EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

AUKF-PINN: An adaptive framework for low-energy gamma multiphase flow measurement under noisy industrial conditions

Yibo Huang, Haibo Liang, Liang Zhu, Linhan He, Ting Zeng, Mingyang Liu iD

PLOS One · 04.08.2026 · 21 (8) · e0355203

DOI: 10.1371/journal.pone.0355203 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 04.08.2026. Verfasst von Yibo Huang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Southwest Petroleum University, Chengdu, China. Hauptthemen laut MEDLINE: Algorithms, Neural Networks, Computer, Industry. Die Arbeit nennt 45 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Key Technology Research and Development Project.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Measuring multiphase flow at drilling sites presents numerous challenges, including detector window adhesion, electromagnetic interference, and temperature drift. These factors significantly increase measurement errors when traditional low-energy gamma flowmeters are directly applied in field conditions. To address this problem, this paper proposes an adaptive unscented Kalman filter and physics-informed neural network fusion algorithm (AUKF-PINN) for real-time and accurate measurement of gas-liquid-solid three-phase flow. This algorithm constructs a four-dimensional extended state space model, which includes the linear mass of the gas phase, liquid phase, solid phase, and the thickness of the adhered layer, achieving joint estimation of physical states and interference states; this model precisely handles the exponential nonlinearity of the Beer-Lambert law using unscented Kalman filtering, avoiding linearization errors; and introduces a lightweight physics-informed neural network to learn the dynamic and noise evolution laws of the adhered layer, ensuring that the network output conforms to basic physical laws; furthermore, an adaptive noise fusion strategy based on innovation matching is designed, combining the physical prior of PINN and the Sage-Husa statistical estimation, to ensure that the filter is always in the optimal gain state. Experimental results based on on-site data from the drilling platform show that AUKF-PINN performs extremely well in predicting the fraction ratio of phases and provides an effective physical information-enhanced filtering example for multiphase flow measurement in complex environments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

AlgorithmsNeural Networks, ComputerIndustryAdaptive AlgorithmsModels, TheoreticalSoft Computing

Autor:innen und Institutionen

  • Southwest Petroleum University, Chengdu, China.
  • China National Petroleum Corporation's Chuanqing Drilling International Engineering Company, Chengdu, China.
  • China National Petroleum Corporation Tarim Branch Oilfield Oil and Gas Marketing Division, Korla, China.
  • Sichuan Northeast Gas Mine of Southwest Oil and Gas Field Branch of China National Petroleum Corporation, Chengdu, China.

ORCID-Profile: Mingyang Liu

Förderung

  • National Key Technology Research and Development Project

Zitieren

APA

Huang, Y., Liang, H., Zhu, L., He, L., Zeng, T., & Liu, M. (2026). AUKF-PINN: An adaptive framework for low-energy gamma multiphase flow measurement under noisy industrial conditions. PLOS One, 21(8), e0355203. https://doi.org/10.1371/journal.pone.0355203

Vancouver

Huang Y, Liang H, Zhu L, He L, Zeng T, Liu M. AUKF-PINN: An adaptive framework for low-energy gamma multiphase flow measurement under noisy industrial conditions. PLOS One. 2026;21(8):e0355203. doi:10.1371/journal.pone.0355203

BibTeX
@article{Huang2026,
  author = {Huang, Yibo and Liang, Haibo and Zhu, Liang and He, Linhan and Zeng, Ting and Liu, Mingyang},
  title = {AUKF-PINN: An adaptive framework for low-energy gamma multiphase flow measurement under noisy industrial conditions},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {8},
  pages = {e0355203},
  doi = {10.1371/journal.pone.0355203}
}
Kostenlos starten →