Application of a recurrent wavelet fuzzy-neural network in the positioning control of a magnetic-bearing mechanism

Abstract

A new recurrent wavelet fuzzy neural network (RWFNN) with adaptive learning rates is proposed to control the rotor position on the axial direction of a thrust magnetic bearing (TMB) mechanism in this study. First, the dynamic analysis of the TMB with differential driving mode (DDM) is derived. Because the dynamic characteristics and system parameters of the TMB mechanism are high nonlinear and time-varying, the RWFNN, which integrates wavelet transforms with fuzzy rules, is proposed to achieve precise positioning control of the TMB. For the designed RWFNN controller, the online learning algorithm is derived using back-propagation method. Moreover, since the improper selection of learning rates for the RWFNN will deteriorate the control performance, an improved particle swarm optimization (IPSO) is adopted to adapt the learning rates of the RWFNN on-line. Numerical simulations show the validity of TMB system using the proposed RWFNN controller with IPSO under the occurrence of uncertainties.