Fuzzy Inference System Approach Using Clustering and Differential Evolution Optimization Applied to Identification of a Twin Rotor System

摘要

In this paper, a Takagi-Sugeno-Kang (TSK) fuzzy inference system using fuzzy c-means clustering and differential evolution optimization is proposed and validated when applied to a twin rotor system (TRS). The TRS is perceived as a challenging problem due to its strong cross coupling between horizontal and vertical axes. The design procedure of the TSK fuzzy approach for TRS is detailed. According to the identification results obtained by applying the TSK fuzzy approach and a nonlinear autoregressive with moving average and exogenous inputs (NARMAX) model, the effectiveness of the proposed fuzzy system design is demonstrated through validation tests.