AUTHOR=Gong Quanyi , Peng Ke , Wang Wei , Xu Bingyin , Zhang Xinhui , Chen Yu TITLE=Series Arc Fault Identification Method Based on Multi-Feature Fusion JOURNAL=Frontiers in Energy Research VOLUME=Volume 9 - 2021 YEAR=2022 URL=https://www.frontiersin.org/journals/energy-research/articles/10.3389/fenrg.2021.824414 DOI=10.3389/fenrg.2021.824414 ISSN=2296-598X ABSTRACT=With the increase of various loads connected to the low-voltage distribution system, the difficulty of identifying low-voltage series fault arcs has greatly increased, which seriously threatens the electricity safety. Aiming at such problems, a neural network algorithm based on multi-feature fusion is proposed. The fault current has the characteristics of randomness, high frequency noise and singularity. A GA-BP neural network model is built, and Wavelet analysis method (base on singularity), Fourier transform method (base on high frequency noise), current cycle difference method (base on randomness) and current cycle similarity derivation method (base on randomness) are used for feature extraction can more comprehensively reflect the characteristics of arc faults. Simulation results show that the multi-feature fusion algorithm has a higher recognition rate than other algorithms. And compared with support vector machine model, logistic regression model and AlexNet model, the GA-BP neural network model has a higher recognition accuracy than the other three models, which can reach 99%.