EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A Machine Learning-Driven Framework for Real-Time Lithology Identification and Drilling Parameter Optimization

Qingshan Liu, Dengyue Li, Shuo Liu, Hefeng Liang, Yuchen Zhou, Conghui Zhao, Kun Liu, Gang Hui, Feng Ni, Peng Du, Siwen Wang

Processes · 02.01.2026 · 14 (1) · 156

DOI: 10.3390/pr14010156 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Processes, online erschienen am 02.01.2026. Verfasst von Qingshan Liu und 10 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 51 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Key Core Technology Research Projects of China National Petroleum Corporation.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Conventional drilling parameter optimization, heavily reliant on lagging lithology data from periodic mud logging, suffers from significant delays between formation change detection and parameter adjustment. This latency often leads to reduced Rate of Penetration (ROP), accelerated tool wear, and increased risk of drilling complications. To address this, this work introduces a closed-loop machine learning framework for real-time lithology identification and autonomous parameter optimization. Its core is a hybrid deep learning model (1D-CNN-LSTM) that establishes a direct mapping from surface drilling parameters, Weight on Bit (WOB), Rotary Speed (RPM), Torque, ROP, to formation lithology, deliberately excluding dependency on expensive Logging-While-Drilling (LWD) tools to ensure cost-effective and broad applicability. Upon lithology change detection, the system retrieves the historically optimal Mechanical Specific Energy (MSE) value for the identified rock type and solves an inverse MSE model to compute optimal WOB and RPM setpoints within operational constraints. Field validation in a comparative trial demonstrated the framework’s efficacy: the test well achieved a 17.4% increase in ROP, a 37.8% reduction in Non-Productive Time, and an 87.5% decrease in stuck pipe incidents compared to an offset well drilled conventionally.

Förderung

  • Key Core Technology Research Projects of China National Petroleum Corporation

Zitieren

APA

Liu, Q., Li, D., Liu, S., Liang, H., Zhou, Y., Zhao, C., Liu, K., Hui, G., Ni, F., Du, P., & Wang, S. (2026). A Machine Learning-Driven Framework for Real-Time Lithology Identification and Drilling Parameter Optimization. Processes, 14(1), 156. https://doi.org/10.3390/pr14010156

Vancouver

Liu Q, Li D, Liu S, Liang H, Zhou Y, Zhao C, et al. A Machine Learning-Driven Framework for Real-Time Lithology Identification and Drilling Parameter Optimization. Processes. 2026;14(1):156. doi:10.3390/pr14010156

BibTeX
@article{Liu2026,
  author = {Liu, Qingshan and Li, Dengyue and Liu, Shuo and Liang, Hefeng and Zhou, Yuchen and Zhao, Conghui and Liu, Kun and Hui, Gang and Ni, Feng and Du, Peng and Wang, Siwen},
  title = {A Machine Learning-Driven Framework for Real-Time Lithology Identification and Drilling Parameter Optimization},
  journal = {Processes},
  year = {2026},
  volume = {14},
  number = {1},
  pages = {156},
  doi = {10.3390/pr14010156}
}
Kostenlos starten →