{"title":"Machine learning for drilling applications: A review","authors":"Ruizhi Zhong , Cyrus Salehi , Ray Johnson Jr","doi":"10.1016/j.jngse.2022.104807","DOIUrl":null,"url":null,"abstract":"<div><p>In the past several decades, machine learning has gained increasing interest in the oil and gas industry<span><span>. This paper presents a comprehensive review of machine learning studies for drilling applications in the following categories: (1) drilling fluids; (2) drilling hydraulics; (3) </span>drilling dynamics; (4) drilling problems; and (5) miscellaneous drilling applications. In each study, the machine learning algorithm(s), sample size, inputs and output(s), and performance are extracted. In addition, similarities of studies in each category are summarized and recommendations are made for future development.</span></p></div>","PeriodicalId":372,"journal":{"name":"Journal of Natural Gas Science and Engineering","volume":"108 ","pages":"Article 104807"},"PeriodicalIF":4.9000,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"13","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Natural Gas Science and Engineering","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1875510022003936","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 13
Abstract
In the past several decades, machine learning has gained increasing interest in the oil and gas industry. This paper presents a comprehensive review of machine learning studies for drilling applications in the following categories: (1) drilling fluids; (2) drilling hydraulics; (3) drilling dynamics; (4) drilling problems; and (5) miscellaneous drilling applications. In each study, the machine learning algorithm(s), sample size, inputs and output(s), and performance are extracted. In addition, similarities of studies in each category are summarized and recommendations are made for future development.
期刊介绍:
The objective of the Journal of Natural Gas Science & Engineering is to bridge the gap between the engineering and the science of natural gas by publishing explicitly written articles intelligible to scientists and engineers working in any field of natural gas science and engineering from the reservoir to the market.
An attempt is made in all issues to balance the subject matter and to appeal to a broad readership. The Journal of Natural Gas Science & Engineering covers the fields of natural gas exploration, production, processing and transmission in its broadest possible sense. Topics include: origin and accumulation of natural gas; natural gas geochemistry; gas-reservoir engineering; well logging, testing and evaluation; mathematical modelling; enhanced gas recovery; thermodynamics and phase behaviour, gas-reservoir modelling and simulation; natural gas production engineering; primary and enhanced production from unconventional gas resources, subsurface issues related to coalbed methane, tight gas, shale gas, and hydrate production, formation evaluation; exploration methods, multiphase flow and flow assurance issues, novel processing (e.g., subsea) techniques, raw gas transmission methods, gas processing/LNG technologies, sales gas transmission and storage. The Journal of Natural Gas Science & Engineering will also focus on economical, environmental, management and safety issues related to natural gas production, processing and transportation.