Application of Fuzzy Wavelet Neural Network to Adaptive Control of Nonlinear Systems
In this paper an application of fuzzy wavelet neural network (FWNN) to control problem of nonlinear systems is investigated.FWNN is applied to approximate unknown dynamic of system.Each fuzzy rule corresponds to one sub-wavelet neural network (subWNN) and one adaptation parameter.Each sub-WNN consists of wavelets with a specified dilation value.Learning of FWNN is performed by two algorithms,extended Kalman filter and recursive least square estimator.Then based on Lyapunov synthesis an on-line adaptive tuning algorithm is designed to adjust the adaptation parameters in the consequent part of fuzzy rules.Proposed scheme can approximate feedback linearization control input so that the closed loop system be stable and achieve a good tracking performance with proper transient response.The capability of the proposed method is illustrated through one numerical example.
fuzzy wavelet neural network adaptive fuzzy control nonlinear systems
Maryam Shahriari-Kahkeshi Maryam Zekri Farid Sheikholeslam
Dep.of Electrical Engineering,Isfahan University of Technology Isfahan,Iran
国际会议
秦皇岛
英文
52-55
2010-11-05(万方平台首次上网日期,不代表论文的发表时间)