Self-tuning control of electrical machines using gradient descent optimization

This paper presents a new approach toward the design of a self-tuning proportional-integral (PI) control for induction motors. By using the method of gradient descent optimization to the parameter space, the controller gains developed in this study are adjusted automatically online. Therefore, the proposed PI control is robust to the changes of induction motor parameters and achieves the performance of global asymptotic speed tracking. Theoretical analysis and simulation results are presented to show the effectiveness of the approach.