ORIGINAL RESEARCH article
Front. Earth Sci.
Sec. Georeservoirs
Volume 13 - 2025 | doi: 10.3389/feart.2025.1658142
Research on Intelligent Fracturing Parameter Optimization Method Based on Deep Learning and Construction Curve Feature Extraction
Provisionally accepted
- 1Petrochina Tarim Oilfield Company, Korla, China
- 2China University of Petroleum, Qingdao, China
Select one of your emails
You have multiple emails registered with Frontiers:
Notify me on publication
Please enter your email address:
If you already have an account, please login
You don't have a Frontiers account ? You can register here
As the development of unconventional oil and gas resources continues, fracturing technology has become a crucial method for enhancing reservoir productivity. However, optimizing fracturing parameters and identifying the key factors that control productivity, along with understanding their mechanisms, remain significant challenges. This paper proposes a novel approach that combines construction curve feature extraction with a hybrid optimization model to improve the effectiveness of fracturing parameter optimization. Initially, key features closely related to productivity were extracted from construction curves, and a comprehensive correlation coefficient method was employed to identify the primary factors influencing open flow capacity. Subsequently, the SSA-BP (Salp Swarm Algorithm-Back Propagation) hybrid optimization model was used to model these selected features, and a genetic algorithm was applied for systematic optimization of fracturing parameters. To validate the proposed method, a field application test was conducted on Well A-X in the A Gas Field of the Tarim Basin. Following the initial fracturing operation, adjustments to the fracturing parameters were made based on feedback from the model, and a refracturing operation was performed. The results indicated a significant increase in daily gas production and a substantial improvement in open flow capacity for Well A-X, confirming the effectiveness and practical value of the proposed method in enhancing post-fracturing productivity. This study contributes a novel framework integrating feature extraction and hybrid optimization, offering a flexible tool for parameter design in low-permeability gas reservoirs.
Keywords: Fracturing optimization, Construction Curve Feature Extraction, deep learning, Hybrid optimization model, Open flow capacity
Received: 02 Jul 2025; Accepted: 10 Sep 2025.
Copyright: © 2025 Qiao, Ren, Liu, Wang, Peng, Zhong, Peng, Feng and Huang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
* Correspondence: Chengwen Wang, China University of Petroleum, Qingdao, China
Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.