Fuzzy neuro-computational technique and its application to modelling and control

Abstract

The authors present a model building technique which combines the strength of fuzzy set theory and neural network based structures. This technique can simultaneously deal with two types of knowledge, nonfuzzy knowledge and fuzzy, which usually describe the behavior of complex processes. The proposed method can also be directly applied to the construction of a new type of intelligent fuzzy controller. Some considerations relating to the adequacy of this fuzzy neuro-computational model are also discussed.<>