An Intelligent Fault Diagnosis Method of Multi-Scale Deep Feature Fusion Based on Information Entropy

Chinese Journal of Mechanical Engineering

Table 2 Diagnostic results of different methods from 10 experiments

Methods	Input dimensions	Average testing accuracy (%)	Standard deviation of testing accuracy
Method 1	300	94.31	0.3187
Method 2	300	88.19	1.3593
Method 3	300	90.13	1.2359
Method 4	300	90.69	1.2823
Method 5	300	90.94	1.0287
Method 6	400	90.74	0.6171
Method 7	28	84.07	1.4211
Method 8	28	89.39	0.8097
Method 9	28	90.40	1.3824
Method 10	28	83.14	1.7112

Notes: Method 1, the proposed method with raw data; Method 2, DNAE with raw data; Method 3, DDAE with raw data; Method 4, DSAE with raw data; Method 5, DCAE with raw data; Method 6, CNN with raw data; Method 7, BP with 28 features; Method 8, SVM with 28 features; Method 9, RF with 28 features; Method 10, Softmax classifier with 28 features.