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.

The framework for partial discharge recognition in power transformers by synergistically combining variational mode decomposition (VMD) optimization with deep spatiotemporal feature learning.

More »

Fig 1 Expand

Fig 2.

Data acquisition and preprocessing process.

More »

Fig 2 Expand

Fig 3.

VMD-based signal feature extraction optimization.

More »

Fig 3 Expand

Fig 4.

The proposed hybrid deep learning architecture.

More »

Fig 4 Expand

Table 1.

STFT feature performance metrics.

More »

Table 1 Expand

Fig 5.

STFT feature performance metrics.

More »

Fig 5 Expand

Table 2.

Wavelet scattering transform results.

More »

Table 2 Expand

Fig 6.

Wavelet scattering transform results.

More »

Fig 6 Expand

Table 3.

VMD-CNN performance across all test conditions.

More »

Table 3 Expand

Fig 7.

VMD-CNN performance.

More »

Fig 7 Expand

Table 4.

Model robustness under adverse conditions.

More »

Table 4 Expand

Table 5.

Standard LSTM performance metrics.

More »

Table 5 Expand

Fig 8.

Standard LSTM performance.

More »

Fig 8 Expand

Table 6.

Transformer model performance across all conditions.

More »

Table 6 Expand

Fig 9.

Transformer model performance.

More »

Fig 9 Expand

Table 7.

Attention-LSTM detailed performance.

More »

Table 7 Expand

Fig 10.

Attention-LSTM performance.

More »

Fig 10 Expand

Fig 11.

TDOA triangulation performance.

More »

Fig 11 Expand

Table 8.

TDOA triangulation localization performance.

More »

Table 8 Expand

Fig 12.

U-net CNN performance.

More »

Fig 12 Expand

Table 9.

U-Net CNN localization performance across all conditions.

More »

Table 9 Expand

Fig 13.

Hybrid model performance.

More »

Fig 13 Expand

Table 10.

Hybrid model detailed localization performance.

More »

Table 10 Expand

Table 11.

Extended comparison with state-of-the-art methods.

More »

Table 11 Expand