Title: Novel adaptive control for avoiding fuzzy rule explosion in nonlinear systems

Authors: Ashwani Kharola

Addresses: Department of Mechanical Engineering, Graphic Era (Deemed to be University), Dehradun, India

Abstract: The study highlights three different control techniques namely proportional integral derivative (PID), adaptive neuro fuzzy inference system (ANFIS) and neural networks (NNs) for the control of highly nonlinear triple inverted pendulum system mounted on a carriage. The objective is to control the complete system within 3.0 sec using above mentioned controllers. The controllers were compared in terms of performance attributes like settling time, steady state error and overshoot responses. The results indicate better performance of ANFIS controller compared to PID and NN controllers. The study also highlights the effect of shape, number and type of membership function on training of ANFIS controller. The study further proposes an ANFIS controller which has been designed using only three membership functions and can successfully solve the problem of rule explosion associated with fuzzy controllers.

Keywords: triple inverted pendulum; fuzzy rule explosion; artificial neural networks; proportional integral derivative; PID; ANFIS; MATLAB; Simulink; simulation.

DOI: 10.1504/IJAAC.2023.131740

International Journal of Automation and Control, 2023 Vol.17 No.4, pp.377 - 396

Received: 25 Mar 2022
Accepted: 26 Jun 2022
Published online: 30 Jun 2023 *

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