A neural multicontroller for strongly nonlinear systems

Abstract

The application of neural networks can present some limitations for the control of strongly nonlinear systems. In this paper, a new control scheme based on a neural multicontroller (NMC) is proposed. Indeed, the developed strategy considers a set of local neural controllers which adapt their parameters thanks to an online adaptation algorithm. The instantaneous choice of the adequate local controller is based on a switching mechanism. The advantages of the proposed method are (1) to avoid the computational complexity issues due to the search for an optimal adapting rate when a single neural controller is used, and in presence of strongly nonlinear systems, and (2) to improve the control law by selecting the suitable controller which generates the most valid control law satisfying the desired closed-loop performances. Numerical examples are illustrated to evaluate the performance of the proposed control scheme compared to the classical one. An application of the new strategy on a chemical reactor model validates satisfactory results.

Keywords:

• Neural multicontroller
• strongly nonlinear systems
• indirect adaptive control
• neural controller
• transesterification reactor model

Acknowledgement

This work was supported by the Ministry of Higher Education and Scientific Research-Tunisia.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

Yassin Farhat

Yassin Farhat received the Engineering Diploma in Electrical and Automatic Engineering, in 2018, from the Graduate School of Applied Sciences and Technology of Gabes-Tunisia. Currently, he is pursuing his PhD thesis at Research laboratory of numerical Control of Industrial Processes. His areas of interest include Nonlinear Process Identification, Neural Emulation and Adaptive Neural Control.

Ali Zribi

Ali Zribi received his Engineering Diploma in Electrical Engineering in 2005, Master Degree, PhD (Doctoral degree) and Habilitation Universitaire in Automatic Control in 2006, 2011 and 2018 respectively from the National School of Engineers of Sfax-Tunisia. He is currently Professor at the Higher Institute of Applied Science and Technology of Gabes. His areas of interest include Identification, Neural Networks and Multimodel Control.

Asma Atig

Asma Atig received the Engineering Diploma in Electrical Engineering, in 2007, and the Master Degree in Automatic Control, in 2008, from the National School of Engineers of Sfax, Tunisia. She received the PhD (Doctoral degree) in Electrical Engineering from the National School of Engineers of Gabes-Tunisia, in 2012, and in Computer Engineering and Signal Processing from University of Le Havre, France. Since 2012, she is an assistant professor at Higher Institute of Industrials Systems of Gabes-Tunisia. She is with Research laboratory of Numerical Control of Industrial Processes since 2007. Her areas of interest include Nonlinear Process Identification, Neural Emulation, Fuzzy logic and Adaptive Control.

Ridha Ben Abdennour

Ridha Ben Abdennour received his State Doctoral degree in Electrical Engineering from the National School of Engineers of Tunis-Tunisia, in 1996 and his PhD (Doctoral degree) in Automatic Control from Higher School of Technical Education in 1987. He is Professor in Automatic Control at the National School of Engineers of Gabes-Tunisia. He is the founder and He was the Head of the Electrical Engineering Department and the Director of the High Institute of Technological Studies of Gabes. Ridha BEN ABDENNOUR is the Director of the Research Laboratory of Numerical Control of Industrial Processes and he is the founder and the honorary President of the Tunisian Association of Automatic Control and Digitalization. His research is on Identification, Multimodel & Multicontrol approaches, Neural Networks, Observers, Diagnosis, Sliding mode control, Numerical Control and Fuzzy supervision. He is the co-author of a book on Identification and Numerical Control of Industrial Processes and he is the author of more than 400 publications. Ridha Ben Abdennour participated in the organization of many Conferences and he was member of some scientific committees of congresses.