Identification of Hybrid Systems by Fuzzy C-Regression Clustering

This paper introduces a method for identifying hybrid systems using fuzzy C-regression clustering. A distinctive aspect of this approach is the use of hyperplanes as cluster prototypes in the input space, with shared parameters between the antecedent and consequent parts. The algorithm features a small number of design parameters, making it easy to implement and tune. The effectiveness of the proposed method is demonstrated on three simulated examples.