An alternating current arc fault weak signal detection method, device, equipment and medium

Abstract

This invention discloses a method, apparatus, equipment, and medium for detecting weak AC arc fault signals. It acquires the bus current signal of a low-voltage power distribution system and performs amplitude standardization preprocessing to generate a normalized signal. The normalized signal is then subjected to time-frequency domain feature fusion extraction to generate a comprehensive feature vector. A nested sliding window mechanism is used to perform fault diagnosis on the comprehensive feature vector, generating a fault diagnosis label. Based on the comprehensive feature vector and the fault diagnosis label, a pre-trained classification model is used to generate arc fault classification results. This invention, through the synergistic effect of signal denoising, feature fusion, real-time diagnosis, and intelligent classification, improves detection sensitivity to reliable identification in low signal-to-noise ratio scenarios (-10dB), and meets the real-time requirements of the UL1699 standard, solving the core problems of insufficient sensitivity and real-time performance in detecting weak AC arc faults.

Images