Recurrent Neural Networks RNNs and Decision Tree DT Machine Learning-Based Approaches For Transmission System Faults Diagnosis - Article

Aug 5, 2026

Accurate and prompt detection of electrical system faults is critical to ensure reliable protection of equipment, prevent false tripping, and avoid cascaded failures. This paper evaluates machine learning methods for fault detection and classification, focusing on a comparative study between Recurrent Neural Networks (RNNs) and Decision Tree (DT). Using a dataset of real-world electrical fault scenarios, the work assesses performance through accuracy, precision, recall, and confusion matrices, highlighting differing strengths and trade-offs for fault management.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

Abstract

Introduction

Journal of Engineering Research Volume 7 Issue 5 This is a Special Issue from the Applied Innovative Research in Engineering Grand Challenges (AIRGEC) Conference,(AIRGEC 2023), Faculty of Engineering, Horus University, New Damietta, Egypt, 25-26 October 2023 Article 41 2023 Recurrent Neural Networks RNNs and Decision Tree DT Machine Learning-Based Approaches For Transmission System Faults Diagnosis Sayed Abuanwar, Mohammed Saeed, Hanan Mosalem, Hatem Khater Follow this and additional works at: [https://digitalcommons.aaru.edu.jo/erjeng](https://digitalcommons.aaru.edu.jo/erjeng) Recommended Citation Abuanwar, Mohammed Saeed, Hanan Mosalem, Hatem Khater, Sayed (2023) "Recurrent Neural Networks RNNs and Decision Tree DT Machine Learning-Based Approaches For Transmission System Faults Diagnosis," Journal of Engineering Research: Vol. 7: Iss. 5, Article 41. Available at: [https://digitalcommons.aaru.edu.jo/erjeng/vol7/iss5/41](https://digitalcommons.aaru.edu.jo/erjeng/vol7/iss5/41) This Article is brought to you for free and open access by Arab Journals Platform. It has been accepted for inclusion in Journal of Engineering Research by an authorized editor. The journal is hosted on Digital Commons, an Elsevier platform. For more information, please contact [rakan@aaru.edu.jo](rakan@aaru.edu.jo), [marah@aaru.edu.jo](marah@aaru.edu.jo), [u.murad@aaru.edu.jo](u.murad@aaru.edu.jo). Journal of Engineering Research (ERJ) Vol. 7– No. 5, 2023 ©Tanta University, Faculty of Engineering ISSN: 2356-9441 [https://erjeng.journals.ekb.eg/](https://erjeng.journals.ekb.eg/ e ISSN:)[ e ISSN:](https://erjeng.journals.ekb.eg/ e ISSN:) 2735-4873 Recurrent Neural Networks RNNs and Decision Tree DT Machine Learning-Based Approaches For Transmission System Faults Diagnosis Sayed Abulanwar1,2, Mohammed Saeed2,3, Hanan Mosalem3, Hatem Khater1 1 Faculty of Engineering, Horus University-Egypt, New Damietta 34518, Egypt 2 Electrical Engineering Department, Faculty of Engineering, Mansoura University, 35516, Mansoura, Egypt 3Communications Engineering Department, Mansoura Higher Institute of Engineering and Technology, El-Mansoura, Egypt Abstract- Accurate and prompt detection of system faults are crucial to maintain sufficient protection of system equipment, avoid false tripping, and cascaded failures. This paper presents a comprehensive study on the effectiveness of machine learning techniques for electrical fault detection and classification. Specifically, a comparative analysis is conducted between two prominent algorithms: Recurrent Neural Networks (RNNs) and Decision Tree (DT). The study employs a dataset comprising realworld electrical fault scenarios to evaluate the performance of RNNs and DT in identifying and categorizing faults. While DT algorithm showed slightly better accuracy in some cases, the RNN exhibited better generalization capabilities and a lower risk of overfitting. The analysis involves various performance metrics such as accuracy, precision, recall, and confusion matrices to comprehensively assess the algorithms' capabilities. The findings provide valuable insights into the strengths and limitations of each approach in the context of electrical fault management. This paper contributes to the selection of suitable techniques based on specific application requirements, advancing the field of predictive maintenance and fault mitigation in electrical systems. Keywords-Decision Tree, Electrical Faults, Fault Classification, Fault Detection, Machine Learning, Recurrent Neural Networks. I. Introduction Security of power systems is currently threated owing to the steady growth of renewable energy resources (RERs) which aggravates their complexity and causes voltage instabilities raised by their intermittencies [1] . As transmission systems represent a pivotal role within the power system, nowadays, their protection is gaining increased popularity owing to the high-power demand and their complex

FAQs

Why is prompt electrical fault detection important in transmission systems?

Prompt detection supports adequate protection of equipment, reduces false tripping, and helps avoid cascaded failures that can threaten system stability.

Which two machine learning algorithms are compared in this paper?

The paper compares Recurrent Neural Networks (RNNs) and Decision Tree (DT) for electrical fault detection and classification.

What metrics are used to evaluate the algorithms’ performance?

Performance is assessed using accuracy, precision, recall, and confusion matrices to examine classification effectiveness and behavior.

Aug 5, 2026

Upload by Emma Wilson