Driven by the global carbon neutral policy, natural gas, especially shale gas, has gradually become an important part of the energy structure transformation due to its abundant reserves and low carbon emission characteristics. Intermittent production of shale gas is a strategy to restore formation pressure through periodic shut-in and opening-in operations. However, production forecasting is challenging due to the volatility and discontinuity of production data. Using production data from 17 typical intermittently producing shale gas wells in a gas field in Changning shale gas field, a unified feature set was constructed through feature extraction, and the GA-BP algorithm was applied to improve prediction accuracy. Through feature extraction, a unified feature set was constructed, and GA-BP algorithm was used to improve the prediction accuracy. The experimental results show that the model has high accuracy and stability in predicting the maximum pressure, maximum flow, average pressure and average daily output. This study provides scientific basis for optimizing production management and prolonging production life of shale gas wells.
WU Kun-yi, WANG Feng, ZHOU Jun, QIN Can, LUO Yan-li, ZHANG Chen-qian.
Data-driven Methodology in Production Forecasting for Intermittent Shale Gas Wells[J].
Science Technology and Engineering, 2026, 26(2): 597-606 DOI:10.12404/j.issn.1671-1815.2500967
ZhangYinghong. Thoughts and suggestions on several issues of energy structure transformation[J]. International Petroleum Econo-mics, 2021, 29(2): 1-15.
QiuLei, ZhangHanwen, XuChenyu, et al. Shale gas production prediction model based on deeplearning[J]. Contemporary Chemical Industry, 2024, 53(11): 2713-2719.
ZhuQikang, LinBotao, YangGuang, et al. Intelligent production optimization method for low-pressure and low-yield shale gaswells[J]. Petroleum Exploration and Development, 2022, 49(4): 770-777.
TianXianglei, JiangHaiyan, YueYanru, et al. Research on production law of gas lift drainage and gas production[J]. Fault-Block Oil and Gas Field, 2012, 19(6): 760-763.
TangYawan. Production characteristics and productivity influencing factors in shale gas development adjust mentarea[J]. Journal of Jianghan Petroleum University of Staff and Workers, 2023, 36(3): 8-10, 16.
ZhouShangwen, WangHongyan, LiuHao, et al. Calculation method of shale gas loss based on Arps production decline model[J]. Natural Gas Geoscience, 2019, 30(1): 102-110.
[15]
虞绍永, 姚军. 非常规气藏工程[M]. 北京: 石油工业出版社, 2013.
[16]
YuShaoyong, YaoJun. Unconventional gas reservoir engineering[M]. Beijing: Petroleum Industry Press, 2013.
[17]
DuongA N. An unconventional rate decline approach for tight and fracture-dominated gas wells[C]// SPE Canada Unconventional Resources Conference. Calgary: SPE, 2010.DOI: 10.2118/137748-MS.
[18]
WangK, LiH, WangJ, et al. Predicting production and estimated ultimate recoveries for shale gas wells: a new methodology approach[J]. Applied Energy, 2017, 206: 1416-1431.
[19]
GouL, YangZ, MinC, et al. A novel domain adaptation method with physical constraints for shale gas production forecasting[J]. Applied Energy, 2024, 371.DOI: 10.1016/j.apenergy.2024.123673.
[20]
ZhouW, LiX, QiZ L, et al. A shale gas production prediction model based on masked convolutional neural network[J]. Applied Energy, 2024, 353.DOI: 10.1016/j.apenergy.2023.122092.
XuBingxiang, BaiYuhu, ChenLing, et al. Optimization scheme of shale gas production prediction technology based on analytical model[J]. Science Technology and Engineering, 2021, 21(9): 3571-3575.
HeYouwei, HeZhiyue, TangYong, et al. Production evaluation and prediction of shale gas wells based on machine learning[J]. Oil Drilling & Production Technology, 2021, 43(4): 518-524.
KongPeng, LiZhongcheng, YangChenxi, et al. Research on post-fracturing production prediction of coalbed methane wells based on PCA-NB method[J]. Special Oil and Gas Reservoirs, 2019, 26(6): 108-112.
HanShan, CheMingguang, SuWang, et al. Single well production prediction method and application of shale gas in Weiyuan Block of Sichuan Basin[J]. Special Oil and Gas Reservoirs, 2022, 29(6): 141-149.
[29]
FargallaM A M, YanW, DengJ, et al. TimeNet: Time2Vec attention-based CNN-BiGRU neural network for predicting production in shale and sandstone gas reservoirs[J]. Energy, 2024, 290.DOI: 10.1016/j.energy.2023.130184.
FuYuqi, WangYang, WuSiqiao, et al. Shale gas well production prediction based on CNN-LSTM-ATT network[J]. Natural Gas Technology and Economy, 2024, 18(2): 32-38.
HanKening, WangWei, FanDongyan, et al. Production prediction of normal pressure shale gas wells based on coupling of production decline and LSTM[J]. Reservoir Evaluation and Development, 2023, 13(5): 647-656.
ChenJuan, HuangHaoyong, LiuJunchen, et al. Productivity prediction technology of shale gas horizontal wells in Changning area based on GA-BP neural network[J]. Science Technology and Engineering, 2020, 20(5): 1851-1858.
YangLi, ZhouZixi, WangTingting, et al. Single well production prediction method based on CNN-GRU-LightGBM model[J]. Science Technology and Engineering, 2024, 24(18): 7606-7614.
KongRundong. Fine management of shale gas wells throughout their lifecycle[J]. China Petroleum and Chemical Standard and Quality, 2023, 43(16): 85-88, 94.
ZhangTao, LiXiangfang, YangLifeng, et al. Brief discussion on the influence of shut-in timing on flowback rate and productivity of shale gaswells[J]. Natural Gas Industry, 2017, 37(8): 48-60.
ZhongHaiquan, ZhengChuangen, XuDiyu, et al. Development of intelligent system for intermittent production gas well network[J]. Science Technology and Engineering, 2021, 21(35): 15019-15026.