CN-122008780-A - Energy optimization-oriented dual-motor electric automobile energy heat integration management method and system

CN122008780ACN 122008780 ACN122008780 ACN 122008780ACN-122008780-A

Abstract

The invention relates to the technical field of energy management strategies of electric vehicles, and discloses an energy optimization-oriented dual-motor electric vehicle energy heat integration management method and system, wherein the method comprises the steps of establishing a front motor torque distribution model and a rear motor torque distribution model based on a vehicle dynamics relation; the method comprises the steps of constructing a whole vehicle integrated thermal management system model, coupling a torque distribution model with the whole vehicle integrated thermal management system model based on a TD3 algorithm, modeling the coupled model into a Markov decision problem, introducing an E-TD3 algorithm to obtain an energy thermal integrated management method based on the E-TD3 algorithm, defining a state space and an action space comprising the running state of a vehicle and the temperature of a key component, and constructing a reward function with minimum total energy consumption and stable temperature as targets. The invention can realize the cooperative control of the temperature of the battery, the double motors and the passenger cabin, effectively reduce the comprehensive energy consumption and improve the stability and the economy of the system.

Inventors

PENG JIANKUN
WU CHANGCHENG
ZHOU GUANGBO
PI DAWEI
GUO XIN
ZHANG HAILONG
MA CHUNYE

Assignees

东南大学

Dates

Publication Date: 20260512
Application Date: 20251205

Claims (10)

1. The energy optimization-oriented energy heat integration management method for the double-motor electric automobile is characterized by comprising the following steps of: Establishing a front motor torque distribution model and a rear motor torque distribution model based on a vehicle dynamics relation; constructing a whole vehicle integrated thermal management system model, wherein the whole vehicle integrated thermal management system model comprises a battery model, a battery thermal management model, a motor thermal management model and a passenger cabin thermal management model; Based on a TD3 algorithm, coupling a torque distribution model with a whole vehicle integrated thermal management system model to obtain a thermal integration management model, modeling the thermal integration management model into a Markov decision problem, introducing an E-TD3 algorithm under the Markov decision frame, and further obtaining a thermal integration management method based on the E-TD3 algorithm; Based on the energy heat integration management method, a state space and an action space comprising the running state of the vehicle and the temperature of the key component are defined, and a reward function which aims at minimum total energy consumption and stable temperature is constructed.
2. The energy optimization-oriented dual-motor electric vehicle energy heat integration management method of claim 1, wherein the building of the front and rear motor torque distribution model based on the vehicle dynamics relation comprises the following steps: ; Wherein, the Conversion coefficients representing the rotational mass; is the mass of the vehicle; Is the running acceleration; Representing a grade angle; is the rolling resistance coefficient; Is the acceleration of gravity; Is the air resistance coefficient; representing the radius of the wheel; Is the vehicle speed; is the frontal area of the vehicle; representing the required drive torque; The expression of the front and rear motor torque distribution model is: ; Wherein, the Representing a torque distribution coefficient; representing the front retarder gear ratio; Representing rear reducer gear ratio; And Torque of motor 1 and motor 2, respectively; the calculation formula of the battery energy consumed by the driving electric automobile is as follows: ; Wherein, the And The rotational speeds of the motor 1 and the motor 2 are respectively; And Efficiency of motor 1 and motor 2 respectively, variable Changes in driving and braking scenarios: Indicating the forward traction torque of the vehicle, Representing regenerative braking; Represents the battery power consumed to drive the electric vehicle.
3. The energy-optimization-oriented dual-motor electric vehicle energy heat integration management method of claim 1, wherein the method for constructing the whole vehicle integrated heat management system model is characterized by comprising the following steps of: the expression of the battery model is as follows: ; Wherein, the Represents an open circuit voltage; 、 And Respectively representing terminal voltage, battery current and battery internal resistance of the battery; representing battery power, given by: ; Wherein, the Battery energy consumed by a whole vehicle thermal management system; representing battery energy consumed to drive the electric vehicle; is compressor power; Fan power for the heat sink; Is the blower power; The power of the motor water pump is calculated; The power of the water pump is the power of the battery; the expression of the battery thermal management model is as follows: ; Wherein, the And (3) with Respectively representing the mass and specific heat capacity of the battery; Representing the heat transfer coefficient; And (3) with Respectively representing the temperatures of the battery and the battery cooling liquid; representing the thermal power generated by the battery itself; representing the thermal power of the battery to dissipate heat to a low temperature environment; Representing the rate of change of cell temperature over time; representing the battery mass flow; the construction method of the motor thermal management model comprises the following steps: the heating value of the motor is calculated by the running power and efficiency, and the following formula is shown: ; Wherein, the Representing the heat generated by the motor; representing motor power; representing motor efficiency; the heat dissipation process of the motor is simplified into two heat transfer mechanisms, namely, one is heat convection and heat dissipation with cooling liquid, and the other is natural heat dissipation to the external environment, wherein the heat dissipation mechanism is as follows: ; Wherein, the The heat dissipation capacity of convection heat exchange between the motor and the cooling liquid is represented; The natural heat dissipation capacity of the motor to the external environment is represented; During heat dissipation of the motor, the temperature change inside the motor is described by the following formula: ; Wherein, the The convection heat dissipation capacity between the motor and the cooling liquid is represented; The natural heat dissipation capacity of the motor to the external environment is represented; And Respectively representing the heat transfer coefficient and the heat exchange area between the motor and the cooling liquid; And Respectively representing the heat transfer coefficient and the heat exchange area between the motor and the external environment; 、 And Respectively representing the temperatures of the motor, the cooling liquid and the environment; representing the specific heat capacity of the motor; Representing the mass of the motor; The construction method of the passenger cabin thermal management model comprises the following steps: the passenger cabin thermal management model comprises passenger cabin temperature calculation, external convection heat exchange capacity and a roof temperature change rule; the dynamic change in the passenger compartment temperature calculation is represented by the following formula: ; Wherein, the Representing the passenger compartment temperature; the time is represented by the time period of the day, For the air quality of the passenger compartment, Is the specific heat capacity of air; Representing solar radiation heat load, which is determined by meteorological conditions and time and obtained through experience; Representing the heat transfer of the vehicle body, directly correlating with the thermal characteristics of the vehicle body material, and obtaining the vehicle body material through experience; representing the amount of cooling provided by the air conditioning system; Represents external convective heat transfer, calculated from the following formula: ; Wherein, the Representing the heat transfer coefficient between the exterior surface of the vehicle body and the environment; The outer surface area of the passenger cabin roof; And (3) with The average temperature and the ambient temperature of the outer surface of the top of the passenger cabin are respectively; The change rule of the roof temperature along with time is as follows: ; Wherein, the Representing the heat transfer coefficient between the interior surface of the passenger compartment and the air in the compartment; Is the total area of the inner surface of the passenger cabin; Is the heat capacity of the inner surface of the roof.
4. The energy-optimization-oriented dual-motor electric vehicle energy heat integration management method of claim 1, wherein the whole vehicle integrated thermal management system model further comprises a thermal management auxiliary model, and the thermal management auxiliary model comprises a motor water pump model, a fan model, a blower model and a compressor model; the expression of the motor water pump model is as follows: ; Wherein, the Is the flow of the water pump of the motor, For the pressure rise of the motor water pump, For the efficiency of the water pump of the motor, Is the density of the cooling liquid; the expressions of the fan model and the blower model are as follows: ; Wherein, the Indicating the fan speed; And Respectively representing blower power and blower flow; And In order to fit the parameters of the model, , ; Fan power; The expression of the compressor model is: ; Wherein, the Indicating the specific enthalpy of the exhaust gas, Represents the specific enthalpy of inspiration, Represents the isentropic specific exhaust enthalpy, Isentropic efficiency; For the suction density, For the displacement of the compressor, For the rotational speed of the compressor, Is compressor flow; And Respectively representing mechanical efficiency and compressor efficiency; Representing compressor power.
5. The energy optimization-oriented dual-motor electric vehicle energy heat integration management method of claim 1, wherein the energy optimization-oriented dual-motor electric vehicle energy heat integration management method is characterized by comprising the steps of coupling a torque distribution model with a whole vehicle integrated heat management system model based on a TD3 algorithm to obtain an energy heat integration management model, modeling the energy heat integration management model into a Markov decision problem, introducing an E-TD3 algorithm under the Markov decision frame to obtain the energy heat integration management method based on the E-TD3 algorithm, and comprising the following steps: The E-TD3 algorithm performs gradient update on individuals in the population by utilizing an actor-critic framework of the TD3 algorithm while performing population evolution by a cross entropy method to realize local optimization, wherein a TD3 network framework update mechanism serving as a basis of E-TD3 gradient update is as follows: The actor network updates the parameters by maximizing the expected cumulative returns as shown in the following equation: ; Two critics networks are updated by minimizing TD errors to solve the overestimation problem, as shown in the following equation: ; the target actor network employs a soft update mechanism as shown in the following equation: ; Wherein, the For small sample numbers; And Parameters of the critics network and the target critics network are respectively represented; Is a discount factor; And (3) with Loss functions of the actor network and the critics network respectively; to be in a certain state And actions Lower target A value; Is a target action; Is an instant rewards; And Parameters of the actor network and the target actor network respectively; is a soft update factor; Representing the updated state; Representing the status of the actor's network A policy at that time; representing a critics network 1 A value; Representing a target critics network A kind of electronic device A value; representing a critic network A kind of electronic device The value of the sum of the values, Respectively representing critics networks 1,2; Cross entropy method is distributed in the current Gaussian Sampling a plurality of policy parameters Updating as follows And (3) with Adding a tiny noise item to prevent covariance degradation during updating; ; ; Wherein, the Representing a noise term; the elite rate is indicated by the index, ; Representing the population number; Represent the first The average value; Represent the first A plurality of weight coefficients; representing the old mean; representing the new mean; Representing a new covariance matrix; Represent the first Parameters of the individual actor network; sampling and generating a group of actor network parameters from the current Gaussian distribution by a cross entropy method, and dividing the actor network parameters into two parts, wherein one part of individuals directly perform performance evaluation based on the cross entropy method, and the other part of individuals undergo gradient update of TD3 before evaluation, wherein the gradient update is shown in the following formula: ; Wherein, the Representing the actor network parameters after gradient update, Representing actor network parameters prior to gradient update, Is the learning rate.
6. The energy-optimization-oriented dual-motor electric vehicle energy heat integration management method of claim 1, wherein the defining a state space and an action space including a vehicle running state and a key component temperature based on the energy heat integration management method, and constructing a reward function targeting at minimum total energy consumption and stable temperature comprises: the expression of the reward function is: ; Wherein, the And Respectively representing the passenger cabin temperature and the passenger cabin reference temperature; And Respectively representing the temperature of the motor 1 and the reference temperature of the motor 1; And Respectively representing the temperature of the motor 2 and the reference temperature of the motor 2; And Respectively representing the battery temperature and the reference temperature of the battery; To balance the weight coefficients of the multi-objective optimization, ; Representing the power consumption of the whole vehicle thermal management system; representing power consumption of the energy management system; Representing a reward; the construction method of the state space of the heat integration management method comprises the following steps: the state space includes a state space of an energy management strategy And state space for thermal management policies ; State space for energy management policies Is defined as follows: ; state space for thermal management policies Is defined as follows: ; state space capable of thermal integration management method The definition is as follows: ; for energy management strategy EMS, a torque distribution coefficient between two motors is selected As control variable, for thermal management strategy TMS, three-way valve state is selected State of four-way valve Rotational speed of compressor Rotational speed of fan Rotational speed of blower Rotation speed of motor water pump Battery water pump rotational speed Is a control variable; action space capable of heat integration management method Is defined as the following formula: 。
7. Energy optimization-oriented dual-motor electric automobile energy heat integration management system is characterized by comprising: a torque distribution model building module configured to build a front and rear motor torque distribution model based on a vehicle dynamics relationship; The system comprises a whole vehicle integrated thermal management system model construction module, a passenger cabin management module and a passenger cabin management module, wherein the whole vehicle integrated thermal management system model construction module is configured to construct a whole vehicle integrated thermal management system model, and the whole vehicle integrated thermal management system model comprises a battery model, a battery thermal management model, a motor thermal management model and a passenger cabin thermal management model; The E-TD3 algorithm obtaining module is configured to couple the torque distribution model and the whole vehicle integrated thermal management system model based on the TD3 algorithm to obtain a thermal integration management model, model the thermal integration management model into a Markov decision problem, introduce the E-TD3 algorithm under the Markov decision frame, and further obtain the thermal integration management method based on the E-TD3 algorithm; And the optimization decision module is configured to define a state space and an action space comprising the running state of the vehicle and the temperature of the key component based on the heat integration management method, and construct a reward function aiming at the minimum total energy consumption and the stable temperature.
8. A computer readable storage medium, on which a computer program is stored, is characterized in that the computer program, when being executed by a processor, implements the steps of the energy-optimization-oriented dual-motor electric vehicle energy heat integration management method according to any one of claims 1 to 6.
9. A computer device, comprising: A memory for storing a computer program; a processor for executing the computer program to implement the energy-optimization-oriented dual-motor electric vehicle energy heat integration management method of any one of claims 1-6.
10. A computer program product comprises a computer program and is characterized in that the computer program, when being executed by a processor, realizes the steps of the energy-optimization-oriented dual-motor electric vehicle energy heat integration management method according to any one of claims 1 to 6.

Description

Energy optimization-oriented dual-motor electric automobile energy heat integration management method and system Technical Field The invention belongs to the technical field of energy management strategies of electric vehicles, and relates to an energy optimization-oriented dual-motor electric vehicle energy heat integration management method and system. Background The advantages of zero emission, low maintenance cost, high energy efficiency and the like of the pure electric vehicle (BEV) become an important solution for coping with climate change and promoting sustainable traffic. However, its practical performance is highly dependent on energy management policies (EMS) and thermal management policies (TMS). The EMS is responsible for optimizing battery power distribution to ensure the endurance mileage, and the TMS is responsible for maintaining the temperatures of key components such as the battery, the motor, the passenger cabin and the like in the optimal working range so as to improve the performance and the safety of the whole vehicle. On the one hand, the existing EMS researches focus on optimizing the power distribution of a dual-motor or multi-motor system, but mostly assume that the electric driving component is in a constant temperature state, neglect the influence of temperature change on the system efficiency, possibly cause the problems of reduced energy utilization efficiency and poor thermal management effect of the vehicle, and even increase the risk of overheat or damage of the electric driving system. On the other hand, the existing TMS researches focus on temperature control of a single component or an independent circuit, lack of cooperative optimization with energy management, and are difficult to cope with complex and variable working conditions. While there have been studies attempting to integrate optimization of thermal management with energy management, much attention has been paid to hybrid vehicles, and no system has yet revealed a mechanism for coupling thermal-energy management in a two-motor electric vehicle. With the development of artificial intelligence, deep reinforcement learning is gradually applied to TMS, however, the existing learning-based thermal management strategy has yet to be improved in learning efficiency, convergence speed and real-time. Disclosure of Invention The invention aims to provide an energy-optimization-oriented double-motor electric automobile energy heat integration management method and system, which can realize the cooperative control of the temperatures of a battery, a double motor and a passenger cabin, effectively reduce comprehensive energy consumption and improve system stability and economy. In order to solve the technical problems, the invention is realized by adopting the following technical scheme. In a first aspect, the invention provides an energy optimization-oriented dual-motor electric vehicle energy heat integration management method, which comprises the following steps: Establishing a front motor torque distribution model and a rear motor torque distribution model based on a vehicle dynamics relation; constructing a whole vehicle integrated thermal management system model, wherein the whole vehicle integrated thermal management system model comprises a battery model, a battery thermal management model, a motor thermal management model and a passenger cabin thermal management model; Based on a TD3 algorithm, coupling a torque distribution model with a whole vehicle integrated thermal management system model to obtain a thermal integration management model, modeling the thermal integration management model into a Markov decision problem, introducing an E-TD3 algorithm under the Markov decision frame, and further obtaining a thermal integration management method based on the E-TD3 algorithm; Based on the energy heat integration management method, a state space and an action space comprising the running state of the vehicle and the temperature of the key component are defined, and a reward function which aims at minimum total energy consumption and stable temperature is constructed. With reference to the first aspect, the heat-integration-capable management method of the present invention further includes performing a simulation experiment according to the heat-integration-capable management method, to verify performance of the heat-integration-capable management method. With reference to the first aspect, further, the establishing a front-rear motor torque distribution model based on the vehicle dynamics relation includes: ; Wherein, the Conversion coefficients representing the rotational mass; is the mass of the vehicle; Is the running acceleration; Representing a grade angle; is the rolling resistance coefficient; Is the acceleration of gravity; Is the air resistance coefficient; representing the radius of the wheel; Is the vehicle speed; is the frontal area of the vehicle; representing the required drive torque; The e