Research of Fuzzy Neural Network Control Algorithm Based On Inverted Pendulum Authentication System

摘要：

This paper adopts the fuzzy neural network,variable fusion matrix and the self-organization feature map network to research fuzzy neural network control method with double inverted pendulum system. Firstly,the mathematical model of double inverted pendulum system is built;Secondly,fuzzy neural network model is constructed and the training algorithm is described;Thirdly,getting the input variables fusion matrix and simplifying training sample;Then,polymerizing the fuzzy classification number of input variables by self-organization feature map network;Finally,the simulation control analysis of double inverted pendulum based on the optimized fuzzy neural network is given. The results show that fuzzy neural network control method based on variable fusion and the self-organization feature map network not only simplifies the structure and improves the control efficiency,so it verifies the feasibility and effectiveness of the proposed control method.

关键词： Double inverted pendulum Fuzzy neural network Variable fusion Self-organization feature map network

作者: Zeng Xiangqiang Zhu Xiaojin Jiang Enyu Sun Wei

作者单位: School of Mechatronics Engineering and Automation,Shanghai University Shanghai,200072,China

会议类型: 国际会议

会议名称: 2011 International Conference on Opto-Electronics Engineering and Information Science(2011光电电子工程与信息科学国际会议 ICOEIS 2011)

会议地点: 西安

会议语种:英文

页码: 2054-2058

在线出版日期: 2011-12-23（万方平台首次上网日期，不代表论文的发表时间）