Energy optimization-oriented dual-motor electric vehicle energy and heat integrated management method and system

Abstract

The invention relates to the technical field of electric vehicle energy management strategies, and discloses a dual-motor electric vehicle energy and heat integrated management method and system oriented to energy optimization, and the method comprises the steps: building a front and rear motor torque distribution model based on a vehicle dynamics relation; constructing a vehicle integrated thermal management system model; based on a TD3 algorithm, the torque distribution model is coupled with the vehicle integrated thermal management system model, and the coupled model is modeled into a Markov decision problem; an E-TD3 algorithm is introduced, and then the energy and heat integrated management method based on the E-TD3 algorithm is obtained; a state space and an action space including the vehicle running state and the key component temperature are defined, and a reward function with the minimum total energy consumption and the stable temperature as targets is constructed. According to the invention, cooperative control of the battery, the double motors and the temperature of the passenger compartment can be realized, comprehensive energy consumption is effectively reduced, and system stability and economy are improved.

Description

Technical Field

[0001] This invention belongs to the field of electric vehicle energy management strategy technology, and relates to an energy and thermal integrated management method and system for dual-motor electric vehicles oriented towards energy optimization. Background Technology

[0002] Battery electric vehicles (BEVs) have become an important solution for addressing climate change and promoting sustainable transportation due to their advantages such as zero emissions, low maintenance costs, and high energy efficiency. However, their actual performance is highly dependent on energy management strategies (EMS) and thermal management strategies (TMS). EMS is responsible for optimizing battery power distribution to ensure driving range, while TMS is responsible for maintaining the temperature of key components such as the battery, motor, and passenger compartment within their optimal operating range to improve overall vehicle performance and safety.

[0003] On the one hand, existing EMS research focuses on power distribution optimization of dual-motor or multi-motor systems. While this has improved vehicle economy to some extent, it mostly assumes that the electric drive components are in a constant temperature state and ignores the impact of temperature changes on system efficiency. This may lead to problems such as decreased vehicle energy utilization efficiency, poor thermal management, and even increase the risk of overheating or damage to the electric drive system.

[0004] On the other hand, existing TMS research largely focuses on temperature control of single components or independent loops, lacking synergistic optimization with energy management, making it difficult to cope with complex and variable operating conditions. Although some studies have attempted to integrate thermal management and energy management for optimization, these have mostly focused on hybrid vehicles and have not yet systematically revealed the coupling mechanism of thermal-energy management in dual-motor pure electric vehicles. With the development of artificial intelligence, deep reinforcement learning is gradually being applied to TMS; however, existing learning-based thermal management strategies still need improvement in terms of learning efficiency, convergence speed, and real-time performance. Summary of the Invention

[0005] The purpose of this invention is to provide an energy-optimized integrated management method and system for the energy and thermal aspects of dual-motor electric vehicles, which can achieve coordinated control of the temperature of the battery, dual motors and passenger compartment, effectively reduce overall energy consumption and improve system stability and economy.

[0006] To solve the above-mentioned technical problems, the present invention is implemented using the following technical solution.

[0007] In a first aspect, the present invention proposes an energy-optimized integrated energy and thermal management method for dual-motor electric vehicles, comprising:

[0008] A torque distribution model for the front and rear motors was established based on vehicle dynamics.

[0009] A vehicle integrated thermal management system model is constructed, which includes a battery model, a battery thermal management model, a motor thermal management model, and a passenger compartment thermal management model.

[0010] Based on the TD3 algorithm, the torque distribution model is coupled with the vehicle integrated thermal management system model to obtain the energy and thermal integrated management model; the energy and thermal integrated management model is modeled as a Markov decision problem; the E-TD3 algorithm is introduced under the Markov decision framework to obtain the energy and thermal integrated management method based on the E-TD3 algorithm.

[0011] Based on the aforementioned energy and thermal integration management method, a state space and action space including the vehicle's operating status and the temperature of key components are defined, and a reward function is constructed with the goal of minimizing total energy consumption and stabilizing temperature.

[0012] In conjunction with the first aspect, the energy and heat integrated management method of the present invention further includes conducting simulation experiments based on the energy and heat integrated management method to verify the performance of the energy and heat integrated management method.

[0013] In conjunction with the first aspect, the establishment of the front and rear motor torque distribution model based on vehicle dynamics includes:

[0014] ;

[0015] in, The conversion factor representing the rotating mass; It's about the quality of the vehicle; It is the acceleration of the vehicle; Indicates the slope angle; It is the rolling resistance coefficient; It is gravitational acceleration; It is the air drag coefficient; Indicates the wheel radius; It is the vehicle speed; It is the frontal area of ​​the vehicle; Indicates the required drive torque;

[0016] The expression for the torque distribution model between the front and rear motors is:

[0017] ;

[0018] in, Indicates the torque distribution coefficient; Indicates the gear ratio of the front reducer; Indicates the gear ratio of the rear reducer; and These are the torques of motor 1 and motor 2, respectively;

[0019] The formula for calculating the battery energy consumed to drive an electric vehicle is as follows:

[0020] ;

[0021] in, and These are the rotational speeds of motor 1 and motor 2, respectively. and The efficiencies of motor 1 and motor 2 are respectively; variables Changes in driving and braking scenarios: Indicates positive traction torque. Indicates regenerative braking; This indicates the battery energy consumed to power an electric vehicle.

[0022] In conjunction with the first aspect, the method for constructing the vehicle integrated thermal management system model is as follows:

[0023] The expression for the battery model is:

[0024] ;

[0025] in, Indicates open-circuit voltage; , and These represent the battery's terminal voltage, battery current, and battery internal resistance, respectively. The battery power is represented by the following formula:

[0026] ;

[0027] in, Battery energy consumed by the vehicle's thermal management system; This represents the battery energy consumed to power an electric vehicle; This refers to the compressor power. This refers to the fan power of the radiator; This refers to the power of the blower. The power of the motor and water pump; For battery-powered water pumps;

[0028] The expression for the battery thermal management model is as follows:

[0029] ;

[0030] in, and These represent the battery's mass and specific heat capacity, respectively. Indicates the heat transfer coefficient; and These represent the temperatures of the battery and the battery coolant, respectively. This indicates the heat power generated by the battery itself; This indicates the thermal power of the battery to dissipate heat to a low-temperature environment; This indicates the rate of change of pool temperature over time. Indicates battery mass flow rate;

[0031] The method for constructing the motor thermal management model is as follows:

[0032] The heat generated by the motor is calculated based on its operating power and efficiency, as shown in the following formula:

[0033] ;

[0034] in, This indicates the heat generated by the motor; Indicates motor power; Indicates motor efficiency;

[0035] The heat dissipation process of an electric motor is simplified into two heat transfer mechanisms: one is convective heat transfer with the coolant; the other is natural heat dissipation to the external environment, as shown in the following equation:

[0036] ;

[0037] in, This indicates the amount of heat dissipation through convective heat transfer between the motor and the coolant. This indicates the amount of heat the motor naturally dissipates to the external environment.

[0038] During the heat dissipation process of the motor, the temperature change inside the motor is described by the following formula:

[0039] ;

[0040] in, This indicates the amount of heat dissipated through convection between the motor and the coolant. This indicates the amount of heat the motor naturally dissipates to the external environment. and These represent the heat transfer coefficient and heat exchange area between the motor and the coolant, respectively. and These represent the heat transfer coefficient and heat exchange area between the motor and the external environment, respectively. , and These represent the temperatures of the motor, coolant, and ambient temperature, respectively. This indicates the specific heat capacity of the motor; Indicates the mass of the motor;

[0041] The method for constructing the crew cabin thermal management model is as follows:

[0042] The passenger compartment thermal management model includes passenger compartment temperature calculation, external convective heat transfer, and roof temperature variation.

[0043] The dynamic changes in the crew cabin temperature are expressed by the following formula:

[0044] ;

[0045] in, Indicates the temperature of the crew cabin; Indicates time, For the air quality in the crew cabin, The specific heat capacity of air; The solar radiation heat load is determined by meteorological conditions and time, and is obtained empirically. This indicates that heat transfer in the vehicle body is directly related to the thermal properties of the body materials, which can be obtained through experience. This indicates the cooling capacity provided by the air conditioning system; External convective heat transfer is represented by the following formula:

[0046] ;

[0047] in, Indicates the heat transfer coefficient between the exterior surface of the vehicle and the environment; The outer surface area of ​​the crew cabin roof; and These are the average temperature of the outer surface of the crew compartment roof and the ambient temperature, respectively.

[0048] The roof temperature changes over time as follows:

[0049] ;

[0050] in, This represents the heat transfer coefficient between the interior surfaces of the crew compartment and the air inside the compartment. This refers to the total surface area inside the crew compartment; This refers to the heat capacity of the inner surface of the roof.

[0051] In conjunction with the first aspect, the vehicle integrated thermal management system model further includes a thermal management auxiliary component model, which includes a motor water pump model, a fan model, a blower model, and a compressor model.

[0052] The expression for the motor-pump model is:

[0053] ;

[0054] in, For motor water pump flow rate, For the pressure rise of the motor and water pump, For motor and water pump efficiency, This refers to the density of the coolant.

[0055] The expressions for the fan model and the blower model are as follows:

[0056] ;

[0057] in, Indicates fan speed; and These represent the blower power and blower flow rate, respectively. and For fitting parameters, , ; This refers to the fan power.

[0058] The expression for the compressor model is:

[0059] ;

[0060] in, Indicates the exhaust enthalpy. Indicates the inspiratory enthalpy. This represents the isentropic exhaust enthalpy. It is isentropic efficiency; Inhalation density, This refers to the compressor displacement. This refers to the compressor speed. For compressor flow rate; and These represent mechanical efficiency and compressor efficiency, respectively. This indicates the compressor power.

[0061] In conjunction with the first aspect, further, based on the TD3 algorithm, the torque distribution model is coupled with the vehicle integrated thermal management system model to obtain an energy and thermal integrated management model; the energy and thermal integrated management model is modeled as a Markov decision problem; the E-TD3 algorithm is introduced under the Markov decision framework, thereby obtaining an energy and thermal integrated management method based on the E-TD3 algorithm; including:

[0062] The E-TD3 algorithm, while performing population evolution through the cross-entropy method, utilizes the actor-commentator architecture of the TD3 algorithm to perform gradient updates on individuals in the population to achieve local optimization. The TD3 network architecture update mechanism, which forms the basis of E-TD3 gradient updates, is as follows:

[0063] The actor network updates its parameters by maximizing the expected cumulative return, as shown in the following equation:

[0064] ;

[0065] The two critic networks are updated by minimizing the TD error to address the overestimation problem, as shown in the following equation:

[0066] ;

[0067] The target actor network uses a soft update mechanism, as shown in the following formula:

[0068] ;

[0069] in, This refers to the number of samples in a small batch. and These represent the parameters of the critic network and the target critic network, respectively. Discount factor; and These are the loss functions for the actor network and the critic network, respectively; In a certain state With action The next goal value; For the target action; For instant rewards; and These are the parameters for the actor network and the target actor network, respectively; This is a soft update factor; Indicates the updated status; Indicates that the actor network is in a state Strategies for the time; This indicates that the commentator network 1 value; Indicates target commentator network of value; Commentator Network of value, , representing critic networks 1 and 2 respectively;

[0070] The cross-entropy method uses the current Gaussian distribution Sample several policy parameters Update as follows and A small noise term is added during the update to prevent covariance degradation.

[0071] ;

[0072] ;

[0073] in, Represents a noise term; Indicates the elite rate, ; Indicates the number of people in the group; Indicates the first Each mean; Indicates the first Each weighting coefficient; This represents the old mean; This represents the new mean; Represent the new covariance matrix; Indicates the first Parameters of an actor network;

[0074] A set of actor network parameters is generated by sampling from the current Gaussian distribution using the cross-entropy method, and then divided into two parts: one part of the individuals is directly evaluated using the cross-entropy method; the other part of the individuals undergoes gradient update using TD3 before evaluation, as shown in the following equation:

[0075] ;

[0076] in, This represents the actor network parameters after gradient update. This represents the actor network parameters before gradient update. This is the learning rate.

[0077] In conjunction with the first aspect, further, based on the energy and thermal integration management method, a state space and action space including the vehicle's operating state and the temperature of key components are defined, and a reward function is constructed with the objectives of minimizing total energy consumption and stabilizing temperature, including:

[0078] The expression for the reward function is:

[0079] ;

[0080] in, and These represent the passenger cabin temperature and the passenger cabin reference temperature, respectively. and These represent the temperature of motor 1 and the reference temperature of motor 1, respectively. and These represent the temperature of motor 2 and the reference temperature of motor 2, respectively. and These represent the battery temperature and the battery reference temperature, respectively. The weighting coefficients are used to balance multi-objective optimization. ; This indicates the power consumption of the vehicle's thermal management system; This indicates the power consumption of the energy management system; Indicates a reward;

[0081] The method for constructing the state space of the integrated energy and thermal management method is as follows:

[0082] The state space includes the state space of the energy management strategy. State space of thermal management strategy ;

[0083] State space of energy management strategy The definition is as follows:

[0084] ;

[0085] State space of thermal management strategy The definition is as follows:

[0086] ;

[0087] State space of integrated energy and thermal management methods Defined as:

[0088] ;

[0089] For the energy management strategy (EMS), the torque distribution coefficient between the two motors is selected. As a control variable; for the thermal management strategy (TMS), the three-way valve state is selected. Four-way valve status Compressor speed Fan speed Blower speed Motor and water pump speed and battery water pump speed For control variables;

[0090] Action space of integrated energy and thermal management methods Defined as follows:

[0091] .

[0092] Secondly, this invention proposes an energy-optimized integrated energy and thermal management system for dual-motor electric vehicles, comprising:

[0093] The torque distribution model building module is configured to establish a torque distribution model between the front and rear motors based on vehicle dynamics relationships.

[0094] The vehicle integrated thermal management system model building module is configured to build a vehicle integrated thermal management system model, which includes a battery model, a battery thermal management model, a motor thermal management model, and a passenger compartment thermal management model.

[0095] The E-TD3 algorithm module is configured to couple the torque distribution model with the vehicle integrated thermal management system model based on the TD3 algorithm to obtain the energy and thermal integrated management model; the energy and thermal integrated management model is modeled as a Markov decision problem; the E-TD3 algorithm is introduced into the Markov decision framework to obtain the energy and thermal integrated management method based on the E-TD3 algorithm.

[0096] The optimization decision module is configured to define a state space and action space, including the vehicle's operating status and the temperature of key components, based on the energy and heat integration management method, and to construct a reward function with the goal of minimizing total energy consumption and stabilizing temperature.

[0097] Thirdly, the present invention proposes a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described energy-optimized dual-motor electric vehicle energy and thermal integration management method.

[0098] Fourthly, the present invention provides a computer device comprising:

[0099] Memory, used to store computer programs;

[0100] A processor is used to execute the computer program to implement the steps of the above-described energy-optimized dual-motor electric vehicle energy and thermal integration management method.

[0101] Fifthly, the present invention proposes a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described energy-optimized dual-motor electric vehicle energy and thermal integration management method.

[0102] Compared with the prior art, the beneficial effects achieved by the present invention are as follows:

[0103] (1) Based on the dual-delay deep deterministic strategy gradient algorithm, this invention introduces the cross-entropy method to optimize the original thermal management strategy and energy management strategy. It can realize the coordinated control of battery, dual motor and passenger compartment temperature, effectively reduce overall energy consumption, improve system stability and economy, and provide a feasible intelligent control scheme for the efficient operation of electric vehicles.

[0104] (2) This invention proposes an integrated energy and heat management method (ITEMS) based on evolutionary deep reinforcement learning (E-TD3) that combines the gradient update capability of traditional TD3 with the evolutionary search capability of CEM (coarse exact matching, a statistical matching method). While ensuring sample efficiency, it enhances the global search capability and effectively solves the problems of traditional TD3 being susceptible to hyperparameter sensitivity and CEM having low sample efficiency.

[0105] (3) This invention designs a multi-objective weighted reward function, comprehensively considering the temperature constraints of the battery, motor, and passenger compartment, as well as the overall vehicle energy consumption. The optimized ITEMS exhibits excellent performance in real-time performance, temperature regulation performance, and algorithm robustness, achieving synergistic optimization of energy and thermal management. This innovation not only improves the safety and comfort of vehicle operation but also significantly reduces energy consumption and extends battery range, providing a new approach to thermal-energy management for electric vehicles. Attached Figure Description

[0106] Figure 1 This is a schematic diagram of the framework of the vehicle integrated thermal management system in Embodiment 1 of the present invention;

[0107] Figure 2 This is the algorithm framework for the energy and thermal integration management method in Embodiment 1 of the present invention;

[0108] Figure 3 This is a learning curve diagram of the TD3 and E-TD3 algorithms in Embodiment 1 of the present invention;

[0109] Figure 4 This is a schematic diagram comparing the battery energy consumption of ITEMS based on TD3 and E-TD3 in Embodiment 1 of the present invention;

[0110] Figure 5 This is a schematic diagram comparing the temperature control of vehicle components under different algorithms in Embodiment 1 of the present invention. Detailed Implementation

[0111] The technical solution of the present invention will be described in detail below with reference to the accompanying drawings and specific embodiments. It should be understood that the embodiments of the present invention and the specific features in the embodiments are detailed descriptions of the technical solution of the present invention, rather than limitations thereof. In the absence of conflict, the embodiments of the present invention and the technical features in the embodiments can be combined with each other.

[0112] The term "and / or" simply describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " generally indicates that the preceding and following related objects have an "or" relationship.

[0113] Example 1

[0114] like Figure 1 As shown, the steps of the energy-optimized dual-motor electric vehicle energy and thermal integration management method in this embodiment are as follows:

[0115] Step 1: Establish a torque distribution model between the front and rear motors based on vehicle dynamics to obtain the torque distribution results and the battery energy consumed to drive the electric vehicle.

[0116] Step 2: Construct an integrated vehicle thermal management system that includes the battery system, motor system, passenger compartment system, and air conditioning system, and establish a model of the integrated vehicle thermal management system. The integrated vehicle thermal management system model includes a battery model, a battery thermal management model, a motor thermal management model, a passenger compartment thermal management model, and a thermal management auxiliary component model.

[0117] Step 3: Based on the TD3 algorithm, the torque distribution model from Step 1 is coupled with the vehicle integrated thermal management system model from Step 2 to obtain the energy and thermal integrated management model; the energy and thermal integrated management model is modeled as a Markov decision problem; the E-TD3 algorithm is introduced under the Markov decision framework to obtain the energy and thermal integrated management method (ITEMS) based on the E-TD3 algorithm, thereby efficiently searching for the cooperative control strategy that can achieve the optimal energy efficiency of the whole vehicle;

[0118] The E-TD3 algorithm is obtained by introducing the Cross-Entropy Method (CEM) into the TD3 algorithm framework to optimize the TD3 algorithm. By combining the global search capability of CEM with the gradient update efficiency of TD3, the E-TD3 algorithm is obtained.

[0119] Step four: Define the state space and action space, including the vehicle's operating status and the temperature of key components, and construct a reward function with total energy consumption and temperature stability as its core; key components include the motor, battery, and passenger compartment.

[0120] Step 5: Conduct simulation experiments using the energy and thermal integration management method of the present invention, compare the learning curve convergence, SOC, energy consumption, and temperature fluctuation of the traditional TD3 algorithm and the ITEMS based on the E-TD3 algorithm of the present invention, and compare the performance of the ITEMS based on the E-TD3 algorithm of the present invention with that of the ITEMS based on the existing three different algorithms. At the same time, further verify the real-time deployability of the ITEMS based on the E-TD3 algorithm of the present invention in the actual vehicle control unit through hardware-in-the-loop testing.

[0121] In this embodiment, step one specifically includes the following sub-steps:

[0122] (1.1) Construct a reference vehicle, which is a pure electric vehicle equipped with two motors (i.e., motor 1 and motor 2). The main parameters are shown in Table 1:

[0123] Table 1

[0124]

[0125] (1.2) The required driving torque for the vehicle is given by the following formula:

[0126] ;

[0127] in, The conversion factor representing the rotating mass; It's about the quality of the vehicle; It is the acceleration of the vehicle; Indicates the slope angle; It is the rolling resistance coefficient; It is gravitational acceleration. It is the air drag coefficient; Indicates the wheel radius. It is the vehicle speed. It is the frontal area of ​​the vehicle.

[0128] (1.3) The torque of the dual motors is determined by the required drive torque and the torque distribution coefficient. This decision is a key learning parameter in the energy and thermal integrated management method of this invention:

[0129] ;

[0130] in, Indicates the required drive torque; Indicates the torque distribution coefficient; Indicates the gear ratio of the front reducer; Indicates the gear ratio of the rear reducer; and These are the torques of motor 1 and motor 2, respectively.

[0131] (1.4) The battery energy consumed to drive an electric vehicle is determined by the following formula.

[0132] ;

[0133] in, and These are the rotational speeds of motor 1 and motor 2, respectively. and The efficiencies of motor 1 and motor 2 are respectively; variables Changes in driving and braking scenarios: This indicates the positive traction torque, while Indicates regenerative braking; This indicates the battery energy consumed to power an electric vehicle.

[0134] Step two specifically includes the following sub-steps: the framework of the integrated thermal management system for dual-motor electric vehicles, as follows... Figure 1 As shown.

[0135] (2.1) The vehicle integrated thermal management system includes a passenger compartment system, a battery system, a motor system, and an air conditioning system. The battery system includes a battery, a battery water pump, and a cooler; the motor system includes motor 1, motor 2, a motor water pump, and a radiator. The battery system and motor system are connected via a four-way valve and use a parallel system structure. A three-way valve is used to adjust the radiator's participation in motor cooling. The passenger compartment system includes a passenger compartment, a blower, and an evaporator; the air conditioning system includes a compressor, an electronic expansion valve, a condenser, an evaporator, and a cooler. The cooler cools the battery and passenger compartment through phase change heat transfer of the refrigerant in the refrigeration cycle.

[0136] (2.2) Constructing the battery model in the vehicle integrated thermal management system model:

[0137] ;

[0138] The above formula is a battery model, where, Indicates open-circuit voltage; , and These represent the battery's terminal voltage, battery current, and battery internal resistance, respectively. The battery power is represented by the following formula:

[0139] ;

[0140] in, Battery energy consumed by the vehicle's thermal management system; This represents the battery energy consumed to power an electric vehicle; This refers to the compressor power. This refers to the fan power of the radiator; This refers to the power of the blower. The power of the motor and water pump; This refers to the power of the battery-powered water pump.

[0141] Constructing the battery thermal management model within the vehicle integrated thermal management system model:

[0142] ;

[0143] The above formula is the battery thermal management model, where, and These represent the battery's mass and specific heat capacity, respectively. Indicates the heat transfer coefficient; and These represent the temperatures of the battery and the battery coolant, respectively. This indicates the heat power generated by the battery itself; This indicates the thermal power of the battery to dissipate heat to a low-temperature environment; This indicates the rate of change of pool temperature over time. This indicates the battery mass flow rate.

[0144] (2.3) Construct the thermal management auxiliary component model in the vehicle integrated thermal management system model. The thermal management auxiliary component model includes the motor water pump model, fan model, blower model and compressor model.

[0145] The motor-driven water pump circulates the coolant to maintain the battery and motor within their optimal operating temperature range. The working process is modeled as follows:

[0146] ;

[0147] The above formula is a model of a motor-driven water pump, where, For motor water pump flow rate, For the pressure rise of the motor and water pump, For motor and water pump efficiency, This refers to the density of the coolant.

[0148] The radiator fan promotes airflow and enhances heat dissipation; the blower is used for ventilation and heat dissipation, helping to regulate the temperature of the passenger compartment and battery, thereby improving overall cooling efficiency. The operation of the radiator fan and blower is modeled by the following formula:

[0149] ;

[0150] The above formula represents the fan model and the blower model, where, Indicates fan speed; and These represent the blower power and blower flow rate, respectively. and Let be the fitting parameters (where ) ; ); This refers to the fan power.

[0151] The compression process of the refrigerant by the compressor can be modeled by the following formula:

[0152] ;

[0153] The above formula is a compressor model, where, Indicates the exhaust enthalpy. Indicates the inspiratory enthalpy. This represents the isentropic exhaust enthalpy. It is isentropic efficiency; Inhalation density, This refers to the compressor displacement. This refers to the compressor speed. For compressor flow rate; and These represent mechanical efficiency and compressor efficiency, respectively. This indicates the compressor power.

[0154] (2.4) The motor thermal management model obtains the heat generation by calculating the motor power and motor efficiency, and establishes the motor temperature change equation by using convection heat dissipation and natural heat dissipation methods.

[0155] Construct a motor thermal management model within the vehicle integrated thermal management system model. The heat generation of the motor is calculated based on its operating power and efficiency, as shown in the following formula:

[0156] ;

[0157] The above formula is the motor thermal management model, where, This indicates the heat generated by the motor; Indicates motor power; This indicates the motor efficiency.

[0158] The heat dissipation process of an electric motor can be simplified into two main heat transfer mechanisms: one is convective heat transfer with the coolant; the other is natural heat dissipation to the external environment, as shown in the following equation:

[0159] ;

[0160] in, This indicates the amount of heat dissipation through convective heat transfer between the motor and the coolant. This indicates the amount of heat the motor naturally dissipates to the external environment.

[0161] During the heat dissipation process of the motor, the temperature change inside the motor is described by the following formula:

[0162] ;

[0163] in, This indicates the amount of heat dissipated through convection between the motor and the coolant. This indicates the amount of heat the motor naturally dissipates to the external environment. and These represent the heat transfer coefficient and heat exchange area between the motor and the coolant, respectively. and These represent the heat transfer coefficient and heat exchange area between the motor and the external environment, respectively. , and These represent the temperatures of the motor, coolant, and ambient temperature, respectively. This indicates the specific heat capacity of the motor; This indicates the mass of the motor.

[0164] (2.5) Construct the passenger compartment thermal management model in the vehicle integrated thermal management system model. The passenger compartment thermal management model includes passenger compartment temperature calculation, external convection heat transfer, and the change law of roof temperature over time.

[0165] The dynamic changes in the crew cabin temperature can be expressed by the following formula:

[0166] ;

[0167] in, Indicates the temperature of the crew cabin; Indicates time, For the air quality in the crew cabin, The specific heat capacity of air; The solar radiation heat load is determined by meteorological conditions and time, and is obtained empirically. This indicates that heat transfer in the vehicle body is directly related to the thermal properties of the body materials, which can be obtained through experience. This indicates the cooling capacity provided by the air conditioning system; This represents external convective heat transfer, which is affected by vehicle speed, ambient temperature, and heat exchange between the vehicle's exterior surface and the surrounding air. It can be calculated using the following formula:

[0168] ;

[0169] in, Indicates the heat transfer coefficient between the exterior surface of the vehicle and the environment; The outer surface area of ​​the crew cabin roof; and These are the average temperature of the outer surface of the crew cabin roof and the ambient temperature, respectively.

[0170] The roof temperature changes over time as follows:

[0171] ;

[0172] in, This represents the heat transfer coefficient between the interior surfaces of the crew compartment and the air inside the compartment. This refers to the total surface area inside the crew compartment; This refers to the heat capacity of the inner surface of the roof.

[0173] Step three specifically includes the following sub-steps, and the algorithm framework of the Energy and Thermal Integrated Management Method (ITEMS) of the present invention is as follows: Figure 2 As shown.

[0174] (3.1) Based on the torque distribution model in step one and the vehicle integrated thermal management system model in step two, an integrated energy and thermal management model is constructed and used as the interaction environment for reinforcement learning. The control problem in this environment is modeled as a Markov decision process (MDP), and the agent determines the control problem based on the current state. (Including vehicle dynamics state and thermal management system state) Output combined action (Including torque distribution coefficient and thermal management accessory control parameters), immediate rewards for environmental feedback. And proceed to the next state. Within this MDP framework, the Evolutionary Dual-Delay Deep Deterministic Policy Gradient (E-TD3) algorithm is employed. This algorithm, while performing population evolution through the cross-entropy method (CEM), utilizes the Actor-Critic architecture of the TD3 algorithm to update the gradients of individuals within the population, thereby achieving local optimization. The TD3 network architecture update mechanism, which forms the basis of the E-TD3 gradient update, is as follows:

[0175] The Actor Network updates its parameters by maximizing the expected cumulative reward, as shown in the following equation:

[0176]

[0177] The two critic networks (Critic Networks) are updated by minimizing the TD error to address the overestimation problem, as shown in the following equation:

[0178]

[0179] The target Actor network employs a soft update mechanism, as shown in the following equation:

[0180]

[0181] in, This refers to the number of samples in a small batch. and These represent the parameters of the Critic network and the target Critic network, respectively. Discount factor; and These are the loss functions for the Actor network and the Critic network, respectively. In a certain state With action The next goal value; For the target action; For instant rewards; and These are the parameters of the Actor network and the target Actor network, respectively. This is a soft update factor; Indicates the updated status; Indicates that the actor network is in a state Strategies for the time; This indicates that the commentator network 1 value; Indicates target commentator network of value; Commentator Network of value, , representing critic networks 1 and 2 respectively (the TD3 algorithm has two critic networks).

[0182] (3.2) Cross-entropy method (CEM) with the current Gaussian distribution Sample several policy parameters They are evaluated in the environment and an elite set is selected, then updated according to the following formula. and A small noise term is added during the update to prevent covariance degradation.

[0183] ;

[0184] ;

[0185] in, This represents a small noise term, used to prevent the covariance matrix from converging too quickly in a single direction; Indicates the elite rate, ; Indicates the number of people in the group; Indicates the first Each mean; Indicates the first Each weighting coefficient; This represents the old mean; This represents the new mean; Represent the new covariance matrix; Indicates the first The parameters of an actor network.

[0186] (3.3) A set of Actor network parameters is generated by sampling from the current Gaussian distribution using CEM, and divided into two parts: one part of the individuals is directly evaluated based on CEM to maintain the diversity of the global search; the other part of the individuals is first updated by TD3 gradient before evaluation, as shown in the following equation:

[0187] ;

[0188] in, This represents the Actor network parameters after gradient update. This represents the Actor network parameters before gradient update. This is the learning rate.

[0189] The trajectories generated by all individuals during environmental interactions are stored in the experience replay pool for subsequent updates to TD3. Then, the previous... Each elite individual updates the distribution parameters, thus forming a loop optimization framework (E-TD3) that combines global exploration and local optimization.

[0190] The specific steps for step four are as follows:

[0191] (4.1) The design of the reward function is closely aligned with the research objective, namely, minimizing the energy consumption of the power battery while maintaining the motor, battery, and passenger compartment systems within their optimal operating temperature range. The reward function is set as follows:

[0192] ;

[0193] in, and These represent the passenger cabin temperature and the passenger cabin reference temperature, respectively. and These represent the temperature of motor 1 and the reference temperature of motor 1, respectively. and These represent the temperature of motor 2 and the reference temperature of motor 2, respectively. and These represent the battery temperature and the battery reference temperature, respectively. These are the weighting coefficients used to balance multi-objective optimization; This indicates the power consumption of the vehicle's thermal management system; This indicates the power consumption of the energy management system; It signifies a reward.

[0194] (4.2) In constructing the state space, the DRL (Deep Reinforcement Learning) agent should include key parameters closely related to energy management and thermal management tasks. The state space of the Energy Management Strategy (EMS) Defined as follows:

[0195] ;

[0196] State space of thermal management strategy Defined as follows:

[0197] ;

[0198] Therefore, the state space of ITEMS Defined as:

[0199] ;

[0200] (4.3) For the energy management strategy EMS, select the torque distribution coefficient between the two motors. As a control variable; for the thermal management strategy (TMS), the three-way valve state is selected. Four-way valve status Compressor speed Fan speed Blower speed Motor and water pump speed and battery water pump speed For control variables. Therefore, the action space of ITEMS. Defined as follows:

[0201] ;

[0202] (4.4) The hyperparameters for determining E-TD3 in this invention are shown in Table 2:

[0203] Table 2

[0204]

[0205] Step five specifically includes the following steps:

[0206] (5.1) A simulation platform was built based on visualization simulation software. The vehicle integrated thermal management system includes the battery system, motor system, passenger compartment system, air conditioning system and auxiliary subsystems. The auxiliary components include water pump, radiator fan, blower and compressor. The operating condition is selected as a high temperature environment (high temperature environment refers to the environment with temperature above 35℃) to examine the temperature regulation and energy consumption performance of battery, motor and passenger compartment. The control cycle is set to 10ms. All algorithms are run under the same hardware conditions and simulation configuration to ensure the comparability of results.

[0207] (5.2) This invention maintains the same scenario parameters and uses RB (Rule-based, traditional rule-based thermal management strategy), H-MPC (hierarchical predictive control method), TD3 (deep reinforcement learning method without evolutionary sampling), and E-TD3 algorithms for training, respectively, and compares the performance of different algorithms in terms of convergence and efficiency, temperature control, and energy consumption. The training conditions consist of a combination of the Worldwide Light Vehicles Test Procedure (WLTC) and the New European Driving Cycle (NEDC). Figure 3 The learning curves for the TD3 and E-TD3 algorithms are shown. Figure 4 For ITEMS battery energy consumption based on TD3 and E-TD3, Figure 5 The results show the temperature control of vehicle components under different algorithms. The E-TD3 algorithm of this invention exhibits the fastest convergence at the training level. The ITEMS based on E-TD3 in this invention can significantly reduce energy consumption at the operational level, while simultaneously controlling the temperatures of the battery, motor, and passenger compartment within the target range, verifying the feasibility and superiority of the ITEMS based on E-TD3 in this invention.

[0208] (5.3) Download the E-TD3 strategy obtained through simulation training to the vehicle control unit.

[0209] (5.4) The vehicle control unit and the energy and heat integrated management method proposed in this invention are tested in a closed loop using a hardware-in-the-loop simulation test system.

[0210] (5.5) Monitor operating time, energy consumption and temperature control performance.

[0211] (5.6) The results show that ITEMS performs well in terms of real-time performance, temperature regulation performance and algorithm robustness.

[0212] The energy and thermal integrated management method of this invention includes constructing a dynamics and energy management model for a dual-motor electric vehicle; establishing a vehicle-wide integrated thermal management system model coupling the battery, motor, and passenger compartment, including a battery thermal model, a motor thermal model, and a passenger compartment thermal model; employing the Twin Delayed Deep Deterministic Policy Gradient (TD3) algorithm to construct an integrated thermal and energy management strategy (ITEMS), and achieving battery energy consumption minimization and precise temperature control by designing the state space, action space, and multi-objective reward function; and introducing the Cross-Entropy Method on this basis. The TD3 algorithm is optimized using CEM, combining the global search capability of CEM with the gradient update efficiency of TD3 to form an evolved TD3 (E-TD3), thereby improving learning efficiency and convergence performance. Simulation results verify that the ITEMS based on E-TD3 has a higher convergence reward value, fewer convergence iterations, and can reduce the total battery energy consumption compared to the original TD3 method. Further hardware-in-the-loop experimental results show that the proposed energy and thermal integrated management method has good real-time performance and application value in actual vehicle control units (VCUs). This invention can achieve coordinated control of battery, dual motors, and passenger compartment temperature, effectively reducing overall energy consumption and improving system stability and economy.

[0213] Example 2

[0214] Based on the same inventive concept as Embodiment 1, this embodiment introduces an energy-optimized dual-motor electric vehicle energy and thermal integrated management system, including a data input layer, a system function layer, a system mechanism layer, and a system service layer;

[0215] The data input layer is used to collect vehicle operating status information and environmental parameters, such as vehicle speed, required driving torque, battery state of charge, battery and dual motor temperatures, and cabin temperature.

[0216] The system functional layer integrates and processes the collected raw data from multiple sources, and calls the energy and heat integrated management model to perform real-time calculation and evaluation of energy consumption and temperature indicators. Together, they form a unified data-driven layer, providing basic support for the system service layer.

[0217] The system mechanism layer embeds the Evolutionary Dual-Delay Deep Deterministic Policy Gradient Algorithm (E-TD3), which combines reinforcement learning with evolutionary search methods to overcome the shortcomings of traditional energy management and thermal management strategies in terms of convergence, real-time performance, and multi-objective balance, providing core decision-making capabilities for the system service layer.

[0218] Data-driven and mechanism-driven approaches interact to form a hybrid "data-mechanism-intelligence" feedback mode, thereby enabling the system service layer to achieve coordinated optimization and real-time control of energy distribution and thermal state in dual-motor electric vehicles. Specific implementation details for each layer are detailed in Example 1 and will not be repeated here.

[0219] Example 3

[0220] Based on the same inventive concept as other embodiments, this embodiment introduces a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described energy-optimized dual-motor electric vehicle energy and thermal integration management method.

[0221] Example 4

[0222] Based on the same inventive concept as other embodiments, this embodiment introduces a computer device, including: a memory for storing a computer program; and a processor for executing the computer program to implement the steps of the above-described energy-optimized dual-motor electric vehicle energy and thermal integration management method.

[0223] Example 6

[0224] Based on the same inventive concept as other embodiments, this embodiment introduces a computer program product, including a computer program that, when executed by a processor, implements the steps of the above-described energy-optimized dual-motor electric vehicle energy and thermal integration management method.

[0225] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0226] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0227] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0228] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0229] The embodiments of the present invention have been described above with reference to the accompanying drawings. However, the present invention is not limited to the specific embodiments described above. The specific embodiments described above are merely illustrative and not restrictive. Those skilled in the art can make many other modifications under the guidance of the present invention, and these modifications are all within the protection scope of the present invention.

Claims

1. A method for integrated energy and thermal management of dual-motor electric vehicles for energy optimization, characterized in that, include: A torque distribution model for the front and rear motors was established based on vehicle dynamics. A vehicle integrated thermal management system model is constructed, which includes a battery model, a battery thermal management model, a motor thermal management model, and a passenger compartment thermal management model. Based on the TD3 algorithm, the torque distribution model is coupled with the vehicle integrated thermal management system model to obtain the energy and thermal integrated management model; the energy and thermal integrated management model is modeled as a Markov decision problem. The E-TD3 algorithm is introduced into the Markov decision framework, and then an energy and thermal integrated management method based on the E-TD3 algorithm is obtained. Based on the aforementioned energy and thermal integration management method, a state space and action space including the vehicle's operating status and the temperature of key components are defined, and a reward function is constructed with the goal of minimizing total energy consumption and stabilizing temperature.

2. The energy and thermal integration management method for dual-motor electric vehicles oriented towards energy optimization according to claim 1, characterized in that: The model for front and rear motor torque distribution based on vehicle dynamics includes: ； in, The conversion factor representing the rotating mass; It's about the quality of the vehicle; It is the acceleration of the vehicle; Indicates the slope angle; It is the rolling resistance coefficient; It is gravitational acceleration; It is the air drag coefficient; Indicates the wheel radius; It is the vehicle speed; It is the frontal area of ​​the vehicle; Indicates the required drive torque; The expression for the torque distribution model between the front and rear motors is: ； in, Indicates the torque distribution coefficient; Indicates the gear ratio of the front reducer; Indicates the gear ratio of the rear reducer; and These are the torques of motor 1 and motor 2, respectively; The formula for calculating the battery energy consumed to drive an electric vehicle is as follows: ； in, and These are the rotational speeds of motor 1 and motor 2, respectively. and The efficiencies of motor 1 and motor 2 are respectively; variables Changes in driving and braking scenarios: Indicates positive traction torque. Indicates regenerative braking; This indicates the battery energy consumed to power an electric vehicle.

3. The energy and thermal integration management method for dual-motor electric vehicles oriented towards energy optimization according to claim 1, characterized in that: The method for constructing the integrated thermal management system model for the vehicle is as follows: The expression for the battery model is: ； in, Indicates open-circuit voltage; , and These represent the battery's terminal voltage, battery current, and battery internal resistance, respectively. The battery power is represented by the following formula: ； in, Battery energy consumed by the vehicle's thermal management system; This represents the battery energy consumed to power an electric vehicle; This refers to the compressor power. This refers to the fan power of the radiator; This refers to the power of the blower. The power of the motor and water pump; For battery-powered water pumps; The expression for the battery thermal management model is as follows: ； in, and These represent the battery's mass and specific heat capacity, respectively. Indicates the heat transfer coefficient; and These represent the temperatures of the battery and the battery coolant, respectively. This indicates the heat power generated by the battery itself; This indicates the thermal power of the battery to dissipate heat to a low-temperature environment; This indicates the rate of change of pool temperature over time. Indicates battery mass flow rate; The method for constructing the motor thermal management model is as follows: The heat generated by the motor is calculated based on its operating power and efficiency, as shown in the following formula: ； in, This indicates the heat generated by the motor; Indicates motor power; Indicates motor efficiency; The heat dissipation process of an electric motor is simplified into two heat transfer mechanisms: one is convective heat transfer with the coolant; the other is natural heat dissipation to the external environment, as shown in the following equation: ； in, This indicates the amount of heat dissipation through convective heat transfer between the motor and the coolant. This indicates the amount of heat the motor naturally dissipates to the external environment. During the heat dissipation process of the motor, the temperature change inside the motor is described by the following formula: ； in, This indicates the amount of heat dissipated through convection between the motor and the coolant. This indicates the amount of heat the motor naturally dissipates to the external environment. and These represent the heat transfer coefficient and heat exchange area between the motor and the coolant, respectively. and These represent the heat transfer coefficient and heat exchange area between the motor and the external environment, respectively. , and These represent the temperatures of the motor, coolant, and ambient temperature, respectively. This indicates the specific heat capacity of the motor; Indicates the mass of the motor; The method for constructing the crew cabin thermal management model is as follows: The passenger compartment thermal management model includes passenger compartment temperature calculation, external convective heat transfer, and roof temperature variation. The dynamic changes in the crew cabin temperature are expressed by the following formula: ； in, Indicates the temperature of the crew cabin; Indicates time, For the air quality in the crew cabin, The specific heat capacity of air; The solar radiation heat load is determined by meteorological conditions and time, and is obtained empirically. This indicates that heat transfer in the vehicle body is directly related to the thermal properties of the body materials, which can be obtained through experience. This indicates the cooling capacity provided by the air conditioning system; External convective heat transfer is represented by the following formula: ； in, Indicates the heat transfer coefficient between the exterior surface of the vehicle and the environment; The outer surface area of ​​the crew cabin roof; and These are the average temperature of the outer surface of the crew compartment roof and the ambient temperature, respectively. The roof temperature changes over time as follows: ； in, This represents the heat transfer coefficient between the interior surfaces of the crew compartment and the air inside the compartment. This refers to the total surface area inside the crew compartment; This refers to the heat capacity of the inner surface of the roof.

4. The energy and thermal integration management method for dual-motor electric vehicles oriented towards energy optimization according to claim 1, characterized in that: The vehicle integrated thermal management system model also includes thermal management auxiliary component models, which include motor and water pump models, fan models, blower models, and compressor models. The expression for the motor-pump model is: ； in, For motor water pump flow rate, For the pressure rise of the motor and water pump, For motor and water pump efficiency, This refers to the density of the coolant. The expressions for the fan model and the blower model are as follows: ； in, Indicates fan speed; and These represent the blower power and blower flow rate, respectively. and For fitting parameters, , ; This refers to the fan power. The expression for the compressor model is: ； in, Indicates the exhaust enthalpy. Indicates the inspiratory enthalpy. This represents the isentropic exhaust enthalpy. It is isentropic efficiency; Inhalation density, This refers to the compressor displacement. This refers to the compressor speed. For compressor flow rate; and These represent mechanical efficiency and compressor efficiency, respectively. This indicates the compressor power.

5. The energy and thermal integration management method for dual-motor electric vehicles oriented towards energy optimization according to claim 1, characterized in that: The TD3 algorithm-based approach couples the torque distribution model with the vehicle integrated thermal management system model to obtain the energy and thermal integrated management model; the energy and thermal integrated management model is then modeled as a Markov decision problem. The E-TD3 algorithm is introduced into the Markov decision framework, resulting in an energy and thermal integrated management method based on the E-TD3 algorithm; including: The E-TD3 algorithm, while performing population evolution through the cross-entropy method, utilizes the actor-commentator architecture of the TD3 algorithm to update the gradients of individuals in the population, thereby achieving local optimization. The TD3 network architecture update mechanism, which forms the basis of the E-TD3 gradient update, is as follows: The actor network updates its parameters by maximizing the expected cumulative return, as shown in the following equation: ； The two critic networks are updated by minimizing the TD error to address the overestimation problem, as shown in the following equation: ； The target actor network uses a soft update mechanism, as shown in the following formula: ； in, This refers to the number of samples in a small batch. and These represent the parameters of the critic network and the target critic network, respectively. Discount factor; and These are the loss functions for the actor network and the critic network, respectively; In a certain state With action The next goal value; For the target action; For instant rewards; and These are the parameters for the actor network and the target actor network, respectively; This is a soft update factor; Indicates the updated status; Indicates that the actor network is in a state Strategies for the time; This indicates that the commentator network 1 value; Indicates target commentator network of value; Commentator Network of value, , representing critic networks 1 and 2 respectively; The cross-entropy method uses the current Gaussian distribution Sample several policy parameters Update as follows and A small noise term is added during the update to prevent covariance degradation. ； ； in, Represents a noise term; Indicates the elite rate, ; Indicates the number of people in the group; Indicates the first Each mean; Indicates the first Each weighting coefficient; This represents the old mean; This represents the new mean; Represent the new covariance matrix; Indicates the first Parameters of an actor network; A set of actor network parameters is generated by sampling from the current Gaussian distribution using the cross-entropy method, and then divided into two parts: one part of the individuals is directly evaluated using the cross-entropy method; the other part of the individuals undergoes gradient update using TD3 before evaluation, as shown in the following equation: ； in, This represents the actor network parameters after gradient update. This represents the actor network parameters before gradient update. This is the learning rate.

6. The energy and thermal integration management method for dual-motor electric vehicles oriented towards energy optimization according to claim 1, characterized in that: The energy and thermal integrated management method defines a state space and action space including the vehicle's operating status and the temperature of key components, and constructs a reward function with the objectives of minimizing total energy consumption and stabilizing temperature, including: The expression for the reward function is: ； in, and These represent the passenger cabin temperature and the passenger cabin reference temperature, respectively. and These represent the temperature of motor 1 and the reference temperature of motor 1, respectively. and These represent the temperature of motor 2 and the reference temperature of motor 2, respectively. and These represent the battery temperature and the battery reference temperature, respectively. The weighting coefficients are used to balance multi-objective optimization. ; This indicates the power consumption of the vehicle's thermal management system; This indicates the power consumption of the energy management system; Indicates a reward; The method for constructing the state space of the integrated energy and thermal management method is as follows: The state space includes the state space of the energy management strategy. State space of thermal management strategy ; State space of energy management strategy The definition is as follows: ； State space of thermal management strategy The definition is as follows: ； State space of integrated energy and thermal management methods Defined as: ； For the energy management strategy (EMS), the torque distribution coefficient between the two motors is selected. As a control variable; for the thermal management strategy (TMS), the three-way valve state is selected. Four-way valve status Compressor speed Fan speed Blower speed Motor and water pump speed and battery water pump speed For control variables; Action space of integrated energy and thermal management methods Defined as follows: 。 7. A dual-motor electric vehicle energy and thermal integration management system for energy optimization, characterized in that, include: The torque distribution model building module is configured to establish a torque distribution model between the front and rear motors based on vehicle dynamics relationships. The vehicle integrated thermal management system model building module is configured to build a vehicle integrated thermal management system model, which includes a battery model, a battery thermal management model, a motor thermal management model, and a passenger compartment thermal management model. The E-TD3 algorithm module is configured to couple the torque distribution model with the vehicle integrated thermal management system model based on the TD3 algorithm to obtain the energy and thermal integrated management model; the energy and thermal integrated management model is modeled as a Markov decision problem; the E-TD3 algorithm is introduced into the Markov decision framework to obtain the energy and thermal integrated management method based on the E-TD3 algorithm. The optimization decision module is configured to define a state space and action space, including the vehicle's operating status and the temperature of key components, based on the energy and heat integration management method, and to construct a reward function with the goal of minimizing total energy consumption and stabilizing temperature.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the energy-optimized dual-motor electric vehicle energy and thermal integration management method as described in any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory, used to store computer programs; A processor for executing the computer program to implement the steps of the energy-optimized dual-motor electric vehicle energy-thermal integrated management method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that: When executed by a processor, the computer program implements the steps of the energy-optimized dual-motor electric vehicle energy-thermal integrated management method as described in any one of claims 1 to 6.

Images