A systematic method for fuzzy modeling from numerical data

A systematic fuzzy modeling method that includes the initial fuzzy model self-generation, significant input selection, partition validation, parameter optimisation and rule-base simplification is proposed. In this framework, the whole procedure of structure identification and parameter optimisation is carried out automatically and efficiently by the combined use of a self-organisation network, fuzzy clustering, adaptive back-propagation learning and similarity analysis. The proposed fuzzy modeling approach has been used for nonlinear system identification and mechanical property prediction in hot rolled steel. Experimental studies demonstrate that the proposed fuzzy models have a good balance between model accuracy and interpretability