Real-time control of ball balancer using neural integrated fuzzy controller

• Published in: The Artificial intelligence review Vol. 53; no. 1; pp. 351 - 368
• Main Authors: Singh, Rupam, Bhushan, Bharat
• Format: Journal Article
• Language: English
• Published: Dordrecht Springer Netherlands 01.01.2020; Springer; Springer Nature B.V
• Subjects: Algorithms; Artificial Intelligence; Balancing; Closed loops; Comparative studies; Computer Science; Computer simulation; Control systems; Controllers; Design; Dimensional analysis; Error analysis; Field programmable gate arrays; Fuzzy control; Fuzzy logic; Fuzzy systems; Multivariable control; Neural networks; Optimization techniques; Proportional integral derivative; Real time; Simulation; System theory; Time response; Vision systems; Neural integrated fuzzy with PID control; Neural integrated fuzzy control; Ball balancer system; Proportional-integral-derivative control
• ISSN: 0269-2821; 1573-7462
• DOI: 10.1007/s10462-018-9658-7

This paper presents the design, control, and validation of two degrees of freedom Ball Balancer system. The ball and plate system is a nonlinear, electromechanical, multivariable, closed-loop unstable system on which study is carried out to control the position of ball and plate angle. The model of the system is developed using MATLAB/Simulink, and neural integrated fuzzy and its hybridization with PID have been implemented. The performance of each controller is evaluated in terms of time response analysis and steady-state error. Comparative study of simulation and real-time control results show that by using the neural integrated fuzzy controller and neural integrated fuzzy with proportional-integral-derivative Controller, the peak overshoot is reduced as compared with the PID controller and lead the system prone to appropriate balancing. These control techniques provide a stable and controlled output to the system for ball balancing and plate angle control.