Fault Diagnosis of Rotating Machinery Based on Evolutionary Convolutional Neural Network

Table 5

Test results on the experimental data test set.

Network structure	Computable parameters	Min accuracy	Max accuracy	Mean of accuracy	Variance of accuracy	Training time (s)
VGG-5	28064	0.770	0.876	0.824	0.00168	25
ECNN	159336	0.878	0.914	0.901	0.00023	28
VGG-11	83232	0.880	0.904	0.888	0.00027	26
VGG-16	129472	0.818	0.920	0.864	0.00162	28