基于改进DQN算法的陶瓷梭式窑温度智能控制  

Intelligent Temperature Control of Ceramic Shuttle Kiln Based on Improved DQN Algorithm

作　　者：朱永红 余英剑 李蔓华 ZHU Yonghong;YU Yingjian;LI Manhua(School of Mechanical and Electronic Engineering,Jingdezhen Ceramic University,Jingdezhen 333403,Jiangxi,China)

机构地区：[1]景德镇陶瓷大学机械电子工程学院,江西景德镇333403

出　　处：《中国陶瓷工业》2024年第5期33-38,共6页China Ceramic Industry

基　　金：国家自然科学基金(62063010);江西省重大科技研发专项(20214ABC28W003)资助。

摘　　要：针对陶瓷梭式窑大延迟、非线性、慢时变及强耦合等特点,提出了基于改进DQN算法的陶瓷梭式窑温度智能控制方法。首先,建立了基于BP神经网络的陶瓷梭式窑模型。然后,提出了基于改进DQN算法的智能控制方法。最后,对所提出的方法进行了仿真研究。仿真结果表明,改进的PRDQN算法的温度控制相对误差为0℃~5℃,温度控制效果相对较好。因此,所提出的方法是有效且可行的。Aiming at the characteristics of large delay,nonlinear,slow time varying and strong coupling,an intelligent temperature control method based on improved DQN algorithm was proposed.Firstly,the model of ceramic shuttle kiln based on BP neural network was established.Then an intelligent control method based on improved DQN algorithm is proposed.Finally,the proposed method is simulated.The simulation results show that the relative error of the improved PRDQN algorithm is between 0℃and 5℃,and the temperature control effect is relatively good.Therefore,the proposed method is effective and feasible.

关 键 词：陶瓷梭式窑 深度强化学习 BP神经网络 PRDQN算法 

分 类 号：TQ174.653[化学工程—陶瓷工业]