Fuzzy modeling for complex processes

A complex process which is difficult to be mathematically expressed can be described by a set of fuzzy inference rules, and fuzzy modeling has been regarded as one of the key problems in fuzzy systems research. A quick and accurate fuzzy modeling method is presented in accordance with the characteristics of SISO systems. That is, the domain of discourse of the input variable is divided firstly according to the changing degree of the process output while the input variable changes, and based on the above, dividing the total number and the premise parameters of the fuzzy rules can be determined, then because the presented fuzzy model can be expressed as a fuzzy neural network which is a feedforward neural network, so the BP algorithm is applied to obtain the consequent parameters of the fuzzy rules. The effectiveness of the presented fuzzy modeling method and the generalization ability of the fuzzy rules model are demonstrated by a simulation example.