基于RBF-Q学习的多品种CSPS系统前视距离控制
首发时间:2018-01-03
摘要:研究一类多品种工件到达的传送带给料加工站(CSPS)系统的前视距离(Look-ahead)优化控制问题.在工件品种数增加的情况下,系统状态规模会呈现指数性增长,考虑传统Q学习面对大规模离散状态所面临的维数灾难,且难以直接处理前视距离为连续化变量的问题,论文引入RBF网络逼近Q值函数.RBF网络的输入为状态行动对,输出为该状态行动对的Q值.仿真结果表明,RBR-Q学习算法可以对CSPS系统性能进行有效地优化,并且提高学习速度.
For information in English, please click here
Look-ahead control of multi-type products CSPS system based on RBF-Q learning
Abstract:This paper is concerned with the look-ahead optimal control problem of the conveyor-serviced production station (CSPS) system for a class of varieties of parts arrival. When the number of varieties of system is increased, the system state scale will show exponential growth, considering the dimension disaster problem of traditional Q-learning in the face of the large-scale discrete state and will be difficult to deal with the problem that the look-ahead is a continuous variable, the RBF network is introduced to approximate the Q value function. The input of the RBF network is the state action pair, and the output is the Q value of the state action pair. The simulation results show that the method can effectively optimize the processing of CSPS system and improve the learning speed.
Keywords: Conveyor-serviced production station (CSPS);RBF network Q-learning Multi-Type products
基金:
引用
No.****
同行评议
共计0人参与
勘误表
基于RBF-Q学习的多品种CSPS系统前视距离控制
评论
全部评论0/1000