A single layer fast learning fuzzy controller/filter
M.E. Ulug · 2002
This paper describes an orthonormal neural network (ONN) designed to function as a fuzzy controller/filter. This single layer network is tested in simulating a third order function with two input variables. The simulation results are described. In this application ONN used one output and two input nodes, Each input node is connected to seven /spl pi/ functions to perform fuzzification resulting in 7/sup 2/=49 fuzzy rules. The conclusions of these rules are the system output and they are given in numerical form. As a result of using a new fast learning algorithm, the training process requires only 100 cycles. The fuzzy controller with the help of some switching can function as a bandpass and/or in-band filter.>