A physics and data dual-driven method for real-time fracturing pressure prediction
Wellhead pressure prediction is challenging due to problems such as drastic pressure fluctuations, numerous disturbing factors, and complex influencing mechanisms. Current research often adopts traditional physical models which find it difficult to capture multiple nonlinear changes and sudden fluct...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Petroleum Geology and Experiment
2024-11-01
|
| Series: | Shiyou shiyan dizhi |
| Subjects: | |
| Online Access: | https://www.sysydz.net/cn/article/doi/10.11781/sysydz2024061323 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846119459848192000 |
|---|---|
| author | Xiaodong HU Junyi LIU Tianyu WANG Fujian ZHOU Xutao LU Pukang YI Chao CHEN |
| author_facet | Xiaodong HU Junyi LIU Tianyu WANG Fujian ZHOU Xutao LU Pukang YI Chao CHEN |
| author_sort | Xiaodong HU |
| collection | DOAJ |
| description | Wellhead pressure prediction is challenging due to problems such as drastic pressure fluctuations, numerous disturbing factors, and complex influencing mechanisms. Current research often adopts traditional physical models which find it difficult to capture multiple nonlinear changes and sudden fluctuations due to the oversimplification of complex formation conditions, fracture characteristics, and fluid dynamics processes, limiting their prediction accuracy and real-time responsiveness in actual operations. Artificial intelligence (AI) models, despite their strong nonlinear fitting capabilities, often lack an in-depth understanding of the physical mechanisms underlying pressure fluctuations and are less sensitive to formation and operational parameters, resulting in poor stability and insufficient interpretability under extreme or dynamically changing conditions. To address these challenges, a physics and data dual-driven prediction method was proposed to predict future pressure trends. An intelligent model based on a long and short-term memory (LSTM) neural network was constructed, integrating the equilibrium height calculations of the proppant bed within the fracture and real-time pumping data at the wellsite as model inputs to predict pressure for the next 60 seconds. Then, combined with traditional wellhead pressure inversion method, wavelet transform was used to decompose predictions from both the intelligent and traditional models. The overall trend of the LSTM model and the characteristics of mutation point in the inverse pressure calculation (IPC) model were utilized to reconstruct the wellhead pressure prediction curves that could balance the overall trend and local fluctuations. Results showed that compared to pure LSTM model, the wavelet fusion model of IPC and LSTM reduced the root mean square error (RMSE) and mean absolute error (MAE) by 37.87% and 15.29%, respectively, in wellhead pressure prediction for the next 60 seconds. The fusion model can accurately capture fracturing pressure changes during field operations, providing more reliable guidance and decision support for field operations. |
| format | Article |
| id | doaj-art-21c9cc832985462893fa4080931c0a62 |
| institution | Kabale University |
| issn | 1001-6112 |
| language | zho |
| publishDate | 2024-11-01 |
| publisher | Editorial Office of Petroleum Geology and Experiment |
| record_format | Article |
| series | Shiyou shiyan dizhi |
| spelling | doaj-art-21c9cc832985462893fa4080931c0a622024-12-17T04:28:52ZzhoEditorial Office of Petroleum Geology and ExperimentShiyou shiyan dizhi1001-61122024-11-014661323133510.11781/sysydz2024061323sysydz-46-6-1323A physics and data dual-driven method for real-time fracturing pressure predictionXiaodong HU0Junyi LIU1Tianyu WANG2Fujian ZHOU3Xutao LU4Pukang YI5Chao CHEN6College of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, ChinaCollege of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, ChinaCollege of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, ChinaCollege of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, ChinaCollege of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, ChinaCollege of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, ChinaCollege of Artificial Intelligence, China University of Petroleum (Beijing), Beijing 102249, ChinaWellhead pressure prediction is challenging due to problems such as drastic pressure fluctuations, numerous disturbing factors, and complex influencing mechanisms. Current research often adopts traditional physical models which find it difficult to capture multiple nonlinear changes and sudden fluctuations due to the oversimplification of complex formation conditions, fracture characteristics, and fluid dynamics processes, limiting their prediction accuracy and real-time responsiveness in actual operations. Artificial intelligence (AI) models, despite their strong nonlinear fitting capabilities, often lack an in-depth understanding of the physical mechanisms underlying pressure fluctuations and are less sensitive to formation and operational parameters, resulting in poor stability and insufficient interpretability under extreme or dynamically changing conditions. To address these challenges, a physics and data dual-driven prediction method was proposed to predict future pressure trends. An intelligent model based on a long and short-term memory (LSTM) neural network was constructed, integrating the equilibrium height calculations of the proppant bed within the fracture and real-time pumping data at the wellsite as model inputs to predict pressure for the next 60 seconds. Then, combined with traditional wellhead pressure inversion method, wavelet transform was used to decompose predictions from both the intelligent and traditional models. The overall trend of the LSTM model and the characteristics of mutation point in the inverse pressure calculation (IPC) model were utilized to reconstruct the wellhead pressure prediction curves that could balance the overall trend and local fluctuations. Results showed that compared to pure LSTM model, the wavelet fusion model of IPC and LSTM reduced the root mean square error (RMSE) and mean absolute error (MAE) by 37.87% and 15.29%, respectively, in wellhead pressure prediction for the next 60 seconds. The fusion model can accurately capture fracturing pressure changes during field operations, providing more reliable guidance and decision support for field operations.https://www.sysydz.net/cn/article/doi/10.11781/sysydz2024061323fracturing pressure predictionphysics and data dual drivenlstmipcwavelet transformfusion model |
| spellingShingle | Xiaodong HU Junyi LIU Tianyu WANG Fujian ZHOU Xutao LU Pukang YI Chao CHEN A physics and data dual-driven method for real-time fracturing pressure prediction Shiyou shiyan dizhi fracturing pressure prediction physics and data dual driven lstm ipc wavelet transform fusion model |
| title | A physics and data dual-driven method for real-time fracturing pressure prediction |
| title_full | A physics and data dual-driven method for real-time fracturing pressure prediction |
| title_fullStr | A physics and data dual-driven method for real-time fracturing pressure prediction |
| title_full_unstemmed | A physics and data dual-driven method for real-time fracturing pressure prediction |
| title_short | A physics and data dual-driven method for real-time fracturing pressure prediction |
| title_sort | physics and data dual driven method for real time fracturing pressure prediction |
| topic | fracturing pressure prediction physics and data dual driven lstm ipc wavelet transform fusion model |
| url | https://www.sysydz.net/cn/article/doi/10.11781/sysydz2024061323 |
| work_keys_str_mv | AT xiaodonghu aphysicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT junyiliu aphysicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT tianyuwang aphysicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT fujianzhou aphysicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT xutaolu aphysicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT pukangyi aphysicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT chaochen aphysicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT xiaodonghu physicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT junyiliu physicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT tianyuwang physicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT fujianzhou physicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT xutaolu physicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT pukangyi physicsanddatadualdrivenmethodforrealtimefracturingpressureprediction AT chaochen physicsanddatadualdrivenmethodforrealtimefracturingpressureprediction |