ARFNNs under Different Types SVR for Identification of Nonlinear Magneto-Rheological Damper Systems with Outliers

作者：Chen Pi Yun; Fu Yu Yi; Su Kuo Lan; Jeng Jin Tsong^*

来源：International Journal of Fuzzy Systems, 2010, 12(4): 311-320.

• Magneto-rheological damper
• Fuzzy neural networks
• Support vector regression
• Annealing robust learning algorithm

This paper demonstrates different types support vector regression (SVR) for annealing robust fuzzy neural networks (ARFNNs) to identification of nonlinear magneto-rheological (MR) damper with outliers. A SVR has the good performances to determine the number of rule in the simplified fuzzy inference system and initial weights for the fuzzy neural networks. In this paper, we independently proposed two different types SVR for the ARFNNs. Hence, a combination model that fuses simplified fuzzy inference system, SVR and radial basis function networks is used. Based on these initial structures, and then annealing robust learning algorithm (ARLA) can be used effectively to adjust the parameters of structures. Simulation results show the superiority of the proposed method with the different types SVR for the nonlinear MR damper systems with outliers.

• 出版日期2010-12
• 单位南开大学