Intelligent Diagnosis of Rolling Bearing Fault Based on Improved Convolutional Neural Network and LightGBM

Table 5

Analysis table of training time and diagnosis time of each model.

Models	Training parameters		Average duration (s)
	Number of layers	Number	Training	Diagnosis
CNN-LSTM	8	507333	432.14	1.03
WDCNN	7	20755	107.26	0.12
CNN-SVM	4	63518	65.81	0.15
GCNN-LightGBM	2	2413	39.73	0.09