An Adaptive NN Controller with Second Order SMC-Based NN Weight Update Law for Asymptotic Tracking

  • Authors:
  • Haris Psillakis

  • Affiliations:
  • Department of Electronic & Computer Engineering, Technical University of Crete, Chania, Greece 73100

  • Venue:
  • ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
  • Year:
  • 2009

Quantified Score

Hi-index 0.01

Visualization

Abstract

The asymptotic tracking control problem of a class of single-input single-output (SISO) uncertain nonlinear systems is addressed in this paper. A single-hidden layer neural network is used as a controller with a novel online weight training algorithm. The proposed NN weight update law mimics standard second order sliding mode control (2-SMC) approaches to ensure semi-global asymptotic convergence of the tracking error to the origin with continuous control effort. A simulation study verifies the effectiveness of the NN controller with 2-SMC-based online training.