In this paper, an intelligent adaptive dynamic surface control system (IADSCS) with recurrent wavelet Elman neural network (RWENN) for induction motor (IM) servo drive is proposed. The IADSCS comprises a dynamic surface controller (DSC), a recurrent wavelet Elman neural network (RWENN) uncertainty observer and a robust controller. First, a computed torque controller (CTC) is designed to stabilize the IM servo drive. Then, a nonlinear disturbance observer (NDO) is designed to estimate the nonlinear lumped parameter uncertainties existed in the CTC law. However, the IM servo drive performance is degraded by the NDO error due to the parameter uncertainties. To improve the robustness of the IM servo drive due to external load disturbances and parameter uncertainties, an IADSCS is designed to achieve this purpose. In the IADSCS, the DSC is used to overcome the explosion of the complexity in the backstepping design technique and the RWENN identifier is used to approximate the lumped parameter uncertainties and compounded disturbances. In addition, the robust controller is designed to recover the approximation error of the RWENN. The stability of the closed-loop system is guaranteed by the Lyapunov stability theory. All control algorithms are implemented using dSPACE1104 DSP-based control computer. The simulation and experimental results show the superiority of the proposed IADSCS in external load disturbance suppression and the robustness against parameter uncertainties.
Computed torque control, dynamic surface control, IM drive, Lyapunov stability, recurrent wavelet Elman neural network, nonlinear disturbance observer, uncertainties.
Fayez F. M. El-Sousy and Khaled A. Abuhasel, “Intelligent Adaptive Dynamic Surface Control System with Recurrent Wavelet Elman Neural Networks for DSP-Based Induction Motor Servo Drives,” Accepted in the IEEE Transactions on Industry Application, vol. 55, no. 2, pp. xx - xx, March./April 2019.
تم النشر في: 2018-10-18 00:58:57
This paper proposes a robust adaptive dynamic surface control system (RADSCS) using recurrent cerebellar model articulation controller-based function link neural network (RCMACFLNN) for uncertain two-axis motion control system driven by two permanent-magnet synchronous motors (PMSMs) servo drives. The proposed control scheme incorporates a dynamic surface controller (DSC), a RCMACFLNN uncertainty observer and a robust controller. First, an optimal computed torque controller (OCTC) is deigned to stabilize the two-axis motion control system. In addition, the OCTC is utilized to approximate the CTC law and minimizes a quadratic performance index based on the Hamilton-Jacobi-Bellman (HJB) optimization scheme. However, the control performance may be destroyed due to parameter uncertainties exist in the OCTC law for the reason that the linear optimal control has an inherent robustness against a certain range of model uncertainties. Therefore, a RADSCS is designed to improve the robustness of the control system. In the RADSCS, the DSC is used to overcome the explosion of the complexity in the backstepping design. As well, the RCMACFLNN uncertainty observer is designed to adaptively estimate the nonlinear parameter uncertainty terms online, whereas the robust controller is designed to recover the residual of the approximation error of the RCMACFLNN. The online adaptive control laws are derived using the Lyapunov stability analysis. From the experimental results, the motions at X-axis and Y-axis are controlled separately and the dynamic behaviors of the proposed RADSCS can achieve robust tracking performance against parameter uncertainties.
تم النشر في: 2018-10-14 14:22:24
محتويات مواقع أعضاء هيئة التدريس بما فيها من نصوص وملفات وصور وأبحاث وأية مواد أخرى هي مسئولية عضو هيئة التدريس بالكامل بصفته صاحب الموقع وبما له من صلاحية مطلقة في الإضافة والحذف، وتخلي الجامعة مسئوليتها عن محتويات تلك المواقع.
جميع الحقوق محفوظة © عمادة تقنية المعلومات والتعليم عن بعد 2018م ــ 1440هـ.