AI-BASED UNDERGROUND CABLE FAULT DETECTION AND LOCATION IDENTIFICATION SYSTEM USING RASPBERRY PI

Abstract

Underground power cables are widely used in modern electrical distribution systems because they improve system reliability, reduce exposure to environmental conditions, and enhance public safety. However, faults occurring in underground cables are difficult to identify due to their concealed installation, resulting in extended maintenance time, increased repair costs, and interruptions in power supply. Conventional fault detection methods often require extensive manual inspection and specialized equipment, making the maintenance process time-consuming and inefficient. Recent advancements in embedded systems, sensor technology, and intelligent monitoring have enabled the development of automated cable fault detection systems capable of accurately identifying fault locations in real time. This project presents an Underground Cable Fault Detection and Location Identification System Using Raspberry Pi Controller. The proposed system employs a Raspberry Pi as the central processing unit to continuously monitor cable conditions and detect abnormalities such as open-circuit faults, short-circuit faults, and earth faults. A voltage divider network and sensing circuits are used to measure electrical parameters along the cable, and the acquired data are processed by the Raspberry Pi to estimate the distance of the fault from the monitoring station. The calculated fault location is displayed on an LCD screen, enabling maintenance personnel to quickly identify the affected cable section. The system provides continuous monitoring, rapid fault localization, and improved maintenance efficiency while minimizing downtime and operational costs. Experimental evaluation demonstrates accurate fault detection, reliable fault distance estimation, and stable system performance under different fault conditions. The proposed framework improves the reliability of underground power distribution networks by reducing fault identification time, simplifying maintenance activities, and enhancing power system safety. The developed solution offers a costeffective, scalable, and efficient approach for intelligent underground cable monitoring and supports the modernization of smart electrical distribution systems.