Hybrid adaptive learning neural network control for steer-by-wire systems via sigmoid tracking differentiator and disturbance observer

Abstract

Steer-by-Wire (SbW) systems are usually affected negatively by the friction torque and self-aligning torque. This paper proposes a hybrid learning neural network controller to achieve precise control for the SbW system. Firstly, a sigmoid tracking differentiator (STD) is introduced to obtain the velocity signal with the angle measurement only. Secondly, by combining the model-free technology, the neural network is applied to overcome the lumped uncertainty including the friction torque and self-aligning torque. Different from the related literature, a second-order identification model is designed to construct the learning law so that the neural network can be adjusted by the tracking error and modeling error simultaneously. Finally, a disturbance observer is proposed for the compensation of compound disturbance including the external disturbance and neural network approximated error. The advantages are that the proposed control scheme not only ensures good tracking performance using the least sensors but also can handle uncertainty and attenuate measurement noise. Lyapunov stability theory proves that the tracking error is uniformly ultimately bounded. Numerical simulations and experiments show the effectiveness and superiorities of the proposed control method.