Loading [MathJax]/extensions/tex2jax.js

Prediction of rock fracture pressure in hydraulic fracturing with interpretable machine learning and mechanical specific energy theory

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Autorschaft

  • Xiaoying Zhuang
  • Yuhang Liu
  • Yuwen Hu
  • Hongwei Guo

Organisationseinheiten

Externe Organisationen

  • Tongji University
  • IMEC

Details

OriginalspracheEnglisch
Aufsatznummer100173
FachzeitschriftRock Mechanics Bulletin
Jahrgang4
Ausgabenummer2
Frühes Online-Datum30 Dez. 2024
PublikationsstatusVeröffentlicht - Apr. 2025

Abstract

Hydraulic fracturing stimulation technology is essential in the oil and gas industry. However, current techniques for predicting rock fracture pressure in hydraulic fracturing face significant challenges in precision and reliability. Traditional approaches often result in inadequate accuracy due to the complex and diverse nature of underground formations. However, recent advances in computational power and optimization techniques have enabled the application of machine learning in mining operations, resulting in improved prediction and feedback. In this study, various machine learning techniques are employed to predict hydraulic fracturing pressure based on the concept of mechanical specific energy. Additionally, the study interprets the models through feature importance analysis. The findings suggest that most machine learning models deliver highly accurate predictions. Feature importance analysis indicates that for an approximate assessment of fracture pressure, the characteristics of well depth and torque are sufficient. For more precise predictions, incorporating additional characteristics from the mechanical specific energy framework into the machine learning model is essential. The study emphasizes the feasibility of employing machine learning methods to predict fracture pressure and their usefulness in determining optimal engineering sites.

ASJC Scopus Sachgebiete

Zitieren

Prediction of rock fracture pressure in hydraulic fracturing with interpretable machine learning and mechanical specific energy theory. / Zhuang, Xiaoying; Liu, Yuhang; Hu, Yuwen et al.
in: Rock Mechanics Bulletin, Jahrgang 4, Nr. 2, 100173, 04.2025.

Publikation: Beitrag in FachzeitschriftArtikelForschungPeer-Review

Zhuang X, Liu Y, Hu Y, Guo H, Nguyen BH. Prediction of rock fracture pressure in hydraulic fracturing with interpretable machine learning and mechanical specific energy theory. Rock Mechanics Bulletin. 2025 Apr;4(2):100173. Epub 2024 Dez 30. doi: 10.1016/j.rockmb.2024.100173
Zhuang, Xiaoying ; Liu, Yuhang ; Hu, Yuwen et al. / Prediction of rock fracture pressure in hydraulic fracturing with interpretable machine learning and mechanical specific energy theory. in: Rock Mechanics Bulletin. 2025 ; Jahrgang 4, Nr. 2.
Download
@article{171f04204e984814b9a632c8eb32d55a,
title = "Prediction of rock fracture pressure in hydraulic fracturing with interpretable machine learning and mechanical specific energy theory",
abstract = "Hydraulic fracturing stimulation technology is essential in the oil and gas industry. However, current techniques for predicting rock fracture pressure in hydraulic fracturing face significant challenges in precision and reliability. Traditional approaches often result in inadequate accuracy due to the complex and diverse nature of underground formations. However, recent advances in computational power and optimization techniques have enabled the application of machine learning in mining operations, resulting in improved prediction and feedback. In this study, various machine learning techniques are employed to predict hydraulic fracturing pressure based on the concept of mechanical specific energy. Additionally, the study interprets the models through feature importance analysis. The findings suggest that most machine learning models deliver highly accurate predictions. Feature importance analysis indicates that for an approximate assessment of fracture pressure, the characteristics of well depth and torque are sufficient. For more precise predictions, incorporating additional characteristics from the mechanical specific energy framework into the machine learning model is essential. The study emphasizes the feasibility of employing machine learning methods to predict fracture pressure and their usefulness in determining optimal engineering sites.",
keywords = "Fracture pressure, Hydraulic fracturing, Interpretable machine learning, Mechanical specific energy, Nonlinear regression",
author = "Xiaoying Zhuang and Yuhang Liu and Yuwen Hu and Hongwei Guo and Nguyen, {Binh Huy}",
note = "Publisher Copyright: {\textcopyright} 2024 Chinese Society for Rock Mechanics & Engineering.",
year = "2025",
month = apr,
doi = "10.1016/j.rockmb.2024.100173",
language = "English",
volume = "4",
number = "2",

}

Download

TY - JOUR

T1 - Prediction of rock fracture pressure in hydraulic fracturing with interpretable machine learning and mechanical specific energy theory

AU - Zhuang, Xiaoying

AU - Liu, Yuhang

AU - Hu, Yuwen

AU - Guo, Hongwei

AU - Nguyen, Binh Huy

N1 - Publisher Copyright: © 2024 Chinese Society for Rock Mechanics & Engineering.

PY - 2025/4

Y1 - 2025/4

N2 - Hydraulic fracturing stimulation technology is essential in the oil and gas industry. However, current techniques for predicting rock fracture pressure in hydraulic fracturing face significant challenges in precision and reliability. Traditional approaches often result in inadequate accuracy due to the complex and diverse nature of underground formations. However, recent advances in computational power and optimization techniques have enabled the application of machine learning in mining operations, resulting in improved prediction and feedback. In this study, various machine learning techniques are employed to predict hydraulic fracturing pressure based on the concept of mechanical specific energy. Additionally, the study interprets the models through feature importance analysis. The findings suggest that most machine learning models deliver highly accurate predictions. Feature importance analysis indicates that for an approximate assessment of fracture pressure, the characteristics of well depth and torque are sufficient. For more precise predictions, incorporating additional characteristics from the mechanical specific energy framework into the machine learning model is essential. The study emphasizes the feasibility of employing machine learning methods to predict fracture pressure and their usefulness in determining optimal engineering sites.

AB - Hydraulic fracturing stimulation technology is essential in the oil and gas industry. However, current techniques for predicting rock fracture pressure in hydraulic fracturing face significant challenges in precision and reliability. Traditional approaches often result in inadequate accuracy due to the complex and diverse nature of underground formations. However, recent advances in computational power and optimization techniques have enabled the application of machine learning in mining operations, resulting in improved prediction and feedback. In this study, various machine learning techniques are employed to predict hydraulic fracturing pressure based on the concept of mechanical specific energy. Additionally, the study interprets the models through feature importance analysis. The findings suggest that most machine learning models deliver highly accurate predictions. Feature importance analysis indicates that for an approximate assessment of fracture pressure, the characteristics of well depth and torque are sufficient. For more precise predictions, incorporating additional characteristics from the mechanical specific energy framework into the machine learning model is essential. The study emphasizes the feasibility of employing machine learning methods to predict fracture pressure and their usefulness in determining optimal engineering sites.

KW - Fracture pressure

KW - Hydraulic fracturing

KW - Interpretable machine learning

KW - Mechanical specific energy

KW - Nonlinear regression

UR - http://www.scopus.com/inward/record.url?scp=105001014745&partnerID=8YFLogxK

U2 - 10.1016/j.rockmb.2024.100173

DO - 10.1016/j.rockmb.2024.100173

M3 - Article

AN - SCOPUS:105001014745

VL - 4

JO - Rock Mechanics Bulletin

JF - Rock Mechanics Bulletin

IS - 2

M1 - 100173

ER -