loading page

BubSAM: Bubble segmentation and shape reconstruction based on Segment Anything Model of bubbly flow
  • +6
  • Haohan Xu,
  • Xin Feng,
  • Yuqi Pu,
  • Xiaoyue Wang,
  • Dingwang Huang,
  • Weipeng Zhang,
  • Xiaoxia Duan,
  • Jie Chen,
  • Chao Yang
Haohan Xu
Institute of Process Engineering Chinese Academy of Sciences
Author Profile
Xin Feng
Institute of Process Engineering Chinese Academy of Sciences

Corresponding Author:[email protected]

Author Profile
Yuqi Pu
Sichuan University
Author Profile
Xiaoyue Wang
Institute of Process Engineering Chinese Academy of Sciences
Author Profile
Dingwang Huang
Institute of Process Engineering Chinese Academy of Sciences
Author Profile
Weipeng Zhang
Institute of Process Engineering Chinese Academy of Sciences
Author Profile
Xiaoxia Duan
Institute of Process Engineering Chinese Academy of Sciences
Author Profile
Jie Chen
Institute of Process Engineering Chinese Academy of Sciences
Author Profile
Chao Yang
Institute of Process Engineering Chinese Academy of Sciences
Author Profile

Abstract

Accurate detection and analysis of bubble size and shape in bubbly flow are critical to understanding mass and heat transfer processes. Convolutional neural networks have limitations in different bubble images due to their dependence on large amounts of labeled data. A new foundational Segment Anything Model (SAM) recently attracts lots of attention for its zero-shot segmentation performance. Herein, we developed a novel image processing method named bubSAM, which achieves efficient and accurate bubble segmentation and shape reconstruction based on SAM. The segmentation performance of bubSAM is 30% higher than that of SAM, and its accuracy reaches 90% under different bubbly flow conditions. The accuracy of bubble shape reconstruction algorithm (BSR) in bubSAM is about 30% higher than that of typical ellipse fitting method, thus better restoring the geometric shape of bubbles. BubSAM can provide great support for understanding gas-liquid multiphase flow and design of industrial multiphase reactors.
26 May 2024Submitted to AIChE Journal
27 May 2024Submission Checks Completed
27 May 2024Assigned to Editor
27 May 2024Review(s) Completed, Editorial Evaluation Pending
24 Jun 2024Editorial Decision: Revise Minor
07 Jul 20241st Revision Received
08 Jul 2024Submission Checks Completed
08 Jul 2024Assigned to Editor
08 Jul 2024Review(s) Completed, Editorial Evaluation Pending
08 Jul 2024Reviewer(s) Assigned
30 Jul 2024Editorial Decision: Accept