Adaptive Network-Based Fuzzy Inference System (ANFIS) Controller for an Active Magnetic Bearing System with Unbalance Mass

Abstract

Active magnetic bearing (AMB) system supports a rotating shaft, without any physical contact by using electromagnetic forces. This paper proposes an intelligent control method for displacements of the air gap between the stator and the rotor in an Active Magnetic Bearing (AMB) system, using the emerging approaches of the Fuzzy Logic Controller (FLC) and Adaptive Neuro-Fuzzy Inference System (ANFIS). The AMB systems are inherently unstable and the relationship between the current and electromagnetic force is nonlinear. In this paper, the control model uses Takagi-Sugeno fuzzy logic, in which the back-propagation algorithm processes information from neural networks to adjust suitably the parameters of the fuzzy controller. This method can be applied to improve the control performance of nonlinear systems. This controller also satisfies the requirements of real-time response and stability under disturbances of system. The ANFIS controller can be feasibly applied to AMB systems with unbalance mass disturbances.