An Unsupervised Deep Feature Learning Model Based on Parallel Convolutional Autoencoder for Intelligent Fault Diagnosis of Main Reducer

Table 6

Precision of different situations.

Models	BPNN	SVM	CNN	PCAE-DNN
Dataset size	Average testing accuracy (%)
100%	89.54	90.15	90.52	95.86
70%	86.39	85.66	88.83	95.04
40%	83.22	82.83	84.37	94.39
20%	73.07	74.47	78.69	93.12
5%	61.91	63.72	73.15	92.47