鉴于现有的预测钻井周期的方法忽视了影响钻井周期的关键因素因而精确度有限,提出采用多变量概率法预测钻井周期,并采用实测数据进行了算例分析和验证。利用自适应核密度估计法建立了各主要钻井阶段与深度相关的钻井周期概率模型,结合蒙特卡洛模拟得出了一次完整钻井施工作业的总周期的概率分布。采用该方法对澳大利亚及亚洲地区192口井的钻井周期进行了预测。尽管现有数据记录不全,但经过统计分析发现,模型模拟结果与实测数据的匹配度很高。研究表明,在10%~90%的置信区间内,总钻井周期比无事故钻井周期延长至少4 d,至多12 d。采用该方法可以得到钻至一定深度的可能的施工周期,有利于评价整个钻井施工过程的风险,模拟数据还可以用于机器学习模型的训练。 图10 表2 参34
LUU Quang Hung
,
LAU Man Fai
,
NG Sebastian P.H.
,
TING Clement P.W.
,
WEE Reuben
,
THEN Patrick H.H.
. 基于多变量概率模型的钻井周期预测方法[J]. 石油勘探与开发, 2021
, 48(4)
: 851
-860
.
DOI: 10.11698/PED.2021.04.18
Current univariate approach to predict the probability of well construction time has limited accuracy due to the fact that it ignores key factors affecting the time. In this study, we propose a multivariate probabilistic approach to predict the risks of well construction time. It takes advantage of an extended multi-dimensional Bernacchia-Pigolotti kernel density estimation technique and combines probability distributions by means of Monte-Carlo simulations to establish a depth-dependent probabilistic model. This method is applied to predict the durations of drilling phases of 192 wells, most of which are located in the Australia-Asia region. Despite the challenge of gappy records, our model shows an excellent statistical agreement with the observed data. Our results suggested that the total time is longer than the trouble-free time by at least 4 days, and at most 12 days within the 10%-90% confidence interval. This model allows us to derive the likelihoods of duration for each phase at a certain depth and to generate inputs for training data-driven models, facilitating evaluation of the risks of an entire drilling operation and has a potential to be used to generate input for data-driven model.
[1] HOLDAWAY K. Harness oil and gas big data with analytics[M]. New Jersey: John Wiley & Sons, 2014: 364.
[2] MAURER W C. The “perfect-cleaning” theory of rotary drilling[J]. Journal of Petroleum Technology, 1962, 14(11): 1270-1274.
[3] BINGHAM M G. A new approach to interpreting rock drill ability[J]. Oil and Gas Journal, 1965, 62(46): 173-179.
[4] ECKEL J R. Microbit studies of the effect of fluid properties and hydraulics[J]. Journal of Petroleum Technology, 1967, 19(4): 541-546.
[5] BOURGOYNE A T, YOUNG F S. A multiple regression approach to optimal drilling and abnormal pressure detection[J]. Society of Petroleum Engineers Journal, 1974, 14(4): 371-384.
[6] WALKER B H, BLACK A D, KLAUBER W P, et al. Roller-bit penetration rate response as a function of rock properties and well depth[R]. New Orleans, USA: 61st Annual Technical Conference and Exhibition of the Society of Petroleum Engineers, 1986.
[7] SEIFABAD M C, EHTESHAMI P. Estimating the drilling rate in Ahvaz oil field[J]. Journal of Petroleum Exploration and Production Technology, 2013, 3: 169-173.
[8] MORAVEJI M K, NADERI M. Drilling rate of penetration prediction and optimization using response surface methodology and bat algorithm[J]. Journal of Petroleum Science and Engineering, 2016, 31: 829-841.
[9] JAHANBAKHSHI R, KESHAVARZI R, JAFARNEZHAD A. Real-time prediction of rate of penetration during drilling operation in oil and gas wells[R]. Chicago, USA: 46th US Rock Mechanics/ Geomechanics Symposium, 2012.
[10] HEGDE C, GRAY K E. Use of machine learning and data analytics to increase drilling efficiency for nearby wells[J]. Journal of Natural Gas Science and Engineering, 2017, 40: 327-335.
[11] ESKANDARIAN S, BAHRAMI P, KAZEMI P. A comprehensive data mining approach to estimate the rate of penetration: Application of neural network, rule based models and feature ranking[J]. Journal of Petroleum Science and Engineering, 2017, 156: 605-615.
[12] DIAZ M B, KIM K Y, KANG T H, et al. Drilling data from an enhanced geothermal project and its pre-processing for ROP forecasting improvement[J]. Geothermics, 2018, 72: 348-357.
[13] GUILHERME I R, MARANA A N, PAPA J P, et al. Petroleum well drilling monitoring through cutting image analysis and artificial intelligence techniques[J]. Engineering Applications of Artificial Intelligence, 2011, 24(1): 201-207.
[14] MENSA-WILMOT G, HARJADI Y, LANGDON S, et al. Drilling efficiency and rate of penetration: Definitions, influencing factors, relationships and values[R]. SPE 128288-MS, 2010.
[15] AWOTUNDE A A, MUTASIEM M A. Efficient drilling time optimization with differential evolution[R]. SPE 172419-MS, 2014.
[16] NOERAGER J A, NORGE E, WHITE J P, et al. Drilling time predictions from statistical analysis[R]. SPE 16164-MS, 1987.
[17] THOROGOOD J L. A mathematical model for analysing drilling performance & estimating well times[R]. SPE 16524-MS, 1987.
[18] SHILLING R B, LOWE D E. Systems for automated drilling AFE cost estimating and tracking[R]. SPE 20331-MS, 1990.
[19] ARDEKANI O S, SHADIZADEH S R. Development of drilling trip time model for southern Iranian oil fields: Using artificial neural networks and multiple linear regression approaches[J]. Journal of Petroleum Exploration and Production Technology, 2013, 3: 287-295.
[20] LEE S S, KIM K Y, SEO J W. Development of a trip time for bit exchange simulator for drilling time estimation[J]. Geothermics, 2018, 71: 24-33.
[21] MCINTOSH J. Probabilistic modeling for well-construction performance[J]. Journal of Petroleum Technology, 2004, 56(11): 36-39.
[22] AKINS W M, ABELL M P, DIGGINS E M. Enhancing drilling risk and performance management through the use of probabilistic time & cost estimating[R]. SPE 92340-MS, 2005.
[23] LOBERG T, ARILD O, MERLO A, et al. The how's and why's of probabilistic well cost estimation[R]. SPE 114696-MS, 2008.
[24] MERLO A, D'ALESIO P, LOBERG T, et al. An innovative tool on a probabilistic approach related to the well construction costs and times estimation[R]. SPE 121837-MS, 2009.
[25] ADAMS J J, GIBSON C, SMITH R. Probabilistic well-time estimation revisited[R]. SPE 119287-PA, 2010.
[26] ADAMS J J, GRUNDY K C, KELLY C M. Probabilistic well-time estimation revisited: Five years on[R]. SPE 173028-PA, 2015.
[27] BERNACCHIA A, PIGOLOTTI S. Self-consistent method for density estimation[J]. Journal of the Royal Statistical Society: Series B (Statistical Methodology), 2011, 73(3): 407-422.
[28] O'BRIEN T A, KASHINATH K, CAVANAUGH N R, et al. A fast and objective multidimensional kernel density estimation method: FastKDE[J]. Computational Statistics & Data Analysis, 2016, 101: 148-160.
[29] WILLIAMSON H S, SAWARYN S J, MORRISON J W. Monte Carlo techniques applied to well forecasting: Some pitfalls[J]. SPE Drilling & Completion, 2006, 21(3): 216-227.
[30] PETERSON S K, MURTHA J A, SCHNEIDER F F. Brief: Risk analysis and Monte Carlo simulation applied to the generation of drilling AFE estimates[J]. Journal of Petroleum Technology, 1995, 47(6): 504-505.
[31] RABIA H. Oilwell drilling engineering: Principles and practice[M]. London: Graham & Trotman, 1985: 400.
[32] TKALICH P, VETHAMONY P, LUU Q H, et al. Sea level trend and variability in the Singapore Strait[J]. Ocean Science, 2013, 9: 293-300.
[33] LUU Q H, TKALICH P, TAY T W. Sea level trend and variability around Peninsular Malaysia[J]. Ocean Science, 2015, 11: 617-628.
[34] LUU Q H, QING W, TKALICH P, et al. Global mean sea level rise during the recent warming hiatus from satellite-based data[J]. Remote Sensing Letters, 2018, 9(5): 498-507.
