Method of Series Arc Fault Detection Based on Phase Space Reconstruction and Convolutional Neural Network

Table 6

Comparison of the method in this paper with traditional series arc fault detection methods.

Method	Whether to preserve graph global information	Sampling accuracy of the required data	Image size	Accuracy rate (%)
Attractor attribute + PCA [8]	N	409.6 kHz	—	98%–98.3
Linear discriminant [9] + GLCM	N	25 kHz	—	97
Time domain grayscale value image + CNN [10]	Y	1 MHz	100 100	97.67
Phase space distance feature matrix + CNN	Y	10 kHz	50 50	99.00