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

Table 1.

Flow pattern types and characteristics.

More »

Table 1 Expand

Fig 1.

Schematic diagram of the experimental setup: (1) Water tank, (2) Centrifugal pump, (3) Valve, (4) Turbine flowmeter, (5) Air compressor, (6) Air buffer tank, (7) Needle valve, (8) Gas flowmeter, (9) Check valve, (10) Gas-liquid mixer, (11) Observation section, (12) Gas-liquid separation water tank, (13) High-speed camera, (14) Computer.

More »

Fig 1 Expand

Fig 2.

Results after preprocessing.

More »

Fig 2 Expand

Fig 3.

Transitional flow pattern images.

More »

Fig 3 Expand

Fig 4.

ECA module structure.

More »

Fig 4 Expand

Fig 5.

Working principle of dilated convolution.

More »

Fig 5 Expand

Fig 6.

Receptive fields under different dilation rates.

More »

Fig 6 Expand

Fig 7.

DenseNet network architecture diagram.

More »

Fig 7 Expand

Fig 8.

Dense Block structure diagram.

More »

Fig 8 Expand

Fig 9.

Dense Layer structure diagram.

More »

Fig 9 Expand

Fig 10.

Schematic diagram of ED-DenseNet model structure.

More »

Fig 10 Expand

Fig 11.

Schematic diagram of flow pattern recognition via transfer learning.

More »

Fig 11 Expand

Table 2.

Ablation study results of the ED-DenseNet model.

More »

Table 2 Expand

Fig 12.

Loss rate change curve.

(The loss and accuracy curves in Figs 11 and 12 remain unchanged, as the additional transitional flow dataset is only used in the test phase and is not included in training or validation).

More »

Fig 12 Expand

Fig 13.

Accuracy change curve.

More »

Fig 13 Expand

Fig 14.

Confusion matrix for flow pattern classification.

More »

Fig 14 Expand

Table 3.

Classification performance of primary and transitional flow patterns.

More »

Table 3 Expand

Fig 15.

Deep learning model flow pattern recognition accuracy.

More »

Fig 15 Expand

Table 4.

Performance and training efficiency of different models.

More »

Table 4 Expand

Fig 16.

Model accuracy curves.

More »

Fig 16 Expand

Fig 17.

Model loss curves.

More »

Fig 17 Expand

Table 5.

Comparison of different optimizers on ED-DenseNet.

More »

Table 5 Expand

Table 6.

Comparison of different optimizers on DenseNet121, MobileNetV3, and ConvNeXt.

More »

Table 6 Expand

Fig 18.

Two-phase flow patterns for nitrogen condensation.

More »

Fig 18 Expand

Table 7.

Generalization experiment results.

More »

Table 7 Expand