{"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 , Ashkan Jahanbani Ghahfarokhi , 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 , Ashkan Jahanbani Ghahfarokhi , 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}
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.
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