Intelligent fuzzy-based automatic voltage regulator with hybrid optimization learning method
This work focuses on enhancing the performance of an Automatic Voltage Regulator (AVR) by providing a good transient response, adaptability to changing circumstances, and robustness. Its objective is centered on utilizing the Adaptive Neuro-Fuzzy Inference System (ANFIS) to control the AVR system. T...
Saved in:
| Published in: | Scientific African Vol. 19; p. e01573 |
|---|---|
| Main Authors: | , , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier B.V
01-03-2023
Elsevier |
| Subjects: | |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | This work focuses on enhancing the performance of an Automatic Voltage Regulator (AVR) by providing a good transient response, adaptability to changing circumstances, and robustness. Its objective is centered on utilizing the Adaptive Neuro-Fuzzy Inference System (ANFIS) to control the AVR system. The study is important because it compares the performance of the system without a controller, with the PID controller and the proposed ANFIS. This work shows a novel application of ANFIS with a hybrid learning algorithm for the AVR system. The ANFIS was designed by using the hybrid optimization learning scheme to train the Fuzzy Inference System (FIS) that is used to control the parameters of the AVR system. To generate the right dataset used for training the fuzzy inferential system, the Proportional-Integral-Derivative (PID) simulation of the entire system connected to the AVR is used setting the simulation time to about ten seconds. Simulation of the work was done in MATLAB/Simulink and enhanced performance objectives (rise time of 1.1994s, settling time of 1.8818, overshoot of 1.3206, and steady-state error of 4.269e-04) were compared to other related works. |
|---|---|
| ISSN: | 2468-2276 2468-2276 |
| DOI: | 10.1016/j.sciaf.2023.e01573 |