基于长短期记忆和元启发式算法的水驱生产优化

IF 4.2 Q2 ENERGY & FUELS
Cuthbert Shang Wui Ng , Ashkan Jahanbani Ghahfarokhi , Menad Nait Amar
{"title":"基于长短期记忆和元启发式算法的水驱生产优化","authors":"Cuthbert Shang Wui Ng ,&nbsp;Ashkan Jahanbani Ghahfarokhi ,&nbsp;Menad Nait Amar","doi":"10.1016/j.petlm.2021.12.008","DOIUrl":null,"url":null,"abstract":"<div><p>In petroleum domain, optimizing hydrocarbon production is essential because it does not only ensure the economic prospects of the petroleum companies, but also fulfills the increasing global demand of energy. However, applying numerical reservoir simulation (NRS) to optimize production can induce high computational footprint. Proxy models are suggested to alleviate this challenge because they are computationally less demanding and able to yield reasonably accurate results. In this paper, we demonstrated how a machine learning technique, namely long short-term memory (LSTM), was applied to develop proxies of a 3D reservoir model. Sampling techniques were employed to create numerous simulation cases which served as the training database to establish the proxies. Upon blind validating the trained proxies, we coupled these proxies with particle swarm optimization to conduct production optimization. Both training and blind validation results illustrated that the proxies had been excellently developed with coefficient of determination, R<sup>2</sup> of 0.99. We also compared the optimization results produced by NRS and the proxies. The comparison recorded a good level of accuracy that was within 3% error. The proxies were also computationally 3 times faster than NRS. Hence, the proxies have served their practical purposes in this study.</p></div>","PeriodicalId":37433,"journal":{"name":"Petroleum","volume":null,"pages":null},"PeriodicalIF":4.2000,"publicationDate":"2023-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"11","resultStr":"{\"title\":\"Production optimization under waterflooding with long short-term memory and metaheuristic algorithm\",\"authors\":\"Cuthbert Shang Wui Ng ,&nbsp;Ashkan Jahanbani Ghahfarokhi ,&nbsp;Menad Nait Amar\",\"doi\":\"10.1016/j.petlm.2021.12.008\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>In petroleum domain, optimizing hydrocarbon production is essential because it does not only ensure the economic prospects of the petroleum companies, but also fulfills the increasing global demand of energy. However, applying numerical reservoir simulation (NRS) to optimize production can induce high computational footprint. Proxy models are suggested to alleviate this challenge because they are computationally less demanding and able to yield reasonably accurate results. In this paper, we demonstrated how a machine learning technique, namely long short-term memory (LSTM), was applied to develop proxies of a 3D reservoir model. Sampling techniques were employed to create numerous simulation cases which served as the training database to establish the proxies. Upon blind validating the trained proxies, we coupled these proxies with particle swarm optimization to conduct production optimization. Both training and blind validation results illustrated that the proxies had been excellently developed with coefficient of determination, R<sup>2</sup> of 0.99. We also compared the optimization results produced by NRS and the proxies. The comparison recorded a good level of accuracy that was within 3% error. The proxies were also computationally 3 times faster than NRS. Hence, the proxies have served their practical purposes in this study.</p></div>\",\"PeriodicalId\":37433,\"journal\":{\"name\":\"Petroleum\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":4.2000,\"publicationDate\":\"2023-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"11\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Petroleum\",\"FirstCategoryId\":\"1087\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2405656121001048\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Petroleum","FirstCategoryId":"1087","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2405656121001048","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 11

摘要

在石油领域,优化碳氢化合物生产至关重要,因为它不仅确保了石油公司的经济前景,而且满足了全球日益增长的能源需求。然而,应用油藏数值模拟(NRS)来优化生产可能会导致高计算足迹。建议使用代理模型来缓解这一挑战,因为它们在计算上要求较低,并且能够产生相当准确的结果。在本文中,我们演示了如何将机器学习技术,即长短期记忆(LSTM)应用于开发三维油藏模型的代理。采用采样技术创建了大量模拟案例,这些案例作为建立代理的训练数据库。在对训练的代理进行盲验证后,我们将这些代理与粒子群优化相结合,以进行生产优化。训练和盲验证结果都表明,代理已经得到了很好的开发,确定系数R2为0.99。我们还比较了NRS和代理产生的优化结果。比较记录了良好的准确度,误差在3%以内。代理在计算上也比NRS快3倍。因此,代理人在本研究中达到了其实际目的。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Production optimization under waterflooding with long short-term memory and metaheuristic algorithm

In petroleum domain, optimizing hydrocarbon production is essential because it does not only ensure the economic prospects of the petroleum companies, but also fulfills the increasing global demand of energy. However, applying numerical reservoir simulation (NRS) to optimize production can induce high computational footprint. Proxy models are suggested to alleviate this challenge because they are computationally less demanding and able to yield reasonably accurate results. In this paper, we demonstrated how a machine learning technique, namely long short-term memory (LSTM), was applied to develop proxies of a 3D reservoir model. Sampling techniques were employed to create numerous simulation cases which served as the training database to establish the proxies. Upon blind validating the trained proxies, we coupled these proxies with particle swarm optimization to conduct production optimization. Both training and blind validation results illustrated that the proxies had been excellently developed with coefficient of determination, R2 of 0.99. We also compared the optimization results produced by NRS and the proxies. The comparison recorded a good level of accuracy that was within 3% error. The proxies were also computationally 3 times faster than NRS. Hence, the proxies have served their practical purposes in this study.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Petroleum
Petroleum Earth and Planetary Sciences-Geology
CiteScore
9.20
自引率
0.00%
发文量
76
审稿时长
124 days
期刊介绍: Examples of appropriate topical areas that will be considered include the following: 1.comprehensive research on oil and gas reservoir (reservoir geology): -geological basis of oil and gas reservoirs -reservoir geochemistry -reservoir formation mechanism -reservoir identification methods and techniques 2.kinetics of oil and gas basins and analyses of potential oil and gas resources: -fine description factors of hydrocarbon accumulation -mechanism analysis on recovery and dynamic accumulation process -relationship between accumulation factors and the accumulation process -analysis of oil and gas potential resource 3.theories and methods for complex reservoir geophysical prospecting: -geophysical basis of deep geologic structures and background of hydrocarbon occurrence -geophysical prediction of deep and complex reservoirs -physical test analyses and numerical simulations of reservoir rocks -anisotropic medium seismic imaging theory and new technology for multiwave seismic exploration -o theories and methods for reservoir fluid geophysical identification and prediction 4.theories, methods, technology, and design for complex reservoir development: -reservoir percolation theory and application technology -field development theories and methods -theory and technology for enhancing recovery efficiency 5.working liquid for oil and gas wells and reservoir protection technology: -working chemicals and mechanics for oil and gas wells -reservoir protection technology 6.new techniques and technologies for oil and gas drilling and production: -under-balanced drilling/gas drilling -special-track well drilling -cementing and completion of oil and gas wells -engineering safety applications for oil and gas wells -new technology of fracture acidizing
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信