Implementing Adaptive Fuzzy Logic Controllers with Neural Networks: A Design Paradigm

TLDR: This dissertation presents an efficient approach that combines fuzzy logic and neural networks to capture these two important features required for an intelligent control system and indicates that fuzzy logicand neural networks are complementary and their combination is ideal to achieve the goal of intelligent control.

Abstract: This article proposes a design of adaptive fuzzy logic based control systems FLCSs with neural networks. A detailed discussion of effects of different reasoning methods on fuzzy controls is given and used to illustrate the need for an adaptive implementation of fuzzy controls. The procedure of decision-making of a FLCS leads to a neuro-fuzzy network consisting of three types of subnets for pattern recognition, fuzzy reasoning, and control synthesis, respectively. The unique knowledge structure embedded in this structured network enables it to carry out adaptive changes of fuzzy reasoning methods and membership functions for both input signal patterns and output control actions, and then recover these changes individually and completely later from its sub nets. Gradient methods for optimization have been used to derive off-line training rules and on-line learning algorithms for the structured neuro-fuzzy network. Issues related to rule modification and generation for an FLCS are addressed based on its network implementation.