Identification of Nonlinear System Based on ANFIS with Subtractive Clustering
Junhong Yue, Jizhen Liu, Xiangjie Liu, Wen Tan · 2006
Subtractive clustering is used to generate an initial T-S fuzzy model with the appropriate rule number and performance index by adjusting the radius of a cluster center. To acquire a T-S fuzzy model with perfect performance, Adaptive nuero-fuzzy inference system (ANFIS) is combined to fine tune the premise parameters and consequent parameters by means of a hybrid gradient descent (GD) and least-squares estimation (LSE). A simulation to a dynamic nonlinear system demonstrates the effective of this method.