Title: Hybrid NN predictive-based LQR controller for rotary double inverted pendulum systems: an analytical study

Authors: Viroch Sukontanakarn; Manukid Parnichkun

Addresses: Faculty of Mechatronics, School of Engineering and Technology, Asian Institute of Technology, Pathumthani 12120, Thailand ' Faculty of Mechatronics, School of Engineering and Technology, Asian Institute of Technology, Pathumthani 12120, Thailand

Abstract: This paper introduces a rotary double inverted pendulum (RDIP) systems. The model is derived by using Euler–Lagrange. Linear quadratic regulator (LQR) controller is applied as the main controller to stabilise the rotary double. However, LQR alone cannot control RDIP efficiently because the plant derived in linear model is not exact model of the real plant. Practically, controller design aiming to guarantee robustness has to consider these uncertainties. In this paper, neural network predictive control is proposed to improve control performance of the conventional LQR controller. Results on control techniques from computer simulation are evaluated and compared.

Keywords: LQR; linear quadratic regulator; RDIP; rotary double inverted pendulum; NNPC; neural network predictive control; neural networks; controller design; simulation.

DOI: 10.1504/IJAAC.2011.043611

International Journal of Automation and Control, 2011 Vol.5 No.4, pp.337 - 355

Received: 28 May 2011
Accepted: 13 Aug 2011
Published online: 17 Apr 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article