ROP Prediction with Supervised Machine Learning; a Case Study

G. R. Darmawan, D. Irawan
{"title":"ROP Prediction with Supervised Machine Learning; a Case Study","authors":"G. R. Darmawan, D. Irawan","doi":"10.25299/jeee.2022.7772","DOIUrl":null,"url":null,"abstract":"Optimum drilling penetration rate, known as the rate of penetration (ROP) has played  a big role in drilling operations. Planning the well   ROP   always becomes a challenge for drilling engineers to calculate the drilling time needed for the section. Optimum ROP is achieved when the time to drill the section is as planned. \nMany empirical approaches were develop to model the ROP based on the drilling parameters, and might not always match  the actual ROP. In some cases, the actual ROP was slower than planned, which may increase the drilling cost, which needs to be avoided. \nHence, some approaches using artificial intelligent (AI), and supervised machine learning  have been develop to overcome it. Supervised machine learning is used to develop a ROP model and ROP prediction for one of  the development fields,  based only on two wells drilling parameters data. The model was train using Gradient Boosting, Random Forest, and Support Vector Machine. Drilling parameter test data then is used to validate the model. The model of Random Forest  shows a good or promising result with R2 of 0.90,   Gradient Boosting shows R2 of 0.86, and Support Vector Machine with R2 0.72. Based on the models generated, the Random Forest has shown good trend which could be used for modeling ROP in the future development wells.","PeriodicalId":33635,"journal":{"name":"Journal of Earth Energy Engineering","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2022-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Earth Energy Engineering","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.25299/jeee.2022.7772","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

Optimum drilling penetration rate, known as the rate of penetration (ROP) has played  a big role in drilling operations. Planning the well   ROP   always becomes a challenge for drilling engineers to calculate the drilling time needed for the section. Optimum ROP is achieved when the time to drill the section is as planned. Many empirical approaches were develop to model the ROP based on the drilling parameters, and might not always match  the actual ROP. In some cases, the actual ROP was slower than planned, which may increase the drilling cost, which needs to be avoided. Hence, some approaches using artificial intelligent (AI), and supervised machine learning  have been develop to overcome it. Supervised machine learning is used to develop a ROP model and ROP prediction for one of  the development fields,  based only on two wells drilling parameters data. The model was train using Gradient Boosting, Random Forest, and Support Vector Machine. Drilling parameter test data then is used to validate the model. The model of Random Forest  shows a good or promising result with R2 of 0.90,   Gradient Boosting shows R2 of 0.86, and Support Vector Machine with R2 0.72. Based on the models generated, the Random Forest has shown good trend which could be used for modeling ROP in the future development wells.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
有监督机器学习的ROP预测;案例研究
最佳钻进速度,即钻速(ROP)在钻井作业中起着重要作用。对于钻井工程师来说,计算井段所需的钻井时间一直是一个难题。当钻井时间按计划进行时,可以实现最佳ROP。许多经验方法都是基于钻井参数来模拟机械钻速的,但这些方法可能并不总是与实际的机械钻速相匹配。在某些情况下,实际ROP比计划的要慢,这可能会增加钻井成本,这是需要避免的。因此,一些使用人工智能(AI)和监督机器学习的方法已经被开发出来来克服它。监督式机器学习仅基于两口井的钻井参数数据,用于开发一个开发油田的ROP模型和ROP预测。采用梯度增强、随机森林和支持向量机对模型进行训练。然后利用钻井参数测试数据对模型进行验证。随机森林模型的R2为0.90,梯度增强模型的R2为0.86,支持向量机模型的R2为0.72,显示出较好的或有希望的结果。基于生成的模型,随机森林显示出良好的趋势,可用于未来开发井的ROP建模。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
10
审稿时长
8 weeks
期刊最新文献
APPLICATION OF PSO-LSSVM IN PREDICTION AND ANALYSIS OF SLOW DRILLING (RATE OF PENETRATION) EVALUATION OF CONTINUOUS AND WATER ALTERNATING GAS (WAG) CO2 INJECTION ON X FIELD RECOVERY FACTOR The Effect of Different Gas Water Ratio on Recovery Factor and CO2 Storage Capacity in Water Alternating Gas Injection. A Case Study: “V” Field Development, North Sea Oil Formation Volume Factor Prediction Using Artificial Neural Network: A Case Study of Niger Delta Crudes Fracturing Fluid Optimization in Limestone Formation Using Guar Gum Crosslinked Fluid
×
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
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1