Neural network-based command filtered control for induction motors with input saturation

In this study, neural networks approximation-based command filtered adaptive control is studied for induction motors with input saturation. The neural networks are utilised to approximate the non-linearities, and the command filtering technology is used to deal with the 'explosion of complexity' problem caused by the derivative of virtual controllers in the conventional backstepping design. The compensating signals are further exploited to get rid of the drawback caused by the dynamics surface technology. It is verified that the adaptive neural controller guarantees that the tracking error can converge to a small neighbourhood of the origin. At last, the effectiveness and advantages of the proposed method are intuitively illustrated by simulation results.