ANFIS multi-tasking algorithm implementation scheme for ball-on-plate system stabilization

Authors

Oussama Hadoune
Badji Mokhtar University, Faculty of Technology, Department of electronics, LASA Laboratory
Mohamed Benouaret
Badji Mokhtar University, Faculty of Technology, Department of electronics, LASA Laboratory
DOI: https://doi.org/10.52549/ijeei.v10i4.4216
Download PDF
Published: 31-12-2022 • Issue: Vol. 10 No. 4: December 2022 • Section: Regular paper

Abstract

This paper presents the design and realization of a ball-on-plate system using a 3-degree-of-freedom parallel robot controlled by an adaptive neuro-fuzzy in-ference system. The ball-on-plate system is nonlinear, multivariable, with an under-actuated feature. Initially, the parallel robot is designed using SolidWorks and mechanized using a computer numerical control machine. Followed by the presentation of the ball-on-plate system mathematical model and the simplified model obtained. Afterwards, the inverse kinematics are performed to derive the appropriate angle for each servomotor. Eventually, the controller is designed and implemented in a double loop feedback scheme. A comparison between the proposed controller and a conventional proportional–integral–derivative controller in terms of time response, overshoot, and steady-state error is carried out. Furthermore, a comparison between sequential and asynchronous parallel processing is conducted for two different scenarios. The first scenario is when moving the ball to the origin while the second is for disturbance rejection. Simulation and experimental results show that the adaptive neuro-fuzzy inference system implemented using asynchronous parallel processing improves the real-time system stability by considerably decreasing oscillations as well as enhancing the ball movement smoothness with a small stead-state error.


Keywords: Control; robotics; real-time.

Author Biographies

Oussama Hadoune

Oussama Hadoune is a PhD student at university of Badji Mokhtar Annaba, Algeria. He holds a master degree in automation and industrial computing. His research areas include; robotics, real-time implementation, adaptive control and artificial intelligence. He received a number of national awards such the master project which was ranked among the top twenty innovative projects in 2019 by the higher ministry of education in Algeria. This same project won the price of the best third project in the national conference of startup at the university of Oum El-Bouaghi, Algeria. He can be contacted at email: oussama.hadoune@univ-annaba.org


Mohamed Benouaret

Mohamed Benoauret is a senior lecturer and professor who received his Bachelor's of science and later on his PhD  in in embedded electronics from the University of Badji Mokhtar Annaba, Algeria. He has supervised and co-supervised more than 20 masters and several Ph.D. students. His research interests include real-time implementation, FPGA, and FFT processors. He can be contacted at email: mohamed.benouaret@gmail.com

How to Cite

[1]
O. Hadoune and M. Benouaret, “ANFIS multi-tasking algorithm implementation scheme for ball-on-plate system stabilization”, IJEEI, vol. 10, no. 4, pp. 983–995, Dec. 2022, doi: 10.52549/ijeei.v10i4.4216.