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.

Systematic schematic diagram of the overall architecture.

More »

Fig 1 Expand

Fig 2.

LIB model.

More »

Fig 2 Expand

Fig 3.

Simplified FD model for battery pack.

More »

Fig 3 Expand

Fig 4.

2DCNN structure.

More »

Fig 4 Expand

Fig 5.

Convolution operation process.

More »

Fig 5 Expand

Fig 6.

LBFD processprocess. ((Icons in the picture are sourced from:

https://freeicons.io/iconset/free-icons-set).

More »

Fig 6 Expand

Table 1.

The experimental basic environmental parameters.

More »

Table 1 Expand

Table 2.

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

More »

Table 2 Expand

Table 3.

Quantitative comparison between feeding raw data directly into a CNN and the method proposed in this study.

More »

Table 3 Expand

Table 4.

Operation performance and signal decomposition effect.

More »

Table 4 Expand

Table 5.

Comparison of computational efficiency and memory consumption.

More »

Table 5 Expand

Fig 7.

Method training loss testing.

More »

Fig 7 Expand

Fig 8.

Loss function and accuracy of each training set.

More »

Fig 8 Expand

Fig 9.

Consistency of extracting data feature information.

More »

Fig 9 Expand

Fig 10.

Accuracy of fault feature identification.

More »

Fig 10 Expand

Fig 11.

Runtime analysis.

More »

Fig 11 Expand

Fig 12.

Analysis of the proportion of misidentified content.

More »

Fig 12 Expand

Fig 13.

Comparison of confusion matrix of Test Set A.

More »

Fig 13 Expand

Fig 14.

Visualization process of LBFD.

More »

Fig 14 Expand

Table 6.

Statistical analysis of model attention distribution for different fault types based on Grad-CAM.

More »

Table 6 Expand

Table 7.

Performance breakdown by fault category on the combined test set.

More »

Table 7 Expand