Arc-1DCNN: An enhanced model for series arc fault detection

Abstract

Series Arc Faults (SAFs) represent a prominent cause of electrical fires in low-voltage distribution systems, often arising from faulty connections or deteriorated insulation. These SAFs occurrences generate high-temperature arcs that endanger electrical system safety. As a result, detecting and accurately identifying SAFs have become crucial concerns. However, the line noise interference and the complexity of the electrical environment make SAFs detection challenging. In this paper, we propose a novel method that combines Wiener filtering with the Arc-1DCNN model to enhance SAFs detection. The method leverages Wiener filtering to enhance current signal, effectively reducing noise interference and providing a more robust dataset for training. To fully exploit the rich high-frequency characteristics of SAFs, Arc-1DCNN incorporates a High-Frequency-Feature-Attention module, enabling the model to capture subtle SAFs anomalies and significantly improving detection accuracy. Experimental validation demonstrates Arc-1DCNN's exceptional performance with 99.94% detection accuracy for SAFs, showcasing its potential for addressing SAFs detection challenges.