Supervisory enhanced genetic algorithm controller design and its application to decoupling induction motor drive

An alternative control scheme including an enhanced genetic algorithm controller (EGAC) and a supervisory controller is developed for nonlinear dynamical systems in this study. In the EGAC design, the spirit of gradient descent training is embedded in genetic algorithm (GA) to construct a main controller to search the optimum control effort under the possible occurrence of uncertainties. To ensure the system states around a defined bound region, a supervisory controller, which is derived in the sense of Lyapunov stability theorem, is added to adjust the control effort. Compared with enunciated GA control methods, the proposed control scheme possesses some salient advantages of simple framework, less executing time and good self-organising properties even for the time-varying system because the simple solution representation and the error backpropagation genetic operation are utilised in the GA process. In addition, the proposed scheme is applied to the position control of a decoupling induction motor (IM) drive, whose effectiveness is verified by the numerical simulation and experimental results and whose advantages are presented in comparison with existing position control schemes.