Adaptive Recurrent Wavelet Network Uncertainty Observer Based on Integral Backstepping Control for a SynRM Drive System

The synchronous reluctance motor (SynRM) received much attention for many applications due to its simple construction. The control performance of a SynRM drive system is highly affected by nonlinear uncertainties, such as parameter variations, external load disturbance, magnetic saturation, high iron losses and friction force etc. The accurate mathematic models are difficult to be established for time-varying and nonlinear uncertainties of the actual SynRM drive system. In this paper an adaptive recurrent wavelet neural network (ARWNN) uncertainty observer based on integral backstepping control system is proposed to achieve the required high-control performance and robust to the uncertainties. Firstly, the field-oriented mechanism is applied to formulate the dynamic equation of the SynRM drive system. Secondly, an integral backstepping approach is proposed to control the motion of SynRM drive system. With proposed integral backstepping control system, the rotor position of the SynRM drive possesses the advantages of good control performance and robustness to uncertainties for the tracking of periodic reference trajectories. Moreover, to further increase the robustness of the SynRM drive system for nonlinear uncertainties, an adaptive RWNN uncertainty observer is proposed to estimate the required lumped uncertainty. The on-line adaptive rule of the RWNN is derived in accordance with Lyapunov function. The updated parameters of the RWNN are used by the gradient descent method and the backpropagation algorithm. Finally, the effectiveness of the proposed control scheme is verified by some experimental results. Copyright (C) 2012 Praise Worthy Prize S.r.l. - All rights reserved.