Hybrid off-road vehicle thermal cooperative control method and system

By employing a combined energy and thermal control method based on GMM and DDPG algorithms, the problem of independent operation of energy management and thermal management in hybrid off-road vehicles under extreme conditions is solved. This achieves joint optimization of energy and thermal management, improves the overall vehicle energy efficiency and thermal stability, adapts to complex operating conditions, and ensures passenger comfort.

CN122402205APending Publication Date: 2026-07-17JIANGSU UNIV +1

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
JIANGSU UNIV
Filing Date
2026-04-17
Publication Date
2026-07-17

AI Technical Summary

Technical Problem

The energy management system and thermal management system of existing hybrid off-road vehicles operate independently, which limits the improvement of energy efficiency under extreme conditions, makes it impossible to dynamically balance the thermal-energy conflict, and results in insufficient overall vehicle energy efficiency and thermal stability.

Method used

A co-optimization control method based on Gaussian mixture model (GMM) and deep deterministic policy gradient (DDPG) algorithm is adopted. Through operating condition identification and reinforcement learning, the joint optimization of energy and thermal management system is achieved. The cooling loop heat load, power ratio of thermal management system and equivalent factor sensitivity are used as state inputs to train the policy network to adjust energy distribution and thermal management actuators in real time.

Benefits of technology

It significantly improves the overall vehicle energy efficiency in complex off-road environments, ensures the thermal stability of key components and passenger comfort, has strong system adaptability and robustness, and the control strategy has real-time and adaptive optimization capabilities.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN122402205A_ABST
    Figure CN122402205A_ABST
Patent Text Reader

Abstract

本发明提供了一种混合动力越野车辆能热协同控制方法及系统。首先,通过采集不同越野环境下的典型工况信息及车辆运行状态信息,构建工况–状态数据库;随后,将工况与状态信息作为强化学习的状态空间,将能量管理策略中的等效因子调节量和热管理系统的执行控制参数作为动作空间,利用深度强化学习算法训练智能体直至收敛;最终实现车辆运行阶段的确定性策略在线输出。本发明采用高斯混合模型对复杂越野工况进行实时分类,并特别提取了三个能够表征车辆能量与热特性耦合关系的关键特征,将其作为强化学习智能体的输入,显著提升了策略在复杂越野场景下的有效性、适应性与稳定性,从而实现混动越野车辆能量管理与热管理的一体化智能控制。
Need to check novelty before this filing date? Find Prior Art