A Review of Intelligent Models for Gas Well Productivity Prediction and Production Optimization

Chenhao Tian; Yongxiang Huang; Shaonan Wang; Chenjun Li

doi:10.54691/6afsw816

Authors

Chenhao Tian
Yongxiang Huang
Shaonan Wang
Chenjun Li

DOI:

https://doi.org/10.54691/6afsw816

Keywords:

Gas Well Productivity Prediction; Production Allocation Model; Inter-Well Interference; Bottom-Hole Pressure; Intelligent Optimization.

Abstract

Natural gas, as a clean and efficient energy source, occupies an increasingly important position under the background of the "dual-carbon" strategy and energy structure transformation. However, affected by various complex factors such as reservoir heterogeneity, gas-liquid-solid multiphase flow, inter-well interference, and lack of bottom-hole pressure, traditional gas well productivity prediction and production allocation methods have problems such as insufficient accuracy, poor adaptability, and high dependence on manual work, making it difficult to meet the needs of efficient development of offshore and unconventional gas reservoirs. Therefore, to meet the requirements of accuracy, adaptability, and intelligence, this paper studies the intelligence of gas well productivity prediction and its production allocation model, analyzes and compares current machine learning algorithms such as XGBoost, Random Forest, Support Vector Machine (SVM), and Long Short-Term Memory Neural Network (LSTM) in gas well dynamic analysis, points out the existing problems in current research, and looks forward to the development trends of gas well productivity prediction and production allocation in the directions of multi-factor coupling, intelligent integration, and full-life-cycle dynamic optimization.

Downloads

Download data is not yet available.

References

[1] Zhang K, Zhao X G, Zhang L M, et al. Research status and prospect of big data and intelligent optimization theory and method in intelligent oilfield development[J]. Journal of China University of Petroleum (Edition of Natural Science), 2020, 44(04): 28-38.

[2] Yang J, Yi F Y, Chen W M. Research on horizontal well productivity grade prediction model based on transfer learning[J]. Inner Mongolia Petrochemical Industry, 2024, 50(08): 18-23.

[3] Li Z W. Research on oil and gas production analysis system based on digital oilfield[J]. Information System Engineering, 2019: 60.

[4] Wang X L, Liu H W. Research on gas well productivity prediction model based on random forest[J]. Data Mining and Applications, 2019, 36(11):14-19.

[5] Wang J L, Jia A L, Wei Y S, et al. Systematic optimization of fracturing parameters and well spacing based on multi-well model[J]. Petroleum Exploration and Development, 2019, 46(05): 981-992.

[6] Brown E, Smith J. Machine learning techniques for gas well productivity assessment and prediction: A case study[J]. Journal of Petroleum Science and Engineering, 2020, 186(1): 38-47.

[7] Ge L, Pu X Y. Application effect evaluation of intelligent production decision support system in shale gas field[J]. Oil & Gas Reservoir Evaluation and Development, 2021: 7.

[8] Shi D M, Dong C S. Construction conception of intelligent application analysis system for production operation in oil production plant[J]. Information System Engineering, 2021:17-18.

[9] Gu C Y, Xiong W X, Li Z K, et al. Research and application of intelligent management system for intermittent gas wells[J]. Petroleum and Chemical Equipment, 2022, 25(9): 62-65, 58. DOI: 10. 3969/ j.issn.1674-8980.2022.09.018.

[10] Zhao K, Chen M F, Wang Y W, et al. Production decline law and recoverable reserves prediction of TY water-bearing shale gas reservoirs[J]. Fault-Block Oil & Gas Field, 2024, 31(3): 395-402. DOI: 10. 6056/ dkyqt202403004.

[11] Zhang L. Research on dynamic reserve evaluation method of Y well block in Yan’an gas field[J], 2023, 7: 92-94.

[12] Luo J, Zhu S H. Comparison and evaluation of dynamic reserve calculation methods for DC structure[J], 2020, 34(1): 89-95.

[13] Wang Z L. Research on automatic reservoir history matching method based on 4D seismic data[D]. University of Chinese Academy of Sciences (Institute of Fluid Mechanics, Chinese Academy of Sciences), 2021.

[14] Huang B, Liu C Y, Tong B W, et al. An interference well test analysis method for characterizing high permeability channels in multilayer reservoirs[J/OL]. Chinese Journal of Computational Physics, 1-12 [2024-11-12].

[15] Wang Y, Wang Y H, Tang S L, et al. Productivity prediction of gas wells in eastern South China Sea based on GA-BP neural network[J]. Petrochemical Industry Application, 2024, 43(09): 61-64+68.

[16] Jia H M, Hu Q J, Zhang C, et al. Productivity prediction and drainage test of coalbed methane dual-layer commingled production vertical wells: A case study of southwestern Zhengzhuang in Qinshui Basin[J]. Oil & Gas Reservoir Evaluation and Development, 2022, 12(04): 657-665. DOI:10. 13809/ j. cnki.cn32-1825/te.2022.04.014.

[17] Wen H C. Analysis and prediction of main controlling factors of shale gas well productivity based on data mining[D]. Chongqing University of Science and Technology, 2023. DOI:10.27854/ d.cnki. gcqkj. 2023.000291.

[18] Hu H, Wang M, Long H, et al. A new method for rational production allocation of shale gas wells in full life cycle: A case study of Luzhou shale gas[J]. Complex Reservoirs, 2023(02):137-143.

[19] Li B. Seepage characteristics and productivity prediction of horizontal wells with volume fracturing in tight oil reservoirs[J]. Chemical Engineering Design Communications, 2023.