Optimization of Hydraulic Fracturing Parameters and Prediction of Gas Extraction Efficiency in Stratified Coal Seams based on Deep Learning

DOI

10.2991/978-94-6463-780-9_53How to use a DOI?

Keywords

Optimization of hydraulic fracturing parameters; Stratified coal seams; Self-attention mechanism; Graph neural network

Abstract

In recent years, as the burial depth of coal seams continues to increase, and the parallel mining and gas treatment needs a similar treatment, how to effectively optimize hydraulic fracturing parameters and accurately predict the gas extraction efficiency of stratified coal seams has become an important challenge for coal mine safety production. It was proposed a multi-stage deep learning model based on self-attention mechanism and Graph Neural Network (GNN) to achieve adaptive optimization of fracturing parameters and high-precision gas extraction efficiency prediction intermediate source while exploiting existing deep learning and numerical simulation techniques. More engineering stimulus—multi-scale features of stratum geology and construction parameters extraction, as well as global correlation capture by the self-attention module. After that, GNN was defined to characterize the topological structure and the interaction information between the stratified coal bodies and multiple well sites, and to integrate spatial relationships into the modeling of fracturing and pumping processes, thus building a multi-task learning framework suitable for complex geological conditions. The experimental results indicate that the proposed multi-stage deep network performs much better than traditional numerical simulation and a single deep learning model on the optimization of the parameters.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Heng Zhang
AU  - Lin Hong
AU  - Xueyuan Zhao
AU  - Lican Liu
AU  - Bo Chen
PY  - 2025
DA  - 2025/07/03
TI  - Optimization of Hydraulic Fracturing Parameters and Prediction of Gas Extraction Efficiency in Stratified Coal Seams based on Deep Learning
BT  - Proceedings of the 2025 International Conference on Engineering Management and Safety Engineering (EMSE 2025)
PB  - Atlantis Press
SP  - 572
EP  - 579
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-780-9_53
DO  - 10.2991/978-94-6463-780-9_53
ID  - Zhang2025
ER  -