The master's thesis of the student (Taha Shaker Mahmoud) with a major in (Mechatronics Engineering) was discussed on Tuesday 11/10/2022 at the discussion room (Hall No. 9) in the Department of Control and Systems Engineering. The thesis title is “An Intelligent Controller Design Based on Feedback linearization Using NARMA-L2 for Nonlinear Systems”

The discussion committee consisted of:

1-Prof. Dr. Ahmed Ibrahim Abdel Karim / Chairman Asst.

2-Prof. Dr. Wajdi Sadiq Abboud / Member Asst.

3-Prof. Dr. Bushra Kadhum Aliwi / Member

4-Prof. Dr. Omar Farouq Lutfy / Member and Supervisor

Feedback linearization provides applicable design tools for a wide variety of nonlinear systems. This thesis presents an intelligent feedback controller based on the feedback linearization approach to control nonlinear systems. In particular, the nonlinear autoregressive moving average (NARMA-L2) network is trained to reproduce the forward dynamics of the controlled system. Thus, the trained NARMA-L2 network can be immediately integrated into the inverse feedback control (IFC) structure. In order to improve the ability of the NARMA-L2 architecture to approximate nonlinear systems, the NARMA-L2 controller consists of two wavelet neural networks (WNNs). In addition, the RASP1 function was used as the wavelet mother function in the WNN architecture, where this function led to the best control accuracy compared to the more commonly used Mexican Hat, Gaussian, and Morlet functions. To avoid the limitations of the gradient descent (GD) methods, the artificial gorilla force optimization (GTO) algorithm is used to determine the optimal settings for the NARMA-L2 inverse control parameters. In particular, several evaluation tests are used to evaluate the efficacy of WNN-based NARMA-L2 in control accuracy and robustness against external disturbances in each system under study. These tests clearly demonstrated the effectiveness of the control system. Finally, a comparative study showed that the WNN-based NARMA-L2 controller achieved better control results compared to the Multilayer Perceptron (MLP), the NARMA-L2-based RBF, and the PID Controller. The discussion was attended by the Assistant Head of the Department for Administrative Affairs (Prof. Dr. Hazem Ibrahim Ali) and the Assistant Head of the Department for Scientific Affairs and Postgraduate Studies (Prof. Dr. Muhammad Youssef Hassan). On this occasion, we congratulate the student (Taha Shaker Mahmoud) and wish him continued success.