The invention relates to an automobile thermal management intelligent control method based on confrontation reinforcement learning. The method comprises the following steps: S1, collecting system environment state data; s2, establishing a thermal system model; s3, setting an initial state of the thermal system model; s4, giving a random environment disturbance d by using an adversarial agent, and giving a control action a by using a control agent; s5, the thermal system model controls the action a according to the received random environment disturbance d, the system environment state data s'of the thermal system model at the next moment, and the first reward value r and the second reward value-r of the thermal system model at the next moment; s6, based on the (s, a, s', r) data set, adopting a reinforcement learning algorithm to train a control agent, based on the (s, d, s',-r) data set, adopting the reinforcement learning algorithm to train an adversarial agent, and S7, judging whether the control agent and the adversarial agent converge or not, if not, returning to S3, and if yes, ending the process.

    本发明涉及一种基于对抗强化学习的汽车热管理智能控制方法,如下:S1:收集系统环境状态数据;S2:建立热系统模型;S3:设置热系统模型的初始状态;S4:利用对抗智能体给出随机环境扰动d,利用控制智能体给出控制动作a;S5:所述热系统模型根据接收的随机环境扰动d、控制动作a,下一时刻热系统模型的系统环境状态数据s’,下一时刻热系统模型的第一奖励值r、第二奖励值‑r;S6:基于(s、a、s’、r)数据集,采用强化学习算法对控制智能体进行训练;基于(s、d、s’、‑r)数据集,采用强化学习算法对对抗智能体进行训练;S7:判断控制智能体和对抗智能体是否都收敛,若不收敛,则返回S3;若收敛,则流程结束。


    Access

    Download


    Export, share and cite



    Title :

    Automobile thermal management intelligent control method based on confrontation reinforcement learning


    Additional title:

    一种基于对抗强化学习的汽车热管理智能控制方法


    Contributors:
    LIU YANG (author) / LIU JIAN (author) / OU JUNFENG (author) / FENG YANYAN (author) / YU HUILI (author)

    Publication date :

    2023-09-22


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    B60H ARRANGEMENTS OR ADAPTATIONS OF HEATING, COOLING, VENTILATING, OR OTHER AIR-TREATING DEVICES SPECIALLY FOR PASSENGER OR GOODS SPACES OF VEHICLES , Anordnung oder Einbau der Heizung, Kühlung, Lüftung oder anderer Luftbehandlungsvorrichtungen für die Fahrzeugräume für Reisende oder Fracht



    2v2 Air Combat Confrontation Strategy Based on Reinforcement Learning

    Wang, Jinlin / Zhu, Longtao / Yang, Hongyu et al. | Springer Verlag | 2023


    UAV Swarm Confrontation Using Hierarchical Multiagent Reinforcement Learning

    Baolai Wang / Shengang Li / Xianzhong Gao et al. | DOAJ | 2021

    Free access


    UAV Confrontation and Evolutionary Upgrade Based on Multi-Agent Reinforcement Learning

    Xin Deng / Zhaoqi Dong / Jishiyu Ding | DOAJ | 2024

    Free access