Deep learning-based bubble detection with swin transformer

ABSTRACT

We developed a deep learning-based bubble detector with a Shifted window Transformer (Swin Transformer) to detect and segment individual bubbles among overlapping bubbles. To verify the performance of the detector, we calculated its average precision (AP) with different number of training images. The mask AP increased with the increase in the number of training images when there were less than 50 images. It was observed that the AP for the Swin Transformer and ResNet were almost the same when there were more than 50 images; however, when few training images were used, the AP of the Swin Transformer were higher than that of the ResNet. Furthermore, for the increase in void fraction, the AP of the Swin Transformer showed a decrease similar to that in the case of the ResNet; however, for few training images, the AP of the Swin Transformer was higher than that of the ResNet in all void fractions. Moreover, we confirmed the detector trained with experimental and synthetic bubble images was able to segment overlapping bubbles and deformed bubbles in a bubbly flow experiment. Thus, we verified that the new bubble detector with Swin Transformer provided higher AP than the detector with ResNet for fewer training images.

KEYWORDS:

• two-phase flow
• thermal hydraulics
• deep learning
• vision transformer
• swin transformer
• bubble detector

Nomenclature

ai	=	interfacial area concentration[1/m]
C0	=	distribution parameter[-]
DH	=	hydraulic equivalent diameter of the pipe[-]
(-dP/dz)F	=	pressure loss per unit length[Pa/m]
g	=	gravitational acceleration[m/s2]
j	=	mixture velocity[m/s]
jg	=	superficial gas velocity[m/s]
Vgj	=	drift velocity[m/s]
Greek letters	=
α	=	void fraction[-]
ε	=	energy dissipation rate per unit mass[m2/s3]
μ	=	viscosity[Pa s]
ν	=	kinematic viscosity of liquid[m2/s]
ρg	=	gas mass density[kg/m3]
ρl	=	liquid mass density[kg/m3]
ρm	=	mixture mass density[kg/m3]
Δρ	=	mass density difference[kg/m3]
σ	=	surface tension[N/m]

Acknowledgments

The authors would like to thank Mr. Koji Ono and Mr. Natsuki Hiramatsu at Human Support Technology for their help in developing the bubble detector and Mr. Mitsuhiko Shibata at JAEA, Mr. Masao Komatsu and Mr. Shuto Tanai at Nuclear Engineering for his help for performing the experiment.

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Funding

The author(s) reported there is no funding associated with the work featured in this article.