Neural Network-Based High-Accuracy Motion Control of a Class of Torque-Controlled Motor Servo Systems with Input Saturation

Abstract

The torque-controlled motor servo system is widely used in many industrial applications. However, input saturation often occurs due to the limitation of the actuator output ability, which may worsen the system control performance. In this paper, in order to inhibit the impact of input saturation on the system, a single-hidden-layer neural network based observer is designed to estimate the value of input saturation, which could later be compensated in the proposed controller. In addition, an adaptive law is introduced to estimate the unknown parameters, and a nonlinear robust term is designed to overcome the time-varying disturbances and other compensation errors. The Lyapunov theorem is used to prove the stability of the proposed controller with the neural network-based observer. Extensive comparative experimental results are obtained to verify the high-performance of the proposed control strategy.