Application of Takagi–Sugeno fuzzy model optimized with an improved Free Search algorithm to industrial polypropylene melt index prediction

Abstract

A new algorithm is presented for learning the Takagi–Sugeno (T-S) fuzzy model from data by improved Free Search algorithm (IFS), where the rule structure (selection of rules and number of rules), input structure (selection of inputs and number of inputs) and parameters of the T-S fuzzy model are all represented as individuals of the IFS and evolved together such that the optimization of the rule structure, the input structure and the parameters can be achieved simultaneously. The developed IFS-T-S model is used for the prediction of melt index in an industrial propylene polymerization process and the results show that the proposed IFS-T-S model has a good fitting and prediction ability.