Neural Output Feedback Control of Automobile Steer-by-Wire System With Predefined Performance and Composite Learning

This article addresses the steering control problem for steer-by-wire (SbW) systems subject to the unknown uncertainty, external disturbance and unavailable variable. Before the controller design, an adaptive neural network-based observer and a disturbance observer are constructed to estimate the angular velocity signal and the compound disturbance, respectively. Then, to guarantee the transient and steady-state performance of steering tracking error within the quantitative boundary, a prescribed performance function is constructed by user-designed tracking accuracy and settling time. Finally, the controller is designed based on the backstepping scheme and the neural network with a composite learning scheme is proposed for the approximation of lumped uncertainty. The Lyapunov stability theory shows that the signals involved in the system are semi-global uniformly ultimately bounded and the tracking error converges to a preset range at finite time. Different numerical simulations and experiments are implemented to verify the effectiveness of the developed control scheme.

Automated summary

This article addresses the steering control problem for steer-by-wire (SbW) systems subject to uncertainties, disturbances, and unavailable variables. An adaptive neural network-based observer and a disturbance observer are constructed to estimate the angular velocity signal and the compound disturbance. The controller is designed based on the backstepping scheme and a composite learning scheme for uncertainty approximation using neural networks. The Lyapunov stability theory shows the bounded signals and convergence of the tracking error within a preset range.