Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition

<div>The curve representation of diagnosis results of models using WPT for the testing sets of two cases with the use of TSFRS and different dimensionality reduction methods. The output dimension sizes of PCA, LDA, LFDA, MMC, and LMMC are 20, 11, 11, 11, and 11, respectively.</div>

Shock and Vibration

fig19

Figure 19

Figure 19: Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition 

Figure 19 | Rolling Bearing Fault Diagnosis Based on Sensitive Feature Transfer Learning and Local Maximum Margin Criterion under Variable Working Condition 