Adaptive nonlinear disturbance observer using double loop self-organizing recurrent wavelet-neural-network for two-axis motion control system

This paper proposes an adaptive nonlinear disturbance observer (ANDO) for identification and control of a two-axis motion control system driven by two permanent-magnet linear synchronous motors (PMLSMs) servo drives. The proposed control scheme incorporates a feedback linearization controller (FLC), a new double loop self-organizing recurrent wavelet neural network (DLSORWNN) controller, a robust controller and an _∞ controller. First, a FLC is designed to stabilize the X-Y table system. Then, a NDO is designed to estimate the nonlinear lumped parameters uncertainties that include the external disturbances, cross-coupled interference and frictional force. However, the X-Y table performance is degraded by the NDO error due to parameter uncertainties. To improve the robustness, the ANDO is designed to attain this purpose. In addition, the robust controller is designed to recover the approximation error of the DLSORWNN while the _∞ controller is specified such that the quadratic cost function is minimized and the worst case effect of NDO error must be attenuated below a desired attenuation level. The online adaptive control laws are derived using the Lyapunov stability analysis and _∞ control theory, so that the stability of the ANDO can be guaranteed. The experimental results show the improvements in disturbance suppression and parameter uncertainties, which illustrate the superiority of the ANDO control scheme.