Citation

Beloufa, Azeddine and Tahraoui, Souaad and Kacimi, Abderrahmane and Allouache, Hadje and Tiang, Jun Jiat and Azzouz, Abdelbasset and Zaid, Mehdi Houari (2026) Robust Backstepping Control of a Twin Rotor MIMO System via an RBF-Tuned High-Gain Observer. Automation, 7 (2). p. 40. ISSN 2673-4052

Text automation-07-00040.pdf - Published Version Restricted to Repository staff only Download (7MB)

Abstract

The design of robust controllers for complex nonlinear systems remains a formidable challenge, particularly concerning the disparity between simulation performance and real-world implementation constraints. This research investigates the practical implementation of a backstepping controller integrated with a High-Gain Observer (HGO) on a Twin Rotor MIMO System (TRMS). While the control architecture exhibited stability and precise tracking in simulation, physical deployment initially failed due to sensitivity to measurement noise and the peaking phenomenon, resulting in a divergent response with a Yaw RMSE of 2.56 rad. Unlike conventional approaches that attempt to bridge the simulation-to-reality gap by optimizing the controller, we hypothesized that the critical bottleneck lay within the observer dynamics. To address this, a Radial Basis Function (RBF) Neural Network was employed to adaptively tune the observer gains in real time. Experimental results demonstrate that this adaptive mechanism successfully mitigated the effects of unmodeled dynamics and noise, reducing the Root Mean Square Error (RMSE) by over 85% in the pitch axis and 95% in the yaw axis. These findings substantiate that online adaptive observer tuning is a decisive strategy for ensuring the reliability of advanced nonlinear controllers on physical hardware.

Item Type:	Article
Uncontrolled Keywords:	RBF neural network, Twin Rotor MIMO System (TRMS)
Subjects:	T Technology > TK Electrical engineering. Electronics Nuclear engineering > TK5101-6720 Telecommunication. Including telegraphy, telephone, radio, radar, television
Divisions:	Faculty of Artificial Intelligence & Engineering (FAIE)
Depositing User:	Ms Rosnani Abd Wahab
Date Deposited:	05 Jun 2026 07:05
Last Modified:	05 Jun 2026 07:05
URII:	http://shdl.mmu.edu.my/id/eprint/16050

Downloads

Edit (login required)