 This systematic review investigated the use of artificial intelligence, AI, in arc fault detection. It found that AI can significantly improve the accuracy and speed of arc fault detection, as well as allow for customization to specific types of faults. However, there are still some challenges such as missed and false detections, limited application of neural networks, and lack of relevant data. Overall, AI shows great potential for improving electrical safety by detecting arc faults more accurately and quickly than traditional methods. This article was authored by Chunping Tian, Zhao Yangsu, Lu Kuanwang, and others.