A Review on Artificial Intelligence-Based Fault Location Methods in Electric Power Distribution Systems | ||
| مدل سازی در مهندسی | ||
| Articles in Press, Accepted Manuscript, Available Online from 05 October 2025 | ||
| Document Type: Research Paper | ||
| DOI: 10.22075/jme.2025.34536.2688 | ||
| Authors | ||
| mohamad aryanfar1; Mostafa Jazaeri* 2 | ||
| 1Department of Power Electricity | ||
| 2Faculty of electrical and computer engineering - Semnan University | ||
| Receive Date: 22 June 2024, Revise Date: 25 May 2025, Accept Date: 08 September 2025 | ||
| Abstract | ||
| Faults and failures in wide electrical power distribution systems can occur for various reasons and have destructive effects on the power quality and also suitable system service continuity if the failure is not identified and resolved in the shortest possible time. Hence, in order to improve the reliability and enhance the network adequacy, fast and accurate fault location is an important concern in the system protection area. The use of Artificial Intelligence (AI) techniques in the field of fault location has been introduced as a practical and useful method from view point of researchers in recent years. In AI-based methods, the estimator can be trained by offline methods to be able to provide fast online estimation of the fault location or fault segment. These methods require a significant amount of training data, which can be based on historical records or generated in a simulation process. Research shows that AI-based methods are less sensitive to noise in the input data and significantly more accurate than serious competitors including impedance-based methods. This paper in fact provides a comprehensive and conceptual review on artificial intelligence-based methods with the aim of fault location in the electrical energy distribution networks. For this purpose, the advantages and disadvantages of the proposed methods presented in the published papers mainly since 2014 are categorized, compared and concluded. | ||
| Keywords | ||
| Artificial intelligence; AI; Fault location; Machine Learning; Distribution Networks | ||
| References | ||
|
| ||
|
Statistics Article View: 293 |
||