Cell state space algorithm and neural network based fuzzy logic controller design

The authors present a method for automatic design of a fuzzy logic controller (FLC). The main problems of designing an FLC are how to optimally and automatically select the control rules and the parameters of the membership function (MF). Cell state space algorithms (CSS), differential competitive learning (DCL), and multilayer neural networks are combined to solve these problems. When the dynamical model of a control process is known, CSS can be used to generate a group of optimal input-output pairs (X,Y) used by a controller. The (X,Y) pairs then can be used to determine the FLC rules by DCL to find the optimal parameters of the MF, using a multilayer neural network trained by a backpropagation algorithm.<>