Adaptive extreme learning machine-based event-triggered control for perturbed Euler-Lagrange systems

doi:10.1002/rnc.6377

Adaptive extreme learning machine-based event-triggered control for perturbed Euler-Lagrange systems

2022-09-26

1

PRE

AI

DOI：10.1002/rnc.6377

Original request for help

Save

Abstract

En 中文

The problem of event-triggered finite-time trajectory tracking control of perturbed Euler-Lagrange systems with nonlinear dynamics and disturbances is addressed in this article. Extreme learning machine (ELM) framework is employed to formulate unknown nonlinearities, and adaptive technique is adopted to adjust output weights of the ELM networks and remedy the negative impacts of disturbances, nonlinearities, and residual errors. Then to ensure the system follows the desired position trajectory within a finite-time, an adaptive ELM-based sliding mode control strategy is developed. Moreover, event-triggered control technique is proposed to regulate control outputs on the basis of the developed control strategy for reducing actuator actions and saving communication resources. Lyapunov stability theorem is utilized to confirm bounded trajectory tracking results and finite-time convergence of the Euler-Lagrange system. Finally, the effectiveness of the developed adaptive ELM-based event-triggered sliding-mode control strategies is substantiated by simulations in a robotic manipulator system.

Keywords:

adaptive ELM-based control

Euler-Lagrange systems

event-triggered control

finite-time trajectory tracking

sliding mode control

Adaptive extreme learning machine-based event-triggered control for perturbed Euler-Lagrange systems

Abstract

Journal

Organization