Prediction of Breakdown Pressure Using a Multi-Layer Neural Network Based on Supercritical CO<sub>2</sub> Fracturing Data
Hydraulic fracturing is a widely employed technique for stimulating unconventional shale gas reservoirs. Supercritical CO<sub>2</sub> (SC-CO<sub>2</sub>) has emerged as a promising fracturing fluid due to its unique physicochemical properties. Existing theoretical models for...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-11-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/14/22/10545 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850217257175613440 |
|---|---|
| author | Xiufeng Zhang Min Zhang Shuyuan Liu Heyang Liu |
| author_facet | Xiufeng Zhang Min Zhang Shuyuan Liu Heyang Liu |
| author_sort | Xiufeng Zhang |
| collection | DOAJ |
| description | Hydraulic fracturing is a widely employed technique for stimulating unconventional shale gas reservoirs. Supercritical CO<sub>2</sub> (SC-CO<sub>2</sub>) has emerged as a promising fracturing fluid due to its unique physicochemical properties. Existing theoretical models for calculating breakdown pressure often fail to accurately predict the outcomes of SC-CO<sub>2</sub> fracturing due to the complex, nonlinear interactions among multiple influencing factors. In this study, we conducted fracturing experiments considering parameters such as fluid type, flow rate, temperature, and confining pressure. A fully connected neural network was then employed to predict breakdown pressure, integrating both our experimental data and published datasets. This approach facilitated the identification of key influencing factors and allowed us to quantify their relative importance. The results demonstrate that SC-CO<sub>2</sub> significantly reduces breakdown pressure compared to traditional water-based fluids. Additionally, breakdown pressure increases with higher confining pressures and elevated flow rates, while it decreases with increasing temperatures. The multi-layer neural network achieved high predictive accuracy, with R, RMSE, and MAE values of 0.9482 (0.9123), 3.424 (4.421), and 2.283 (3.188) for training (testing) sets, respectively. Sensitivity analysis identified fracturing fluid type and tensile strength as the most influential factors, contributing 28.31% and 21.39%, respectively, followed by flow rate at 12.34%. Our findings provide valuable insights into the optimization of fracturing parameters, offering a promising approach to better predict breakdown pressure in SC-CO<sub>2</sub> fracturing operations. |
| format | Article |
| id | doaj-art-ba341f633d994801809aab7b8cf8c2bf |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-ba341f633d994801809aab7b8cf8c2bf2025-08-20T02:08:07ZengMDPI AGApplied Sciences2076-34172024-11-0114221054510.3390/app142210545Prediction of Breakdown Pressure Using a Multi-Layer Neural Network Based on Supercritical CO<sub>2</sub> Fracturing DataXiufeng Zhang0Min Zhang1Shuyuan Liu2Heyang Liu3Department of Geotechnical Engineering, Tongji University, Shanghai 200092, ChinaGeotechnical Institute, TU Bergakademie Freiberg, 09599 Freiberg, GermanySchool of Resource and Civil Engineering, Northeastern University, Shenyang 110819, ChinaSchool of Resource and Civil Engineering, Northeastern University, Shenyang 110819, ChinaHydraulic fracturing is a widely employed technique for stimulating unconventional shale gas reservoirs. Supercritical CO<sub>2</sub> (SC-CO<sub>2</sub>) has emerged as a promising fracturing fluid due to its unique physicochemical properties. Existing theoretical models for calculating breakdown pressure often fail to accurately predict the outcomes of SC-CO<sub>2</sub> fracturing due to the complex, nonlinear interactions among multiple influencing factors. In this study, we conducted fracturing experiments considering parameters such as fluid type, flow rate, temperature, and confining pressure. A fully connected neural network was then employed to predict breakdown pressure, integrating both our experimental data and published datasets. This approach facilitated the identification of key influencing factors and allowed us to quantify their relative importance. The results demonstrate that SC-CO<sub>2</sub> significantly reduces breakdown pressure compared to traditional water-based fluids. Additionally, breakdown pressure increases with higher confining pressures and elevated flow rates, while it decreases with increasing temperatures. The multi-layer neural network achieved high predictive accuracy, with R, RMSE, and MAE values of 0.9482 (0.9123), 3.424 (4.421), and 2.283 (3.188) for training (testing) sets, respectively. Sensitivity analysis identified fracturing fluid type and tensile strength as the most influential factors, contributing 28.31% and 21.39%, respectively, followed by flow rate at 12.34%. Our findings provide valuable insights into the optimization of fracturing parameters, offering a promising approach to better predict breakdown pressure in SC-CO<sub>2</sub> fracturing operations.https://www.mdpi.com/2076-3417/14/22/10545supercritical CO<sub>2</sub>hydraulic fracturingbreakdown pressure predictionmulti-layer neural networklaboratory data |
| spellingShingle | Xiufeng Zhang Min Zhang Shuyuan Liu Heyang Liu Prediction of Breakdown Pressure Using a Multi-Layer Neural Network Based on Supercritical CO<sub>2</sub> Fracturing Data Applied Sciences supercritical CO<sub>2</sub> hydraulic fracturing breakdown pressure prediction multi-layer neural network laboratory data |
| title | Prediction of Breakdown Pressure Using a Multi-Layer Neural Network Based on Supercritical CO<sub>2</sub> Fracturing Data |
| title_full | Prediction of Breakdown Pressure Using a Multi-Layer Neural Network Based on Supercritical CO<sub>2</sub> Fracturing Data |
| title_fullStr | Prediction of Breakdown Pressure Using a Multi-Layer Neural Network Based on Supercritical CO<sub>2</sub> Fracturing Data |
| title_full_unstemmed | Prediction of Breakdown Pressure Using a Multi-Layer Neural Network Based on Supercritical CO<sub>2</sub> Fracturing Data |
| title_short | Prediction of Breakdown Pressure Using a Multi-Layer Neural Network Based on Supercritical CO<sub>2</sub> Fracturing Data |
| title_sort | prediction of breakdown pressure using a multi layer neural network based on supercritical co sub 2 sub fracturing data |
| topic | supercritical CO<sub>2</sub> hydraulic fracturing breakdown pressure prediction multi-layer neural network laboratory data |
| url | https://www.mdpi.com/2076-3417/14/22/10545 |
| work_keys_str_mv | AT xiufengzhang predictionofbreakdownpressureusingamultilayerneuralnetworkbasedonsupercriticalcosub2subfracturingdata AT minzhang predictionofbreakdownpressureusingamultilayerneuralnetworkbasedonsupercriticalcosub2subfracturingdata AT shuyuanliu predictionofbreakdownpressureusingamultilayerneuralnetworkbasedonsupercriticalcosub2subfracturingdata AT heyangliu predictionofbreakdownpressureusingamultilayerneuralnetworkbasedonsupercriticalcosub2subfracturingdata |