IJRR

International Journal of Research and Review

| Home | Current Issue | Archive | Instructions to Authors | Journals |

Year: 2024 | Month: October | Volume: 11 | Issue: 10 | Pages: 518-535

DOI: https://doi.org/10.52403/ijrr.20241047

Artificial Neural Network-Based Fault Detection on Nigerian 330kv Power Transmission Line

Hammed Waheed Olalekan1, Onyegbadue Ikenna Augustine2, Guiawa Mathurine3

1,2,3Department of Electrical and Electronic Engineering, College of Engineering, Igbinedion University, Okada, Edo State, Nigeria

Corresponding Author: Hammed Waheed Olalekan

ABSTRACT

In Nigeria, there will inevitably be ongoing difficulties with 330kv power transmission lines. This drop in insulation strength between the phase conductors and the earthed screen encircling the conductors may be the cause of the difficulties that have emerged on the electric transmission circuit. Many scholars have approached these problems in different ways. Fast Fourier Transform (FFT), Wavelet Transform, Fourier Transform, S-Transform, and Fourier Series are a few of the techniques utilized to address these transmission line problems. It has not been widely and thoroughly adopted to solve problems in Power System Engineering, according to numerous study studies on artificial neural networks (ANNs). Consequently, the 330kV Power Transmission Line problems have been addressed in this research by using artificial neural networks (ANNs). the training efficacy of any ANN challenges diagnosis system. The MATLAB/Simulink R2018a was utilized to conduct simulations on an ANN challenges detector. The ANN detector was trained with pre-fault and fault signals as inputs, allowing for the identification of different types of line difficulties. Results indicated that at Mean Square Error (MSE) of 1.6856e-5, the best training performance for the challenges was attained. At Regression, it approaches zero (9.8958e-1). Because it met the requirements, the simulation's outcome is acceptable.

Keywords: Power System, Transmission Line, Matlab/Simulink, Three Phase, Artificial neural networks, fault detection.

[PDF Full Text]