文章基本信息

标题：ADAPTIVE INTELLIGENT INVERSE CONTROL OF NONLINEAR SYSTEMS WITH REGARD TO SENSOR NOISE AND PARAMETER UNCERTAINTY (MAGNETIC BALL LEVITATION SYSTEM CASE STUDY)
本地全文：下载
作者：Yaghoub Pour Asad ; Afshar Shamsi ; Hoda Ivani 等
期刊名称：International Journal on Smart Sensing and Intelligent Systems
印刷版ISSN：1178-5608
出版年度：2016
卷号：9
期号：1
页码：148-168
出版社：Massey University
摘要：Type-2 Fuzzy Neural Networks have tremendous capability in identification and control ofnonlinear, time-varying and uncertain systems. In this paper the procedure of designing inverseadaptive type-2 fuzzy neural controller for online control of nonlinear dynamical systems will bepresented. At first the structure of a novel class of Interval Type-2 Nonlinear Takagi-Sugeno-KengFuzzy Neural Networks (IT2-NTSK-FNN) will be presented. There is a class of nonlinear functionof inputs in the consequent part of fuzzy rules. This IT2-NTSK-FNN comprises seven layers and thefuzzification is done in two first layers including type-2 fuzzy neurons with uncertainties in themean of Gaussian membership functions. Third layer is rule layer and model reduction occurs infourth layer via adaptive nodes. Fifth, sixth and seventh layers are consequent layer, centroid rules'calculation layer and output layer respectively. For training the network backpropagation (steepestdescend) method with adaptive training rate is used. Finally, three methods including onlineadaptive inverse controller based on IT2-NTSK-FNN, IT2-TSK-FNN (linear consequent part) andAdaptive Neuro-Fuzzy Inference System (ANFIS) are employed to control of a magnetic balllevitation system. External disturbances and uncertainty in parameters are considered in the modelof magnetic ball levitation system. Simulation results show the efficacy of the proposed method.
关键词：Nonlinear Type-2 Fuzzy; Adaptive Inverse control; Magnetic ball levitation System