Lightweight Ac Arc Fault Diagnosis via Fourier Transform Inspired Multi-frequency Neural Network

TL;DR

This paper introduces MFNN, a multi-frequency neural network with a novel adaptive activation function, designed for fast, accurate, and resource-efficient arc fault detection in power systems, outperforming existing methods.

Contribution

The work proposes a new multi-frequency neural network architecture with an adaptive activation function, embedding physical knowledge for improved arc fault diagnosis under resource constraints.

Findings

MFNN outperforms other models in fault location accuracy.

MFNN demonstrates superior noise immunity, with 14.51% and 16.3% higher accuracy at low SNR.

EAS and the network architecture significantly enhance MFNN's performance.

Abstract

Lightweight online detection of series arc faults is critically needed in residential and industrial power systems to prevent electrical fires. Existing diagnostic methods struggle to achieve both rapid response and robust accuracy under resource-constrained conditions. To overcome the challenge, this work suggests leveraging a multi-frequency neural network named MFNN, embedding prior physical knowledge into the network. Inspired by arcing current curve and the Fourier decomposition analysis, we create an adaptive activation function with super-expressiveness, termed EAS, and a novel network architecture with branch networks to help MFNN extract features with multiple frequencies. In our experiments, eight advanced arc fault diagnosis models across an experimental dataset with multiple sampling times and multi-level noise are used to demonstrate the superiority of MFNN. The corresponding experiments show: 1) The MFNN outperforms other models in arc fault location, befitting from signal decomposition of branch networks. 2) The noise immunity of MFNN is much better than that of other models, achieving 14.51% over LCNN and 16.3% over BLS in test accuracy when SNR=-9. 3) EAS and the network architecture contribute to the excellent performance of MFNN.