Home Journals Articles Updates About
CN
image
收藏切换
Feature Extraction and Flow Pattern Recognition of Gas-Liquid Two-Phase Flow Based on Improved Wavelet Thresholding
收藏切换
PDF
Li CHEN1, 2, Yanlian DU1, 2, Fusen PENG1, 2, Zhenhua HAN1, 2, Rongqian RUAN2, 3, Yijun SHEN2, 3
Mining and Metallurgical Engineering | 2025, 45(3) : 35 - 43
Less
收藏切换
Mining and Metallurgical Engineering | 2025, 45(3): 35-43
• MINING •
Feature Extraction and Flow Pattern Recognition of Gas-Liquid Two-Phase Flow Based on Improved Wavelet Thresholding
Full
Li CHEN1, 2, Yanlian DU1, 2, Fusen PENG1, 2, Zhenhua HAN1, 2, Rongqian RUAN2, 3, Yijun SHEN2, 3
Affiliations
  • 1.School of Information and Communication Engineering, Hainan University, Haikou 570100, Hainan, China
  • 2.State Key Laboratory of South China Sea Marine Resources Utilization, Hainan University, Haikou 570100, Hainan, China
  • 3.School of Marine Science and Engineering, Hainan University, Haikou 570100, Hainan, China
Published: 2025-06-01 doi: 10.3969/j.issn.0253-6099.2025.03.006
Outline
收藏切换

Wavelet analysis was performed for the collected pressure signals of gas-liquid two-phase flow in a vertical pipe in an air lift test. The optimal wavelet basis functions were determined by improving the signal-to-noise ratio (SNR). The range of decomposition levels was determined based on changes in energy of detail coefficients, and optimal decomposition levels were determined by the entropy weight method together with SNR, root mean square error and smoothness. After denoise with wavelet thresholding, three-level decomposition of signal was performed with the wavelet packet method, and then flow patterns were identified for gas-liquid two-phase flow with the energy ratio in the 1st and 2nd frequency bands and entropy values as feature vectors. The flow pattern recognition based on 389 sets of pressure signals shows that the extraction feature vector combined with random subspace decision tree can efficiently identify and classify gas-liquid two-phase flow patterns, and the overall mean recognition rate is up to 98.08% by adopting the improved wavelet thresholding.

marine engineering  /  air lift  /  gas-liquid two-phase flow  /  wavelet analysis  /  entropy weight method  /  thresholding  /  flow pattern recognition
Li CHEN, Yanlian DU, Fusen PENG, Zhenhua HAN, Rongqian RUAN, Yijun SHEN. Feature Extraction and Flow Pattern Recognition of Gas-Liquid Two-Phase Flow Based on Improved Wavelet Thresholding[J]. Mining and Metallurgical Engineering, 2025 , 45 (3) : 35 -43 . DOI: 10.3969/j.issn.0253-6099.2025.03.006
Appendix
Less
Year 2025 volume 45 Issue 3
PDF
63
29
Cite this Article
BibTeX
Article Info
doi: 10.3969/j.issn.0253-6099.2025.03.006
  • Receive Date：2024-12-23
  • Online Date：2026-03-19
  • Published：2025-06-01
Article Data
Affiliations
History
  • Received：2024-12-23
Funding
Affiliations
    1.School of Information and Communication Engineering, Hainan University, Haikou 570100, Hainan, China
    2.State Key Laboratory of South China Sea Marine Resources Utilization, Hainan University, Haikou 570100, Hainan, China
    3.School of Marine Science and Engineering, Hainan University, Haikou 570100, Hainan, China
References
Share
https://castjournals.cast.org.cn/joweb/kygczz/EN/10.3969/j.issn.0253-6099.2025.03.006
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62199257
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House