致密油藏压裂水平井产量预测

doi:10.7657/XJPG20220510

摘要/Abstract

摘要：

针对致密油藏压裂水平井流态复杂及全生命周期产量预测误差大的问题,在对前人经验递减模型适用性研究的基础上,选取以不稳定流和过渡流为主导的产量指数递减（SEPD）模型及以边界控制流为主导的指数模型进行组合,通过结合节点处的产量相等和递减率相等,构建了以边界控制流时间为节点的全生命周期新型分段产量预测模型,同时建立了广义回归神经网络算法下的边界控制流时间预测方法及分段函数的最小二乘法拟合参数求取方法。结果表明,不论是否到达边界控制流,新模型普遍比单一SEPD模型和指数模型的拟合度高,其预测结果更接近于生产后期的指数评估结果,误差小于5%。

关键词: 致密油藏, 压裂, 水平井, 全生命周期, 边界控制流, 广义回归, 神经网络, 产量预测

Abstract:

Regarding complex flow regime and large error in lifecycle production prediction for fractured horizontal wells in tight oil reservoirs, the stretched exponential production decline (SEPD) model dominated by transient flow and transitional flow and the exponential model dominated by boundary-dominated flow (BDF) were selected and combined based on the research on the adaptability of empirical production decline model proposed in previous studies. Given equal production and equal decline rate at nodes, a new lifecycle segmented production prediction model with BDF time as node was constructed. Furthermore, the methods for predicting BDF time based on the generalized regression neural network algorithm and for determining the parameters of piecewise function by least square fitting were established. The results show that, whether the BDF is attained, the new model realizes a better fitting than the SEPD or exponential model, and its prediction results are closer to the exponential evaluation results in the late stage of production with an error of less than 5%.

Key words: tight oil reservoir, fracturing, horizontal well, lifecycle, boundary-dominated flow, generalized regression, neural network, production prediction

中图分类号:

TE328

宋俊强, 李晓山, 王硕, 顾开放, 潘虹, 王鑫. 致密油藏压裂水平井产量预测[J]. 新疆石油地质, 2022, 43(5): 580-586.

SONG Junqiang, LI Xiaoshan, WANG Shuo, GU Kaifang, PAN Hong, WANG Xin. Production Prediction of Fractured Horizontal Wells in Tight Oil Reservoirs[J]. Xinjiang Petroleum Geology, 2022, 43(5): 580-586.

图/表 6

图1

图2

表1

图3

图4

表2

参考文献 21

[1]	罗皓. 基于递减率模型的产量递减规律研究[D]. 成都: 西南石油大学, 2019.
	LUO Hao. Research on rate decline curve based on decline rate model[D]. Chengdu: Southwest Petroleum University, 2019.
[2]	陈元千, 徐佳倩, 傅礼兵. 预测页岩气井产量和可采储量泛指数递减模型的建立及应用[J]. 油气地质与采收率, 2021, 28(1):132-136.
	CHEN Yuanqian, XU Jiaqian, FU Libing. Establishment and application of pan exponential decline model for forecasting production rate and recoverable reserves of shale gas wells[J]. Petroleum Geology and Recovery Efficiency, 2021, 28(1):132-136.
[3]	闫怡. 致密油藏水平井体积压裂产量递减研究[D]. 山东青岛: 中国石油大学(华东), 2017.
	YAN Yi. Production decline analysis on volumetric fractured horizontal wells in tight reservoir[D]. Qingdao,Shandong: China University of Petroleum(East China), 2017.
[4]	李铁宁. 基于动态神经网络的油田开发数据分析和预测模型研究[D]. 黑龙江大庆: 东北石油大学, 2016.
	LI Tiening. Research on analysis and prediction model of oilfield development data based on dynamic neural network[D]. Daqing,Heilongjiang: Northeast Petroleum University, 2016.
[5]	梁卫卫, 党海龙, 崔鹏兴, 等. 三维地质建模技术在致密砂岩油藏水平井开发中的应用. 新疆石油地质, 2020, 41(5):616-621.
	LIANG Weiwei, DANG Hailong, CUI Pengxing, et al. Application of 3D geological modeling in horizontal well development of tight sandstone oil reservoirs[J]. Xinjiang Petroleum Geology, 2020, 41(5):616-621.
[6]	吴昊镪, 彭小龙, 朱苏阳, 等. 砾岩油藏弓形井多级水平缝压裂聚驱采收率数值模拟[J]. 新疆石油地质, 2022, 43(1):85-91.
	WU Haoqiang, PENG Xiaolong, ZHU Suyang, et al. Numerical simulation on polymer flooding recovery of conglomerate reservoirs:horizontal fractures in arched wells after multi-stage fraturing[J]. Xinjiang Petroleum Geology, 2022, 43(1):85-91.
[7]	姜瑞忠, 刘秀伟, 崔永正, 等. 非稳态窜流多段压裂水平井井底压力分析[J]. 油气地质与采收率, 2019, 26(5):86-95.
	JIANG Ruizhong, LIU Xiuwei, CUI Yongzheng, et al. Bottomhole pressure analysis of multistage fractured horizontal well during unsteady crossflow[J]. Petroleum Geology and Recovery Efficiency, 2019, 26(5):86-95.
[8]	周明德. 致密油藏体积压裂井生产动态分析[D]. 黑龙江大庆: 东北石油大学, 2020.
	ZHOU Mingde. Production transient analysis of volume fracturing wells in tight reservoirs[D]. Daqing,Heilongjiang: Northeast Petroleum University, 2020.
[9]	刘传斌, 姜汉桥, 李俊键, 等. 页岩气产量递减变化组合模型的探讨[J]. 断块油气田, 2015, 22(6):770-772.
	LIU Chuanbin, JIANG Hanqiao, LI Junjian, et al. Discussion on combination model of shale gas production decline[J]. Fault-Block Oil & Gas Field, 2015, 22(6):770-772.
[10]	王怒涛, 陈仲良, 祝明谦, 等. 页岩气压裂水平井产量递减组合模型分析[J]. 大庆石油地质与开发, 2018, 37(5):135-140.
	WANG Nutao, CHEN Zhongliang, ZHU Mingqian, et al. Analysis of the combination model for the production decline of the shale-gas fractured horizontal well[J]. Petroleum Geology & Oilfield Development in Daqing, 2018, 37(5):135-140.
[11]	周芸, 周福建, 冯连勇. 一种新型油气产量预测模型[J]. 大庆石油地质与开发, 2018, 37(5):76-80.
	ZHOU Yun, ZHOU Fujian, FENG Lianyong. A new model for predicting oil and gas production[J]. Petroleum Geology & Oilfield Development in Daqing, 2018, 37(5):76-80.
[12]	ARPS J J. Analysis of decline curves[J]. AIME, 1945, 149(2):228-247.
[13]	陈元千, 徐佳倩, 傅礼兵, 等. 对SEPD模型和YM-SEPD方法的评论及PEPD模型的建立与应用[J]. 断块油气田, 2020, 27(6):766-769.
	CHEN Yuanqian, XU Jiaqiang, FU Libing, et al. Review for SEPD model and YM-SEPD method,as well as establishment and application of PEPD model[J]. Fault-Block Oil & Gas Field, 2020, 27(6):766-769.
[14]	MANDA P, NKAZI, D B. The evaluation and sensitivity of decline curve modelling[J]. Energies, 2020, 13:2 765. doi: 10.3390/en13112765
[15]	SEIDLE J P, O’CONNER L S. Estimation of unconventional well recoveries and economics from transient flow data[R]. SPE 179983-MS, 2016.
[16]	LUO Hongwen, LI Haitao, ZHANG Jianfeng, et al. Production performance analysis of fractured horizontal well in tight oil reservoir[J]. Journal of Petroleum Exploration and Production Technology, 2018, 8:229-247. doi: 10.1007/s13202-017-0339-x
[17]	张凤远. 致密气田产量递减规律分析方法研究及应用[D]. 北京: 中国石油大学(北京), 2017.
	ZHANG Fengyuan. Research on production decline analysis methods and the application in tight gas field[D]. Beijing: China University of Petroleum(Beijing), 2017.
[18]	BOWDEN G J, NIXON J B, DANDY G C, et al. Forecasting chlorine residuals in a water distribution system using a general regression neural network[J]. Mathematical Computer Modelling, 2006, 44(5):469-484. doi: 10.1016/j.mcm.2006.01.006
[19]	王国昌, 吕学菊. 用广义回归神经网络和遗传算法分析产量递减[J]. 新疆石油地质, 2006, 27(1):90-93.
	WANG Guochang, LV Xueju. Application of generalized regression neural network and genetic algorithm to production decline analaysis[J]. Xinjiang Petroleum Geology, 2006, 27(1):90-93.
[20]	姚宏, 于七龙, 那琳. 基于粒子群优化算法-广义回归神经网络的磷化膜耐蚀性预测模型[J]. 电镀与精饰, 2021, 43(11):1-6.
	YAO Hong, YU Qilong, NA Lin. Prediction model of phosphating film corrosion resistance based on particle swarm optimization algorithm-generalized regression neural network[J]. Plating and Finishing, 2021, 43(11):1-6.
[21]	杨雅萍, 张文莲, 孙晓云. 基于改进蝙蝠算法优化广义回归神经网络的岩质边坡稳定性预测[J]. 科学技术与工程, 2021, 21(20):8 719-8 726.
	YANG Yaping, ZHANG Wenlian, SUN Xiaoyun. Stability prediction of rock slope based on improved bat algorithm-generalized regression neural network[J]. Science Technology and Engineering, 2021, 21(20):8 719-8 726.