Self-Organizing Adaptive Fuzzy Brain Emotional Learning Control for Nonlinear Systems.

• Main Authors: Ravitej Rama rao, 單杰
• Other Authors: Chih-Min Lin
• Format: Others
• Language: en_US
• Published: 2017
• Online Access: http://ndltd.ncl.edu.tw/handle/3k94t7

碩士 === 元智大學 === 電機工程學系 === 105 === This study develops a new self-organizing adaptive control system with a fuzzy brain emotional learning controller (FBELC). The FBELC neural network is the mathematical replica of human brain emotions incorporated with fuzzy inference rules, which mimics the judgments and emotions of the brain. The FBELC contains two sub-neural networks, namely a sensory neural network and an emotional neural network. These duet networks influence each other, thus improving the learning ability of the system. The proposed control system also merges sliding mode control to simplify the input space dimension of FBELC. In this study, the structure of FBELC can be self-organized; thus the growing and pruning of input layers of FBELC can be automatically proceeded to give the most efficient network structure. Moreover, the new parameter adaptive law is derived using gradient descent method to achieve effective learning ability of the network. The proposed control system comprises the self-organizing adaptive FBELC (SOAFC) used as the main controller and a robust compensator designed to obtain robust stability of the system for handling nonlinear systems. The developed SOAFC is then applied to a double inverted pendulum system, a chaotic system and a biped robot system to illustrate its effectiveness.