Diagnosis of Fault on 330kV Power System Transmission Lines Using Artificial Neural Network and Travelling Wave

• Author(s): Kazaka T. D. ; Ogboh V. C. ; Obute K. C. ; Oyiogu D. C
• Paper ID: 1707864
• Page: 609-632
• Published Date: 17-04-2025
• Published In: Iconic Research And Engineering Journals
• Publisher: IRE Journals
• e-ISSN: 2456-8880
• Volume/Issue: Volume 8 Issue 10 April-2025

Abstract

The reliability and stability of high-voltage power transmission systems are critical for efficient energy delivery and national grid integrity. In this study, we investigate the application of Artificial Intelligence (AI) techniques for the diagnosis of faults on 330kV power system transmission lines. Traditional fault detection and location methods often suffer from latency, reduced accuracy under complex fault conditions, and limitations in real-time analysis. This research leverages machine learning algorithms, including Artificial Neural Networks (ANN), Support Vector Machines (SVM), and Decision Trees (DT), to detect, classify, and locate various types of faults—such as single line-to-ground (SLG), line-to-line (LL), double line-to-ground (DLG), and three-phase faults—based on real-time voltage and current signal features. Simulations were conducted using MATLAB/Simulink to model the transmission network and generate training datasets under diverse operating conditions. The AI models demonstrated high accuracy and robustness in fault classification and location estimation, with significantly improved speed compared to conventional methods. This work highlights the potential of AI-driven systems to enhance fault management in high-voltage transmission networks, reduce downtime, and support proactive maintenance strategies in smart grid applications. Let me know if you want it tailored toward a specific region or case study (like Nigeria or a particular substation), or if you want to add performance metrics or specific AI models.

Keywords

Transmission Line, Artificial Neural Network, Fault, Traveling Wave, Location.

Citations

IRE Journals:
Kazaka T. D. , Ogboh V. C. , Obute K. C. , Oyiogu D. C "Diagnosis of Fault on 330kV Power System Transmission Lines Using Artificial Neural Network and Travelling Wave" Iconic Research And Engineering Journals Volume 8 Issue 10 2025 Page 609-632

IEEE:
Kazaka T. D. , Ogboh V. C. , Obute K. C. , Oyiogu D. C "Diagnosis of Fault on 330kV Power System Transmission Lines Using Artificial Neural Network and Travelling Wave" Iconic Research And Engineering Journals, 8(10)