Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Fig 1.

CNN structure.

More »

Fig 1 Expand

Fig 2.

GADF conversion.

More »

Fig 2 Expand

Fig 3.

Self-calibrated convolution.

More »

Fig 3 Expand

Fig 4.

Cooperative compensation attention mechanism.

More »

Fig 4 Expand

Fig 5.

DSCNN model structure.

More »

Fig 5 Expand

Table 1.

DSCNN model hyperparameters.

More »

Table 1 Expand

Table 2.

Implementation process of DSCNN.

More »

Table 2 Expand

Fig 6.

HUST bearing fault physical map.

More »

Fig 6 Expand

Fig 7.

HIT aero-engine test rig.

More »

Fig 7 Expand

Fig 8.

HIT bearing fault physical map.

More »

Fig 8 Expand

Table 3.

Aero-engine bearing data.

More »

Table 3 Expand

Fig 9.

Comparison of GADF plots before and after adding noise.

(a)-(e) denotes no noisy. (a’)-(e’) denotes adding noisy.

More »

Fig 9 Expand

Fig 10.

HUST classification results.

More »

Fig 10 Expand

Fig 11.

t-SNE visualization and confusion matrix.

More »

Fig 11 Expand

Fig 12.

HIT classification results of different datasets.

More »

Fig 12 Expand

Fig 13.

Data visualization results on the HIT dataset.

(a)-(f) represent the t-SNE visualization result. (a’)-(f’) represent probability density estimation curves and histograms for different models.

More »

Fig 13 Expand