingly used in urban distribution. Traditional fuel light trucks have problems such as high fuel consumption and serious pollution, while pure electric light trucks have disadvantages such as limited driving range and long charging time. Extended-range hybrid light trucks combine the advantages of fuel and electric. By enabling the internal combustion engine to generate electricity when necessary, the vehicle's driving range is extended while reducing dependence on charging infrastructure. However, there is still room for optimization in the energy management of existing extended-range hybrid light trucks, especially in urban distribution. How to reasonably utilize the energy replenishment opportunities at the unloading point and improve energy utilization efficiency is an urgent problem to be solved. Summary of the invention

[0003] The purpose of this application is to provide an energy management control method, device and electronic equipment for an extended-range hybrid light truck. It is an energy management method for an extended-range hybrid light truck based on energy replenishment at the unloading point. It uses a model predictive control (MPC) method based on a hybrid logic dynamic (MLD) model, integrates intelligent network prediction, and comprehensively considers charging costs and operating costs to distribute and replenish energy, thereby providing strong support for the application of extended-range hybrid light trucks in urban distribution.

[0004] In a first aspect, the present application provides an energy management control method for an extended-range hybrid light truck, the method comprising: obtaining current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck, and obtaining predicted energy demand data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction; obtaining unloading point information, cargo information, and charging facility information of each unloading point, and determining charging analysis results of each unloading point based on the unloading point information, cargo information, charging facility information and predicted energy demand data of each unloading point; constructing an MLD model based on the predicted energy demand data and the charging analysis results; determining the operating cost based on the fuel consumption cost and the transportation time cost; determining the charging cost based on the charging charge standard; constructing a multi-objective optimization function based on the operating cost and the charging cost; determining the energy management strategy of the extended-range hybrid light truck based on the MLD model and the MPC architecture in combination with the multi-objective optimization function to perform energy management control of the current extended-range hybrid light truck.

[0005] Furthermore, the above-mentioned step of obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck includes: collecting vehicle operation-related data of the extended-range hybrid light truck; the vehicle operation-related data includes: vehicle operation data, traffic condition data, unloading point-related information, and vehicle energy consumption data; pre-processing the vehicle operation-related data to obtain processed vehicle operation-related data; the pre-processing includes: noise filtering and format conversion; obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck from the pre-processed vehicle operation-related data.

[0006] Furthermore, the above-mentioned steps of obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck, and obtaining the predicted energy consumption data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction, include: based on the current task details, historical driving data, and current vehicle operation data of the extended-range hybrid light truck, predicting the arrival time of the vehicle at each stop through reinforcement learning of the prediction network and the value network; predicting the predicted energy consumption data of the extended-range hybrid light truck based on the arrival time of the vehicle at each stop, historical energy consumption data, historical driving data, and current vehicle operation data; the predicted energy consumption data represents the energy data required to complete the task.

[0007] Furthermore, the above-mentioned unloading point information includes: the location, service time window, and facility conditions of each unloading point; the cargo information includes: the quantity, weight, and unloading method of the cargo; the charging facility information includes: the type of charging pile, power, and charging cost; based on the unloading point information, cargo information, charging facility information, and predicted energy demand data of each unloading point, the step of determining the charging opportunity analysis results of each unloading point includes: determining the unloading efficiency according to the unloading point information of each unloading point; estimating the unloading time according to the unloading efficiency and cargo information; updating the availability and queuing conditions of the charging piles in real time based on the unloading time; determining the charging opportunity analysis results of each unloading point according to the predicted energy demand data of the vehicle and the availability and queuing conditions of the charging piles; the analysis results include whether charging can be performed at each unloading point.

[0008] Furthermore, the construction process of the above MLD model is as follows: obtain the continuous input variables of the extended-range hybrid light truck power system; the continuous input variables include: engine power, generator power, drive motor power, battery power; set discrete input logic variables and continuous state variables; the discrete input logic variables include: range extender start-stop state variables, charging pile charging variable, motor gear variable; continuous state variables include: battery charge state, vehicle running speed; among them, the charging pile charging variable is determined based on the charging analysis results; determine the operating constraints of each component, including: battery constraints, drive motor constraints, generator constraints, engine constraints, The vehicle task consumption time constraint and the system total power constraint are determined based on the predicted energy demand data. Based on the power system architecture of the extended-range hybrid light truck, the battery energy consumption model, the generator / drive motor energy consumption model, the engine energy consumption model and the vehicle longitudinal dynamics model are established. Based on the continuous input variables, discrete input logic variables and continuous state variables, as well as the operating constraints of each component, the continuous state equation of the system under different logic variable inputs is established, and the correlation between the continuous state change of the system and the discontinuous working mode switching is expressed through a set of mixed integer inequalities to establish the MLD model of the extended-range hybrid light truck power system as follows:

[0009]

[0010] Among them, x(k+1) represents the system state at time k+1; x(k) is the system state at time k; u(k) is the system input at time k; w(k) is the auxiliary logical variable and auxiliary continuous variable at time k; y(k) is the system output at time k; A, B, B aux , B aff , C, D u , D aux , D aff 、E x 、E u 、E aux 、E aff are coefficient matrices.

[0011] Furthermore, the steps of establishing a battery energy consumption model, a generator / drive motor energy consumption model, an engine energy consumption model and a vehicle longitudinal dynamics model based on the power system architecture of the extended-range hybrid light truck include:

[0012] The battery energy consumption model is as follows:

[0013]

[0014] Among them, U is the open circuit voltage of the power battery; R is the internal resistance of the power battery; P batis the power battery discharge power; η m is the power battery discharge efficiency; Q is the state of charge of the power battery; max is the full charge capacity of the battery;

[0015] The generator / drive motor energy consumption model is as follows:

[0016]

[0017] Where P e (t) is the output power of the generator / drive motor at time t; T e (t) is the output torque of the generator / drive motor at time t; ω e (t) is the output speed of the generator / drive motor at time t; η e is the output efficiency of the generator / drive motor;

[0018] The engine energy consumption model is as follows:

[0019]

[0020] In the formula, is the fuel consumption rate of the engine; Map(T ice ,ω ice ) represents the engine fuel consumption MAP;

[0021] By clustering the data of the engine under different output torque and speed conditions, several clusters with similar fuel consumption characteristics are obtained. A local linear fuel consumption fitting model is established for each cluster, and a piecewise affine fitting model of engine fuel consumption that is piecewise linearly related to engine torque and speed is obtained:

[0022]

[0023] In the formula, a i 、b i are the linear fitting coefficients in each region; T ice Indicates engine torque; n ice Indicates engine speed;

[0024] The longitudinal dynamics model of the extended-range hybrid light truck is established based on Newton's dynamic equations:

[0025]

[0026] Where, T tq is the driving torque; i g is the transmission ratio of the transmission; i0 is the transmission ratio of the main reducer; η e is the transmission system efficiency; R t is the tire radius; mv is the total mass of the vehicle; f is the rolling resistance coefficient; ψ is the road slope; C D A is the air resistance coefficient; a is the frontal area; g is the acceleration of gravity; δ is the vehicle rotation mass conversion coefficient; u a For vehicle speed.

[0027] Furthermore, the steps of determining the operating cost based on the fuel consumption cost and the transportation time cost; determining the charging cost based on the charging charge standard; and constructing a multi-objective optimization function based on the operating cost and the charging cost include: determining the multi-objective optimization function according to the following specified formula:

[0028]

[0029] Among them, α and β are the charging cost weight and the operating cost weight respectively; C charge (t) is the charging cost at time t; C operation (t) is the operating cost at time t; In the formula, E charge,i is defined as the amount of electricity charged at the i-th charging station; p i It is defined as the unit price of charging; N represents the number of charging stations; In the formula, C fuel is the fuel consumption cost, C time is the task time cost; F con (t) is the fuel consumption rate at time t; P fuel is the unit price of fuel consumption; δ1 and δ2 are the weights of fuel consumption cost and task time cost respectively; T delay is the delay time of the transportation task caused by charging; c time It is the unit price of time cost, which is linearly related to the urgency of the task.

[0030] Furthermore, the above-mentioned steps of determining the energy management strategy of the extended-range hybrid light truck based on the MLD model and the MPC architecture in combination with the multi-objective optimization function to perform energy management control of the current extended-range hybrid light truck include: continuously looping the following steps through the MPC framework: constructing an optimization problem containing multiple decision variables based on the MLD model and the multi-objective optimization function; the optimization problem is used to minimize operating costs and charging costs by optimizing the control strategy, while ensuring that the system meets various constraints; wherein the multiple decision variables include: engine power, generator power, drive motor power, battery power, range extender start and stop, charging capability and motor gear at each moment in the future time window; using a mixed integer linear programming method to solve the optimization problem and obtain the optimal control strategy in the future time window; controlling the operation of the extended-range hybrid light truck according to the optimal control strategy.

[0031] On the second aspect, the present application also provides an energy management control device for an extended-range hybrid light truck, the device comprising: an energy demand prediction module, used to obtain the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck, and obtain the predicted energy demand data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction; a charging analysis module, used to obtain the unloading point information, cargo information, and charging facility information of each unloading point, and determine the charging analysis results of each unloading point based on the unloading point information, cargo information, charging facility information, and predicted energy demand data of each unloading point; a model construction module, used to construct an MLD model based on the predicted energy demand data and the charging analysis results; a function construction module, used to determine the operating cost based on the fuel consumption cost and the transportation time cost; determine the charging cost based on the charging charge standard; and construct a multi-objective optimization function based on the operating cost and the charging cost; an energy management module, used to determine the energy management strategy of the extended-range hybrid light truck based on the MLD model and the MPC architecture, combined with the multi-objective optimization function, so as to perform energy management control of the current extended-range hybrid light truck.

[0032] In a third aspect, the present application further provides an electronic device, comprising a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method described in the first aspect above.

[0033] In a fourth aspect, the present application further provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method described in the first aspect above.

[0034] In the extended-range hybrid light truck energy management control method, device and electronic device provided in the present application, the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck are first obtained, and the predicted energy demand data of the extended-range hybrid light truck is obtained through reinforcement learning and energy consumption prediction; then the unloading point information, cargo information and charging facility information of each unloading point are obtained, and the charging analysis results of each unloading point are determined based on the unloading point information, cargo information, charging facility information and predicted energy demand data of each unloading point; further based on the predicted energy demand data and the charging analysis results, an MLD model is constructed; the operating cost is determined based on the fuel consumption cost and the transportation time cost; the charging cost is determined based on the charging charge standard; a multi-objective optimization function is constructed based on the operating cost and the charging cost; based on the MLD model and the MPC architecture, the energy management strategy of the extended-range hybrid light truck is determined in combination with the multi-objective optimization function to perform energy management control of the current extended-range hybrid light truck. This method is an energy management method for extended-range hybrid light trucks based on energy replenishment at the unloading point. It uses a model predictive control (MPC) method based on a hybrid logic dynamic (MLD) model, integrates intelligent network prediction, and comprehensively considers charging costs and operating costs to distribute and replenish energy, thereby improving the vehicle's energy utilization efficiency and economy, and providing strong support for the application of extended-range hybrid light trucks in urban distribution. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] In order to more clearly illustrate the specific implementation methods of the present application or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0036] Figure 1 A flow chart of an energy management control method for an extended-range hybrid light truck provided in an embodiment of the present application;

[0037] Figure 2 A flowchart of a data acquisition preprocessing process provided in an embodiment of the present application;

[0038] Figure 3 An energy management strategy architecture diagram provided for an embodiment of the present application;

[0039] Figure 4 A schematic diagram of a hybrid logic dynamic model of a range-extended hybrid light truck powertrain system provided in an embodiment of the present application;

[0040] Figure 5 A schematic diagram of a multi-objective optimization function provided in an embodiment of the present application;

[0041] Figure 6 A structural block diagram of an energy management control device for an extended-range hybrid light truck provided in an embodiment of the present application;

[0042] Figure 7 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0043] The technical solution of the present application will be described clearly and completely below in conjunction with the embodiments. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0044] There is still room for improvement in the energy management of existing extended-range hybrid light trucks. Especially in urban distribution, how to rationally utilize energy replenishment opportunities at unloading points and improve energy efficiency is an issue that needs to be addressed urgently.

[0045] Based on this, the embodiments of the present application provide an energy management control method, device and electronic equipment for an extended-range hybrid light truck. It is an energy management method for an extended-range hybrid light truck based on energy replenishment at the unloading point. It integrates intelligent network prediction through a model predictive control (MPC) method based on a hybrid logic dynamic (MLD) model, and comprehensively considers charging costs and operating costs to distribute and replenish energy, thereby providing strong support for the application of extended-range hybrid light trucks in urban distribution.

[0046] To facilitate understanding of this embodiment, a method for energy management control of an extended-range hybrid light truck disclosed in an embodiment of the present application is first introduced in detail.

[0047] The extended-range hybrid light truck in this embodiment can be a vehicle used by a logistics company in urban distribution. First, the real-time traffic conditions, path information and unloading point information are obtained through the Internet of Vehicles terminal, and then uploaded to the cloud server for data analysis. Based on real-time data and historical data, an energy consumption prediction model is constructed. The on-board controller establishes the MLD model, and combines the energy consumption prediction model with the MPC method for energy management to ensure that the vehicle maximizes the use of the dwell time for battery recharging during each stop at the unloading point. At the same time, the power generation task of the internal combustion engine is reasonably arranged according to the predicted energy demand. This method can effectively reduce the vehicle's fuel consumption, improve battery utilization efficiency, and reduce overall operating costs.

[0048] Figure 1 A flow chart of an extended-range hybrid light truck energy management control method provided in an embodiment of the present application, the method specifically comprising the following steps:

[0049] Step S102, obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck, and obtaining the predicted energy demand data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction;

[0050] Step S104, obtaining unloading point information, cargo information, and charging facility information of each unloading point, and determining a charging analysis result of each unloading point based on the unloading point information, cargo information, charging facility information, and predicted energy demand data of each unloading point;

[0051] Step S106, constructing an MLD model based on the predicted energy demand data and the charging analysis results; Step S108, determining the operating cost based on the fuel consumption cost and the transportation time cost; determining the charging cost based on the charging fee standard; constructing a multi-objective optimization function based on the operating cost and the charging cost;

[0052] Step S110 , based on the MLD model and the MPC architecture, an energy management strategy of the extended-range hybrid light truck is determined in combination with a multi-objective optimization function to perform energy management control of the current extended-range hybrid light truck.

[0053] The above MLD (Mixed Logic Dynamic) model is a mixed logic dynamic model. The above MPC (Model-based Predictive Control) architecture is a special type of control, and its current control action is obtained by solving a finite time domain open-loop optimal control problem at each sampling moment. The current state of the process is used as the initial state of the optimal control problem, and the optimal control sequence obtained only implements the first control action.

[0054] The extended-range hybrid light truck energy management control method provided in the embodiment of the present application is an extended-range hybrid light truck energy management method based on energy replenishment at the unloading point. It uses a model predictive control (MPC) method based on a hybrid logic dynamic (MLD) model, integrates intelligent network prediction, and comprehensively considers charging costs and operating costs to distribute and replenish energy, thereby improving the vehicle's energy utilization efficiency and economy, and providing strong support for the application of extended-range hybrid light trucks in urban distribution.

[0055] An embodiment of the present application also provides another extended-range hybrid light truck energy management control method, which is implemented on the basis of the above embodiment; this embodiment focuses on describing the data acquisition and preprocessing process, the prediction process, the charging analysis process, the MLD model construction process and the control solution process.

[0056] (1) Data acquisition and preprocessing process:

[0057] See also Figure 2As shown, the steps of obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck include:

[0058] Step S202, collecting vehicle operation related data of the extended-range hybrid light truck; the vehicle operation related data includes: vehicle operation data, traffic condition data, unloading point related information, and vehicle energy consumption data;

[0059] In specific implementation, vehicle operation data (including speed, acceleration, battery status, fuel consumption, generator status, etc.), traffic condition data (real-time traffic flow, congestion, road construction information, etc.), unloading point information (including location, estimated arrival time, stay time, charging facility status, etc.), vehicle energy consumption data (under different road conditions, loads, driving habits, etc.), etc. can be collected through hardware equipment installed on the vehicle, map service providers, vehicle-to-vehicle (V2V) and vehicle-to-infrastructure (V2I) communications and other sources, and uploaded to the cloud platform.

[0060] Step S204, preprocessing the vehicle operation related data to obtain processed vehicle operation related data; the preprocessing includes: noise filtering and format conversion;

[0061] In specific implementation, the Kalman filter algorithm can be used to denoise the data to eliminate sensor errors and sudden anomalies; statistical methods or machine learning models can be used to detect abnormal data points and process them, such as discarding or correcting them; the data can be converted into a unified format and unit, and the data can be timestamped to ensure the time consistency of different data sources, which is convenient for subsequent processing and analysis.

[0062] Step S206, obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck from the pre-processed vehicle operation related data.

[0063] (2) Model prediction process:

[0064] See also Figure 3 As shown, the steps of obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck, and obtaining the predicted energy consumption data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction include:

[0065] (2.1) Based on the current mission details, historical driving data, and current vehicle operation data of the extended-range hybrid light truck, the arrival time of the vehicle at each stop is predicted through reinforcement learning of the prediction network and the value network. The steps of arrival time prediction are as follows:

[0066] Establish a complete data collection and management system, including historical travel time data (records of vehicle travel time on different road sections, usually including timestamp, vehicle speed, weather conditions, road type and other information), historical traffic flow data (traffic flow fluctuations during peak and non-peak periods, frequency of congestion), stop point history records (historical arrival time, departure time, stay time, etc. of vehicles at each stop), weather and event records (historical events such as road construction, traffic accidents, extreme weather, etc., which may affect changes in travel time).

[0067] Real-time vehicle data includes GPS data (real-time information such as the current vehicle location, driving speed, and driving direction), real-time traffic monitoring data (such as the current road congestion, vehicle speed, traffic events, etc.), real-time weather information (the impact of weather changes on road conditions and driving speeds, such as rainy days, foggy days, snowy days, etc.), and real-time traffic event data (including sudden traffic accidents, road closures, etc.).

[0068] First, we build a preliminary arrival time prediction model through historical data analysis. Based on the data of similar situations in history, we analyze the mean and variance of historical driving time to obtain the average driving time and fluctuation range of the road section under different time periods and weather conditions. We divide the journey from the starting point to the end point into several sections, and accumulate the time of each section to obtain the estimated arrival time of the entire journey. Then, we superimpose the real-time data information of the vehicle to correct the estimated arrival time model.

[0069] Reinforcement learning is introduced to optimize the prediction of arrival time, combining historical data with real-time data to gradually learn the optimal prediction strategy under different environments. The state space of reinforcement learning includes the current vehicle position, speed, real-time road conditions (traffic flow, congestion status, weather), current cumulative driving time, etc. The parameters of the arrival time model are corrected in the action space. The goal of the reward function is to minimize the error of the arrival time prediction, that is, to minimize the difference between the actual arrival time and the predicted time. After each adjustment of the parameters of the arrival time model, the system will give rewards or penalties based on the difference between the actual arrival time of the vehicle and the predicted value. In the actual operation of the vehicle, through continuous feedback and adjustment, it is ensured that the arrival time prediction can be updated in time with the changes in the actual situation.

[0070] (2.2) Based on the arrival time of the vehicle at each stop, historical energy consumption data, historical driving data, and current vehicle operation data, the predicted energy consumption data of the extended-range hybrid light truck is predicted; the predicted energy consumption data represents the energy data required to complete the task.

[0071] In the specific implementation, first obtain the task details, such as the starting point, end point, intermediate stops and time requirements, analyze the vehicle's historical driving data, understand the driving time, road conditions and potential problems of common routes, and then use reinforcement learning to predict the estimated arrival time of each stop based on the driving path and real-time traffic conditions, considering traffic flow fluctuations and possible traffic events. Monitor the location and driving conditions of the vehicle in real time, adjust the arrival time prediction to ensure accuracy. Then, based on the energy consumption data of the vehicle under different conditions (road conditions, traffic flow, vehicle load, air conditioning use, etc.), combined with the driver's driving habits, use machine learning models (such as regression models, neural networks), build an energy consumption prediction model based on the vehicle's driving path, estimated arrival time and the current state of the vehicle, calculate the total energy demand of the vehicle to complete the task, monitor the energy consumption in real time, compare it with the predicted value, adjust the prediction model, and improve the prediction accuracy.

[0072] (3) Charging opportunity analysis process:

[0073] The above-mentioned unloading point information includes: the location, service time window, and facility conditions of each unloading point; the cargo information includes: the quantity, weight, and unloading method of the cargo; the charging facility information includes: the type of charging pile, power, and charging cost; based on the unloading point information, cargo information, charging facility information, and predicted energy demand data of each unloading point, the steps of determining the charging opportunity analysis results of each unloading point include: determining the unloading efficiency based on the unloading point information of each unloading point; estimating the unloading time based on the unloading efficiency and cargo information; updating the availability and queuing conditions of the charging piles in real time based on the unloading time; determining the charging opportunity analysis results of each unloading point based on the predicted energy demand data of the vehicle and the availability and queuing conditions of the charging piles; the analysis results include whether charging can be performed at each unloading point.

[0074] During the specific implementation, the location, service time window, and facilities (such as the number and type of charging piles) of each unloading point are collected. The cargo information of each unloading point is obtained, including the quantity, weight, unloading method, etc., and the unloading time is estimated based on the cargo information and the service efficiency of the unloading point. The information of the charging facilities at each unloading point is obtained, including the type of charging pile, power, and charging cost (electricity price). The availability and queuing of the charging piles are updated in real time. Based on the energy demand forecast of the vehicle and the information of the charging facilities, it is determined whether charging can be performed at each unloading point.

[0075] (4) Construction process of MLD model:

[0076] See also Figure 4 As shown in Figure 2, the construction process of the above MLD model is as follows:

[0077] (4.1) Obtaining continuous input variables of the extended-range hybrid light truck power system; the continuous input variables include: engine power Pice , generator power P ge , drive motor power P de 、Battery power P bat ;

[0078] (4.2) Set discrete input logic variables and continuous state variables; discrete input logic variables include: range extender start / stop state variable δ ice (0 means off, 1 means on), whether the charging pile can charge variable δ c (0 means non-rechargeable, 1 means rechargeable), motor gear position variable δ gi (i represents the current gear, 1 represents the gear is valid, and 0 represents the gear is invalid); continuous state variables include: battery state of charge SOC, vehicle running speed v; among them, the variable δ of whether the charging pile can be charged c Determined based on charging analysis results;

[0079] (4.3) Determine the operating constraints of each component, including: battery constraints, drive motor constraints, generator constraints, engine constraints, vehicle mission time constraints and system total power constraints; among which, the system total power constraints are determined based on the predicted energy demand data; specifically, based on the predicted energy demand data, a relaxation factor is given and the power fluctuation range is determined as the system total output power (battery and motor power) constraint.

[0080] (4.3.1) Battery constraints include:

[0081] Maximum and minimum SOC: SOC min ≤SOC(t)≤SOC max

[0082] In the formula, SOC min , SOC max are the minimum and maximum states of charge of the power battery respectively.

[0083] Maximum charge and discharge power:

[0084] In the formula, is the maximum discharge power of the power battery.

[0085] (4.3.2) The constraints of the drive motor include:

[0086] Maximum output power:

[0087] Maximum output torque:

[0088] Maximum speed:

[0089] Where P ge is the output power of the driving motor; T ge is the output torque of the driving motor; ge Output speed of the drive motor; and They are the maximum power, maximum torque and maximum speed of the driving motor respectively.

[0090] (4.3.3) The constraints of the generator include:

[0091] Maximum output power:

[0092] Maximum output torque:

[0093] Maximum speed:

[0094] Where P de is the output power of the generator / drive motor; T de Output torque for the generator / drive motor; ω de Output speed for the generator / drive motor; and They are the maximum power, maximum torque and maximum speed of the generator respectively.

[0095] (4.3.4) The constraints of the engine include:

[0096] Maximum output power:

[0097] Maximum output torque:

[0098] Maximum output speed:

[0099] Where, T ice is the actual output torque of the engine; ω ice is the actual output speed of the engine; They are the maximum output power, maximum output torque and maximum output speed of the engine respectively.

[0100] (4.3.5) Vehicle mission time constraints: t o ≤t max

[0101] Where, t o and t max The actual time and maximum time constraint consumed by a vehicle for a single transportation task.

[0102] (4.4) Based on the powertrain architecture of the extended-range hybrid light truck, establish the battery energy consumption model, generator / drive motor energy consumption model, engine energy consumption model and vehicle longitudinal dynamics model;

[0103] The battery energy consumption model is used to describe the energy changes of the battery under different operating conditions. It can be expressed as the relationship between the battery's charge and discharge power and the battery's state of charge (SOC), as follows:

[0104]

[0105] Among them, U is the open circuit voltage of the power battery; R is the internal resistance of the power battery; P bat is the power battery discharge power; η m is the power battery discharge efficiency; Q is the state of charge of the power battery; max is the full charge capacity of the battery;

[0106] The generator / drive motor energy consumption model describes the efficiency and energy consumption characteristics of the generator / drive motor, which usually depends on the output power, torque and speed of the generator / drive motor. The relationship between the output power, torque and speed of the generator / drive motor is as follows:

[0107]

[0108] Where P e (t) is the output power of the generator / drive motor at time t; T e (t) is the output torque of the generator / drive motor at time t; ω e (t) is the output speed of the generator / drive motor at time t; η e is the output efficiency of the generator / drive motor;

[0109] The engine energy consumption model is used to describe the fuel consumption of the internal combustion engine at different working points. The fuel consumption rate of the engine is nonlinearly related to the engine torque and speed, as follows:

[0110]

[0111] In the formula, is the fuel consumption rate of the engine; Map(T ice ,ω ice ) represents the engine fuel consumption MAP;

[0112] By clustering the data of the engine under different output torque and speed conditions, several clusters with similar fuel consumption characteristics are obtained. A local linear fuel consumption fitting model is established for each cluster, and a piecewise affine fitting model of engine fuel consumption that is piecewise linearly related to engine torque and speed is obtained:

[0113]

[0114] In the formula, a i 、b i are the linear fitting coefficients in each region; T ice Indicates engine torque; n ice Indicates engine speed;

[0115] The longitudinal dynamics model of the extended-range hybrid light truck is established based on Newton's dynamic equations:

[0116]

[0117] Where, T tq is the driving torque; i g is the transmission ratio of the transmission; i0 is the transmission ratio of the main reducer; η e is the transmission system efficiency; R t is the tire radius; m v is the total mass of the vehicle; f is the rolling resistance coefficient; ψ is the road slope; C D A is the air resistance coefficient; a is the frontal area; g is the acceleration of gravity; δ is the vehicle rotation mass conversion coefficient; u a For vehicle speed.

[0118] (4.5) Based on the continuous input variables, discrete input logic variables and continuous state variables, as well as the operating constraints of each component, the continuous state equation of the system under different logic variable inputs is established. The correlation between the continuous state change of the system and the discontinuous working mode switching is expressed by a set of mixed integer inequalities to establish the MLD model of the extended-range hybrid light truck power system as follows:

[0119]

[0120] Among them, x(k+1) represents the system state at time k+1; x(k) is the system state at time k; u(k) is the system input at time k; w(k) is the auxiliary logical variable and auxiliary continuous variable at time k; y(k) is the system output at time k; A, B, B aux , B aff , C, D u , D aux , D aff 、E x 、E u 、E aux 、E aff are coefficient matrices.

[0121] (5) Multi-objective optimization function construction process:

[0122] Furthermore, the above process of determining the operating cost based on the fuel consumption cost and the transportation time cost, determining the charging cost based on the charging charge standard, and constructing a multi-objective optimization function based on the operating cost and the charging cost is as follows, see Figure 5 As shown:

[0123] Factors such as charging cost (electricity price, charging station charging standard) and operating cost (fuel consumption cost, transportation time cost) are introduced to establish a multi-objective optimization function to minimize the total cost and energy consumption while meeting the task scheduling requirements. The formula of the multi-objective optimization function is as follows:

[0124]

[0125] Among them, α and β are the charging cost weight and the operating cost weight respectively; C charge (t) is the charging cost at time t; C operation (t) is the operating cost at time t; In the formula, E charge,i is defined as the amount of electricity charged at the i-th charging station; p i It is defined as the unit price of charging; N represents the number of charging stations; In the formula, C fuel is the fuel consumption cost, C time is the task time cost; F con (t) is the fuel consumption rate at time t; P fuel is the unit price of fuel consumption; δ1 and δ2 are the weights of fuel consumption cost and task time cost respectively; T delay is the delay time of the transportation task caused by charging; c time It is the unit price of time cost, which is linearly related to the urgency of the task.

[0126] (6) Control the solution process:

[0127] That is, the energy management strategy of the extended-range hybrid light truck is determined based on the MLD model and the MPC architecture in combination with the multi-objective optimization function to perform the steps of energy management control of the current extended-range hybrid light truck, including:

[0128] The following steps are continuously executed in a loop through the MPC framework: Based on the MLD model and multi-objective optimization function, an optimization problem containing multiple decision variables is constructed; the optimization problem is used to minimize operating costs and charging costs by optimizing the control strategy, while ensuring that the system meets various constraints; among them, multiple decision variables include: engine power, generator power, drive motor power, battery power, range extender start and stop, charging capability and motor gear at each moment in the future time window; mixed integer linear programming method is used to solve the optimization problem and obtain the optimal control strategy in the future time window; the operation of the extended-range hybrid light truck is controlled according to the optimal control strategy.

[0129] For specific implementation, see Figure 3 The energy management framework diagram shown in the figure uses the MPC method to estimate the state and energy demand of the system in the future based on the constructed hybrid logic dynamic energy consumption model, and then minimizes the operating cost and charging cost by optimizing the control strategy, while ensuring that the system meets various constraints. Based on the above prediction model and multi-objective optimization function, an optimization problem containing multiple decision variables is constructed, including the engine power, generator power, drive motor power, battery power, range extender start and stop, charging and motor gear at each moment in the future. This problem uses the mixed integer linear programming method to solve the optimal charging, power generation and discharge strategies in the future (i.e., prediction window). These strategies can ensure the optimality of energy management while meeting various physical constraints of the system. The solved strategies include a series of control actions corresponding to the optimal decision of each time step, and only the first control action of the optimization result is implemented in each control cycle; repeat the above process at each time step, and adjust the control strategy in real time according to the latest state and prediction information to ensure that the system is always in the optimal state.

[0130] The relationship between the model and the optimization objective is as follows:

[0131] Prediction model: It is used to predict the changes in system status (such as battery power, energy consumption, etc.) in the future, which provides the necessary input for the optimization problem.

[0132] Multi-objective optimization function: Based on the future state information provided by the prediction model, an objective function is constructed to minimize energy consumption, cost, or other performance indicators.

[0133] Optimization solution: Based on the prediction model and multi-objective optimization function, the optimal strategy in the future time window is obtained by solving the optimization problem.

[0134] The entire process is continuously cycled through the MPC framework, and the system control strategy is adjusted in real time to ensure that the current optimal control action is executed at each time step.

[0135] The energy management control method for a programmed hybrid light truck provided in the embodiment of the present application has the following advantages:

[0136] (1) Combined with intelligent network prediction, rationally utilize the vehicle unloading time for energy replenishment, comprehensively consider the charging time and charging cost, and improve the energy utilization efficiency of batteries and internal combustion engines on the premise of ensuring task scheduling, reduce operating costs, reduce fuel consumption, and extend the vehicle's cruising range.

[0137] (2) By adopting the online prediction of MPC energy management strategy based on MLD model, the system can dynamically adjust the energy management strategy according to real-time data and prediction results to adapt to various working conditions such as urban distribution, ensuring the efficient operation of vehicles in different environments.

[0138] Based on the above method embodiment, the present application embodiment also provides an energy management control device for an extended-range hybrid light truck, see Figure 6 As shown, the device includes: an energy demand prediction module 602, which is used to obtain the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck, and obtain the predicted energy demand data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction; a charging analysis module 604, which is used to obtain the unloading point information, cargo information, and charging facility information of each unloading point, and determine the charging analysis results of each unloading point based on the unloading point information, cargo information, charging facility information, and predicted energy demand data of each unloading point; a model construction module 606, which is used to construct an MLD model based on the predicted energy demand data and the charging analysis results; a function construction module 608, which is used to determine the operating cost based on the fuel consumption cost and the transportation time cost; determine the charging cost based on the charging charge standard; and construct a multi-objective optimization function based on the operating cost and the charging cost; an energy management module 610, which is used to determine the energy management strategy of the extended-range hybrid light truck based on the MLD model and the MPC architecture in combination with the multi-objective optimization function, so as to perform energy management control of the current extended-range hybrid light truck.

[0139] Furthermore, the energy demand prediction module 602 is used to collect vehicle operation related data of the extended-range hybrid light truck; the vehicle operation related data include: vehicle operation data, traffic condition data, unloading point related information, and vehicle energy consumption data; the vehicle operation related data are pre-processed to obtain processed vehicle operation related data; the preprocessing includes: noise filtering and format conversion; from the pre-processed vehicle operation related data, the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck are obtained.

[0140] Furthermore, the energy demand prediction module 602 is used to predict the arrival time of the vehicle at each stop based on the current task details, historical driving data, and current vehicle operation data of the extended-range hybrid light truck through reinforcement learning of the prediction network and the value network; predict the predicted energy consumption data of the extended-range hybrid light truck based on the arrival time of the vehicle at each stop, historical energy consumption data, historical driving data, and current vehicle operation data; the predicted energy consumption data represents the energy data required to complete the task.

[0141] Furthermore, the above-mentioned unloading point information includes: the location, service time window, and facility conditions of each unloading point; the cargo information includes: the quantity, weight, and unloading method of the cargo; the charging facility information includes: the type, power, and charging cost of the charging pile; the charging analysis module 604 is used to determine the unloading efficiency based on the unloading point information of each unloading point; estimate the unloading time based on the unloading efficiency and cargo information; update the availability and queuing of the charging piles in real time based on the unloading time; determine the charging opportunity analysis results of each unloading point based on the vehicle's predicted energy demand data and the availability and queuing of the charging piles; the analysis results include whether charging can be performed at each unloading point.

[0142] Furthermore, the model building module 606 is used to execute the following MLD model building process: obtaining continuous input variables of the extended-range hybrid light truck power system; the continuous input variables include: engine power, generator power, drive motor power, battery power; setting discrete input logic variables and continuous state variables; the discrete input logic variables include: range extender start-stop state variables, charging pile charging variable, motor gear variable; the continuous state variables include: battery charge state, vehicle running speed; determining the operating constraints of each component, including: battery constraints, drive motor constraints, generator constraints Constraints, engine constraints, and vehicle mission consumption time constraints; based on the power system architecture of the extended-range hybrid light truck, establish the battery energy consumption model, generator / drive motor energy consumption model, engine energy consumption model, and vehicle longitudinal dynamics model; based on continuous input variables, discrete input logical variables, and continuous state variables, as well as the operating constraints of each component, establish the continuous state equation of the system under different logical variable inputs, and express the correlation between the continuous state change of the system and the discontinuous working mode switching through a set of mixed integer inequalities to establish the MLD model of the extended-range hybrid light truck power system as follows:

[0143]

[0144] Among them, x(k+1) represents the system state at time k+1; x(k) is the system state at time k; u(k) is the system input at time k; w(k) is the auxiliary logical variable and auxiliary continuous variable at time k; y(k) is the system output at time k; A, B, B aux , B aff , C, D u , D aux , D aff 、E x 、E u 、E aux 、E aff are coefficient matrices.

[0145] Furthermore, the model building module 606 is used to:

[0146] The battery energy consumption model is as follows:

[0147]

[0148] Among them, U is the open circuit voltage of the power battery; R is the internal resistance of the power battery; P bat is the power battery discharge power; η m is the power battery discharge efficiency; Q is the state of charge of the power battery; max is the full charge capacity of the battery;

[0149] The generator / drive motor energy consumption model is as follows:

[0150]

[0151] Where P e (t) is the output power of the generator / drive motor at time t; T e (t) is the output torque of the generator / drive motor at time t; ω e (t) is the output speed of the generator / drive motor at time t; η e is the output efficiency of the generator / drive motor;

[0152] The engine energy consumption model is as follows:

[0153]

[0154] In the formula, is the fuel consumption rate of the engine; Map(T ice ,ω ice ) represents the engine fuel consumption MAP;

[0155] By clustering the data of the engine under different output torque and speed conditions, several clusters with similar fuel consumption characteristics are obtained. A local linear fuel consumption fitting model is established for each cluster, and a piecewise affine fitting model of engine fuel consumption that is piecewise linearly related to engine torque and speed is obtained:

[0156]

[0157] In the formula, a i 、b i are the linear fitting coefficients in each region; T ice Indicates engine torque; n ice Indicates engine speed;

[0158] The longitudinal dynamics model of the extended-range hybrid light truck is established based on Newton's dynamic equations:

[0159]

[0160] Where, T tq is the driving torque; i g is the transmission ratio of the transmission; i0 is the transmission ratio of the main reducer; η e is the transmission system efficiency; R t is the tire radius; m v is the total mass of the vehicle; f is the rolling resistance coefficient; ψ is the road slope; C D A is the air resistance coefficient; a is the frontal area; g is the acceleration of gravity; δ is the vehicle rotation mass conversion coefficient; u a For vehicle speed.

[0161] Furthermore, the above function construction module 66 is used to construct the formula of the multi-objective optimization function as follows:

[0162]

[0163] Among them, α and β are the charging cost weight and the operating cost weight respectively; C charge (t) is the charging cost at time t; C operation (t) is the operating cost at time t; In the formula, E charge,i is defined as the amount of electricity charged at the i-th charging station; p i It is defined as the unit price of charging; N represents the number of charging stations; In the formula, C fuel is the fuel consumption cost, C time is the task time cost; F con (t) is the fuel consumption rate at time t; P fuel is the unit price of fuel consumption; δ1 and δ2 are the weights of fuel consumption cost and task time cost respectively; T delay is the delay time of the transportation task caused by charging; c time It is the unit price of time cost, which is linearly related to the urgency of the task.

[0164] Furthermore, the energy management module 610 is used to continuously execute the following steps in a loop through the MPC framework: construct an optimization problem containing multiple decision variables based on the MLD model and the multi-objective optimization function; the optimization problem is used to minimize the operating cost and the charging cost by optimizing the control strategy, while ensuring that the system meets various constraints; wherein the multiple decision variables include: the engine power, the generator power, the drive motor power, the battery power, the start and stop of the range extender, whether it can be charged, and the gear position of the motor at each moment in the future time window; use the mixed integer linear programming method to solve the optimization problem and obtain the optimal control strategy in the future time window; control the operation of the extended-range hybrid light truck according to the optimal control strategy.

[0165] The device provided in the embodiment of the present application has the same implementation principle and technical effects as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the embodiment of the device, reference may be made to the corresponding contents in the aforementioned method embodiment.

[0166] The present application also provides an electronic device, such as Figure 7 As shown, it is a schematic diagram of the structure of the electronic device, wherein the electronic device includes a processor 71 and a memory 70, the memory 70 stores computer executable instructions that can be executed by the processor 71, and the processor 71 executes the computer executable instructions to implement the above method.

[0167] exist Figure 7 In the illustrated embodiment, the electronic device further includes a bus 72 and a communication interface 73 , wherein the processor 71 , the communication interface 73 and the memory 70 are connected via the bus 72 .

[0168] Among them, the memory 70 may include a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 73 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 72 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The bus 72 can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 7Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0169] The processor 71 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the hardware integrated logic circuit or software instructions in the processor 71. The above processor 71 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present application can be directly embodied as a hardware decoding processor to execute, or the hardware and software modules in the decoding processor can be executed. The software module can be located in a mature storage medium in the field such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor 71 reads the information in the memory and completes the steps of the method of the above embodiment in combination with its hardware.

[0170] An embodiment of the present application also provides a computer-readable storage medium, which stores computer-executable instructions. When the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the above method. The specific implementation can be found in the aforementioned method embodiment, which will not be repeated here.

[0171] The computer program products of the methods, devices, and electronic devices provided in the embodiments of the present application include a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the methods described in the previous method embodiments. The specific implementation can be found in the method embodiments, which will not be repeated here.

[0172] Unless otherwise specifically stated, the relative steps, numerical expressions and values ​​of the components and steps set forth in these embodiments do not limit the scope of the present application.

[0173] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a non-volatile computer-readable storage medium that is executable by a processor. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.

[0174] In the description of the present application, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc., indicating the orientation or positional relationship, are based on the orientation or positional relationship shown in the drawings, and are only for the convenience of describing the present application and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present application. In addition, the terms "first", "second", and "third" are used for descriptive purposes only, and cannot be understood as indicating or implying relative importance.

[0175] Finally, it should be noted that the above-described embodiments are only specific implementation methods of the present application, which are used to illustrate the technical solutions of the present application, rather than to limit them. The protection scope of the present application is not limited thereto. Although the present application is described in detail with reference to the above-described embodiments, ordinary technicians in the field should understand that any technician familiar with the technical field can still modify the technical solutions recorded in the above-described embodiments within the technical scope disclosed in the present application, or can easily think of changes, or make equivalent replacements for some of the technical features therein; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application, and should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.

Claims

1. An energy management control method for an extended-range hybrid light truck, characterized in that: The method comprises: Obtaining current task details, historical driving data, current vehicle operation data, and historical energy consumption data of the extended-range hybrid light truck, and obtaining predicted energy demand data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction; Obtaining unloading point information, cargo information, and charging facility information of each unloading point, and determining a charging analysis result of each unloading point based on the unloading point information, cargo information, charging facility information of each unloading point and the predicted energy demand data; constructing an MLD model based on the predicted energy demand data and the charging analysis result; Determine the operating cost based on the fuel consumption cost and the transportation time cost; determine the charging cost based on the charging charge standard; and construct a multi-objective optimization function based on the operating cost and the charging cost; Based on the MLD model and the MPC architecture, the energy management strategy of the extended-range hybrid light truck is determined in combination with the multi-objective optimization function to perform energy management control of the current extended-range hybrid light truck.

2. The method according to claim 1, characterized in that: The step of obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck comprises: Collecting vehicle operation related data of the extended-range hybrid light truck; the vehicle operation related data includes: vehicle operation data, traffic condition data, unloading point related information, and vehicle energy consumption data; Preprocessing the vehicle operation related data to obtain processed vehicle operation related data; the preprocessing includes: noise filtering and format conversion; The current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck are obtained from the preprocessed vehicle operation related data.

3. The method according to claim 1, characterized in that The step of obtaining the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck, and obtaining the predicted energy consumption data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction includes: Based on the current mission details, historical driving data, and current vehicle operation data of the extended-range hybrid light truck, the arrival time of the vehicle at each stop is predicted through reinforcement learning of the prediction network and the value network; Based on the arrival time of the vehicle at each stop, the historical energy consumption data, the historical driving data, and the current vehicle operation data, the predicted energy consumption data of the extended-range hybrid light truck is predicted; the predicted energy consumption data represents the energy data required to complete the task.

4. The method according to claim 1, characterized in that The unloading point information includes: the location, service time window, and facility conditions of each unloading point; the cargo information includes: cargo quantity, weight, and unloading method; the charging facility information includes: charging pile type, power, and charging fee; The step of determining the charging opportunity analysis result of each unloading point based on the unloading point information, cargo information, charging facility information, and the predicted energy demand data of each unloading point includes: Determining unloading efficiency according to the unloading point information of each unloading point; estimating the unloading time according to the unloading efficiency and the cargo information; updating the availability and queue status of charging posts in real time based on the unloading time; The charging opportunity analysis results of each unloading point are determined based on the predicted energy demand data of the vehicle and the availability and queue status of the charging piles; the analysis results include whether charging is possible at each unloading point.

5. The method according to claim 1, characterized in that The construction process of the MLD model is as follows: Obtaining continuous input variables of a power system of a range-extended hybrid light truck; the continuous input variables include: engine power, generator power, drive motor power, and battery power; Discrete input logic variables and continuous state variables are set; the discrete input logic variables include: range extender start / stop state variable, charging pile chargeability variable, motor gear variable; the continuous state variables include: battery charge state, vehicle running speed; wherein the charging pile chargeability variable is determined based on the charging analysis result; Determine the operating constraints of each component, including: battery constraints, drive motor constraints, generator constraints, engine constraints, vehicle mission consumption time constraints and system total power constraints; wherein the system total power constraints are determined based on the predicted energy demand data; Based on the power system architecture of the extended-range hybrid light truck, establish the battery energy consumption model, generator / drive motor energy consumption model, engine energy consumption model and vehicle longitudinal dynamics model; Based on the continuous input variables, discrete input logic variables and continuous state variables, as well as the operating constraints of each component, the continuous state equation of the system under different logic variable inputs is established, and the correlation between the continuous state change of the system and the discontinuous working mode switching is expressed by a set of mixed integer inequalities to establish the MLD model of the extended-range hybrid light truck power system as follows: Among them, x(k+1) represents the system state at time k+1; x(k) is the system state at time k; u(k) is the system input at time k; w(k) is the auxiliary logical variable and auxiliary continuous variable at time k; y(k) is the system output at time k; A, B, B aux , B aff , C, D u , D aux , D aff 、E x 、E u 、E aux 、E aff are coefficient matrices.

6. The method according to claim 5, characterized in that Based on the power system architecture of the extended-range hybrid light truck, the steps of establishing the battery energy consumption model, the generator / drive motor energy consumption model, the engine energy consumption model and the vehicle longitudinal dynamics model include: The battery energy consumption model is as follows: Among them, U is the open circuit voltage of the power battery; R is the internal resistance of the power battery; P bat is the power battery discharge power; η m is the power battery discharge efficiency; Q is the state of charge of the power battery; max is the full charge capacity of the battery; The generator / drive motor energy consumption model is as follows: Where P e (t) is the output power of the generator / drive motor at time t; T e (t) is the output torque of the generator / drive motor at time t; ω e (t) is the output speed of the generator / drive motor at time t; η e is the output efficiency of the generator / drive motor; The engine energy consumption model is as follows: In the formula, is the fuel consumption rate of the engine; Map(T ice ,ω ice ) represents the engine fuel consumption MAP; By clustering the data of the engine under different output torque and speed conditions, several clusters with similar fuel consumption characteristics are obtained. A local linear fuel consumption fitting model is established for each cluster, and a piecewise affine fitting model of engine fuel consumption that is piecewise linearly related to engine torque and speed is obtained: In the formula, a i , b i are the linear fitting coefficients in each region; T ice Indicates engine torque; n ice Indicates engine speed; The longitudinal dynamics model of the extended-range hybrid light truck is established based on Newton's dynamic equations: Where, T tq is the driving torque; i g is the transmission ratio of the transmission; i0 is the transmission ratio of the main reducer; η e is the transmission system efficiency; R t is the tire radius; m v is the total mass of the vehicle; f is the rolling resistance coefficient; ψ is the road slope; C D A is the air resistance coefficient; a is the frontal area; g is the acceleration of gravity; δ is the vehicle rotation mass conversion coefficient; u a For vehicle speed.

7. The method according to claim 5, characterized in that The operating cost is determined based on the fuel consumption cost and the transportation time cost; the charging cost is determined based on the charging charge standard; and the steps of constructing a multi-objective optimization function based on the operating cost and the charging cost include: Determine the multi-objective optimization function according to the following specified formula: Among them, α and β are the charging cost weight and the operating cost weight respectively; C charge (t) is the charging cost at time t; C operation (t) is the operating cost at time t; In the formula, E charge,i is defined as the amount of electricity charged at the i-th charging station; p i is defined as the charging unit price; N represents the number of charging stations; C operation (t) = δ1C fuel (t)+δ2C time (t); In the formula, C fuel is the fuel consumption cost, C time is the task time cost; F con (t) is the fuel consumption rate at time t; P fuel is the unit price of fuel consumption; δ1 and δ2 are the weights of fuel consumption cost and task time cost respectively; T delay is the delay time of the transportation task caused by charging; c time It is the unit price of time cost, which is linearly related to the urgency of the task.

8. The method according to claim 1, characterized in that Based on the MLD model and the MPC architecture, the energy management strategy of the extended-range hybrid light truck is determined in combination with the multi-objective optimization function to perform energy management control of the current extended-range hybrid light truck, including: The following steps are performed continuously in the MPC framework: Based on the MLD model and the multi-objective optimization function, an optimization problem including multiple decision variables is constructed; the optimization problem is used to minimize the operating cost and the charging cost by optimizing the control strategy, while ensuring that the system meets various constraints; wherein the multiple decision variables include: the engine power, the generator power, the drive motor power, the battery power, the start and stop of the range extender, whether charging is possible, and the gear position of the motor at each moment in the future time window; Using mixed integer linear programming method to solve the optimization problem, to obtain the optimal control strategy in the future time window; The operation of the extended-range hybrid light truck is controlled according to the optimal control strategy.

9. An energy management control device for an extended-range hybrid light truck, characterized in that: The device comprises: An energy demand prediction module is used to obtain the current task details, historical driving data, current vehicle operation data and historical energy consumption data of the extended-range hybrid light truck, and obtain the predicted energy demand data of the extended-range hybrid light truck through reinforcement learning and energy consumption prediction; a charging analysis module, used to obtain unloading point information, cargo information, and charging facility information of each unloading point, and determine a charging analysis result of each unloading point based on the unloading point information, cargo information, charging facility information, and the predicted energy demand data of each unloading point; A model building module, used to build an MLD model based on the predicted energy demand data and the charging analysis result; A function building module, used to determine the operating cost based on the fuel consumption cost and the transportation time cost; determine the charging cost based on the charging charge standard; and build a multi-objective optimization function based on the operating cost and the charging cost; The energy management module is used to determine the energy management strategy of the extended-range hybrid light truck based on the MLD model and the MPC architecture in combination with the multi-objective optimization function, so as to perform energy management control of the current extended-range hybrid light truck.

10. An electronic device, characterized in that: The method comprises a processor and a memory, wherein the memory stores computer executable instructions that can be executed by the processor, and the processor executes the computer executable instructions to implement the method according to any one of claims 1 to 8.

11. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer-executable instructions, and when the computer-executable instructions are called and executed by a processor, the computer-executable instructions prompt the processor to implement the method according to any one of claims 1 to 8.

Images