Rolling Bearing Fault Diagnosis Using Modified Neighborhood Preserving Embedding and Maximal Overlap Discrete Wavelet Packet Transform with Sensitive Features Selection

<div>The diagnosis results of models using MODWPT for the testing sets of two cases with the use of FSASD and different dimensionality reduction methods. The output dimension sizes of PCA, LDA, and SNPEL are 20, 11, and 20, respectively. The “NO” represents the model without using dimensionality reduction method.</div>

Shock and Vibration

fig20

Figure 20

Figure 20: Rolling Bearing Fault Diagnosis Using Modified Neighborhood Preserving Embedding and Maximal Overlap Discrete Wavelet Packet Transform with Sensitive Features Selection 

Figure 20 | Rolling Bearing Fault Diagnosis Using Modified Neighborhood Preserving Embedding and Maximal Overlap Discrete Wavelet Packet Transform with Sensitive Features Selection 