Nonlinear System Control Using A Recurrent Neural Fuzzy Network Based on Reinforcement Particle Swarm Optimization

摘要：

This paper proposes a recurrent neural fuzzy network with the reinforcement improved particle swarm optimization (R-IPSO) for solving various control problems. The R-IPSO, which consists of structure learning and parameter learning, is also proposed. The structure learning is adopts several sub-swarms to constitute variable fuzzy systems and uses an elite-based structure strategy (ESS) to find suitable the number of fuzzy rules for solving a problem. The parameter learning is adopts an improved particle swarm optimization (IPSO). The examples have been given to illustrate the performance and effectiveness.

关键词： Neural fuzzy network particle swarm optimization recurrent network elite-based structure strategy reinforcement learning control.

作者: Cheng-Jian Lin Ying-Ming Lin Chi-Yung Lee

作者单位: Dept. of CSIE, National Chin-Yi University of Technology Taichung Country 411, Taiwan,R.O.C. Dept. of CSIE, NanKai University of Technology Nantou County 542, Taiwan,R.O.C.

会议类型: 国际会议

会议名称: 2010 International Symposium on Computational Intelligence and Edsign(第三届计算智能与设计国际学术研讨会 ISCID 2010)

会议地点: 杭州

会议语种:英文

页码: 196-200

在线出版日期: 2010-10-29（万方平台首次上网日期，不代表论文的发表时间）