Sliding mode control with a neural network compensation scheme for electro-hydraulic systems

TL;DR

This paper proposes a sliding mode control approach enhanced with neural network compensation to effectively manage the nonlinearities and dead-zone effects in electro-hydraulic systems, ensuring stable and precise control.

Contribution

It introduces a novel control scheme combining sliding mode control with neural network compensation specifically for electro-hydraulic systems with unknown dead-zone nonlinearities.

Findings

Proven stability and convergence of the control system using Lyapunov theory.

Numerical simulations demonstrate improved control performance.

Effective handling of dead-zone nonlinearities in electro-hydraulic systems.

Abstract

Electro-hydraulic servo-systems are widely employed in industrial applications such as robotic manipulators, active suspensions, precision machine tools and aerospace systems. They provide many advantages over electric motors, including high force to weight ratio, fast response time and compact size. However, precise control of electro-hydraulic systems, due to their inherent nonlinear characteristics, cannot be easily obtained with conventional linear controllers. Most flow control valves can also exhibit some hard nonlinearities such as dead-zone due to valve spool overlap. This work describes the development of a sliding mode controller with a neural network compensation scheme for electro-hydraulic systems subject to an unknown dead-zone input. The boundedness and convergence properties of the closed-loop signals are proven using Lyapunov stability theory. Numerical results are presented in order to demonstrate the control system performance.