Analytical Comparisons of the PID, ANN, and ANFIS Controllers' Performance in the AVR System

Avijit Kundu; Saiful Islam Tuhin; Md. Sahadat Hossain Sani; Md. Wahidur Rahman Easin; Md. Arif Hasan Masum1

1

Publication Date: 2023/08/21

Abstract: This research paper thoroughly investigates the performance characteristics of PID, which stands for Proportional-Integral-Derivative, ANFIS, an acronym for Adaptive-Neuro-Fuzzy Inference System, and ANN (Artificial-Neural-Network) controllers in Automatic Voltage Regulator (AVR) systems. This investigation aims to analyze the controller's behavior so that it can be used in any of the other control systems in the power system. Leveraging the power of MATLAB-SIMULINK, the PID controller undergoes meticulous tuning, while the ANFIS and ANN controllers are trained using meticulously curated data from the PID controller.Although the ANN controller exhibits a reduction in overshoot compared to the PID controller, it falls short with a lengthier settling- time. Based on this comprehensive analysis, it is unequivocally established that the ANFIS controller reigns supreme, closely trailed by the ANN controller and the PID controller. These findings offer profound insights for researchers and practitioners, guiding them in the astute selection of controllers for any control system.

Keywords: AVR (Automatic-Voltage-Regulator), PID (Proportional Integral Derivative), ANFIS (Adaptive Neuro Fuzzy Inference System), ANN (Artificial-Neural-Network), Simulink, Controller, MATLAB, etc.

DOI: https://doi.org/10.5281/zenodo.8269112

PDF: https://ijirst.demo4.arinfotech.co/assets/upload/files/IJISRT23AUG699.pdf

REFERENCES

No References Available