面向钻井模型的灵敏度分析与特征选择

IF 2.6 3区 工程技术 Q3 ENERGY & FUELS Journal of Energy Resources Technology-transactions of The Asme Pub Date : 2023-04-20 DOI:10.1115/1.4062382
Sofia Tariq, D. Sui
{"title":"面向钻井模型的灵敏度分析与特征选择","authors":"Sofia Tariq, D. Sui","doi":"10.1115/1.4062382","DOIUrl":null,"url":null,"abstract":"\n Data-driven models have risen in popularity during the past ten years, which increase the effectiveness and durability of systems without necessitating a lot of human involvement. Despite all of their advantages, they remain the limitations in terms of model interpretation, data selection and model evaluation, etc. Sensitivity Analysis is a powerful tool to decipher behaviors of data-driven models to analyze the correlations among inputs and outputs of models, and quantify the severity of inputs' influence on outputs to effectively interpret these black-box models. Feature Selection (FS) is a pre-processing approach used in data-driven modeling to select the crucial parameters as inputs fed to models. For the most of existing works, the FS is well-used to select inputs through the analysis on the drilling data correlations, while SA is seldom employed for data-driven model evaluation and interpretation in drilling applications. Data-driven Rate of Penetration (ROP) models have consistently outperformed many conventional ROP models, most likely as a result of their strong data analysis capabilities, capacity to learn from data in order to recognize data patterns, and effective policies for making logical decisions automatically. A data-driven ROP model was developed from a benchmarking field drilling dataset in this work. Following the ROP modelling, sensitivity analysis methods were employed to identify the input variables that had the greatest influence on ROP estimations. The FS techniques and the sensitivity analysis were combined during the data preprocessing to identify the most important aspects for modelling. The outcomes demonstrate that using the obust sensitivity analysis techniques to overcome the limits of machine learning models allows for the best interpretation and understanding of the produced data-driven models.","PeriodicalId":15676,"journal":{"name":"Journal of Energy Resources Technology-transactions of The Asme","volume":" ","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2023-04-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Sensitivity Analysis and Feature Selection for Drilling-oriented Models\",\"authors\":\"Sofia Tariq, D. Sui\",\"doi\":\"10.1115/1.4062382\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"\\n Data-driven models have risen in popularity during the past ten years, which increase the effectiveness and durability of systems without necessitating a lot of human involvement. Despite all of their advantages, they remain the limitations in terms of model interpretation, data selection and model evaluation, etc. Sensitivity Analysis is a powerful tool to decipher behaviors of data-driven models to analyze the correlations among inputs and outputs of models, and quantify the severity of inputs' influence on outputs to effectively interpret these black-box models. Feature Selection (FS) is a pre-processing approach used in data-driven modeling to select the crucial parameters as inputs fed to models. For the most of existing works, the FS is well-used to select inputs through the analysis on the drilling data correlations, while SA is seldom employed for data-driven model evaluation and interpretation in drilling applications. Data-driven Rate of Penetration (ROP) models have consistently outperformed many conventional ROP models, most likely as a result of their strong data analysis capabilities, capacity to learn from data in order to recognize data patterns, and effective policies for making logical decisions automatically. A data-driven ROP model was developed from a benchmarking field drilling dataset in this work. Following the ROP modelling, sensitivity analysis methods were employed to identify the input variables that had the greatest influence on ROP estimations. The FS techniques and the sensitivity analysis were combined during the data preprocessing to identify the most important aspects for modelling. The outcomes demonstrate that using the obust sensitivity analysis techniques to overcome the limits of machine learning models allows for the best interpretation and understanding of the produced data-driven models.\",\"PeriodicalId\":15676,\"journal\":{\"name\":\"Journal of Energy Resources Technology-transactions of The Asme\",\"volume\":\" \",\"pages\":\"\"},\"PeriodicalIF\":2.6000,\"publicationDate\":\"2023-04-20\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Journal of Energy Resources Technology-transactions of The Asme\",\"FirstCategoryId\":\"5\",\"ListUrlMain\":\"https://doi.org/10.1115/1.4062382\",\"RegionNum\":3,\"RegionCategory\":\"工程技术\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Energy Resources Technology-transactions of The Asme","FirstCategoryId":"5","ListUrlMain":"https://doi.org/10.1115/1.4062382","RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0

摘要

在过去的十年里,数据驱动模型越来越受欢迎,它在不需要大量人工参与的情况下提高了系统的有效性和耐用性。尽管它们具有所有优势,但在模型解释、数据选择和模型评估等方面仍然存在局限性。敏感性分析是解读数据驱动模型行为的有力工具,可以分析模型的输入和输出之间的相关性,并量化输入对输出影响的严重程度,从而有效地解释这些黑匣子模型。特征选择(FS)是数据驱动建模中使用的一种预处理方法,用于选择关键参数作为输入。在大多数现有工作中,FS被很好地用于通过分析钻井数据相关性来选择输入,而SA很少用于钻井应用中的数据驱动模型评估和解释。数据驱动的渗透率(ROP)模型一直优于许多传统的ROP模型,这很可能是因为它们强大的数据分析能力、从数据中学习以识别数据模式的能力,以及自动做出逻辑决策的有效策略。在这项工作中,从基准现场钻井数据集开发了一个数据驱动的ROP模型。在ROP建模之后,采用灵敏度分析方法来确定对ROP估计影响最大的输入变量。在数据预处理过程中,FS技术和灵敏度分析相结合,以确定建模的最重要方面。结果表明,使用obust敏感性分析技术来克服机器学习模型的局限性,可以更好地解释和理解生成的数据驱动模型。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
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
Sensitivity Analysis and Feature Selection for Drilling-oriented Models
Data-driven models have risen in popularity during the past ten years, which increase the effectiveness and durability of systems without necessitating a lot of human involvement. Despite all of their advantages, they remain the limitations in terms of model interpretation, data selection and model evaluation, etc. Sensitivity Analysis is a powerful tool to decipher behaviors of data-driven models to analyze the correlations among inputs and outputs of models, and quantify the severity of inputs' influence on outputs to effectively interpret these black-box models. Feature Selection (FS) is a pre-processing approach used in data-driven modeling to select the crucial parameters as inputs fed to models. For the most of existing works, the FS is well-used to select inputs through the analysis on the drilling data correlations, while SA is seldom employed for data-driven model evaluation and interpretation in drilling applications. Data-driven Rate of Penetration (ROP) models have consistently outperformed many conventional ROP models, most likely as a result of their strong data analysis capabilities, capacity to learn from data in order to recognize data patterns, and effective policies for making logical decisions automatically. A data-driven ROP model was developed from a benchmarking field drilling dataset in this work. Following the ROP modelling, sensitivity analysis methods were employed to identify the input variables that had the greatest influence on ROP estimations. The FS techniques and the sensitivity analysis were combined during the data preprocessing to identify the most important aspects for modelling. The outcomes demonstrate that using the obust sensitivity analysis techniques to overcome the limits of machine learning models allows for the best interpretation and understanding of the produced data-driven models.
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
CiteScore
6.40
自引率
30.00%
发文量
213
审稿时长
4.5 months
期刊介绍: Specific areas of importance including, but not limited to: Fundamentals of thermodynamics such as energy, entropy and exergy, laws of thermodynamics; Thermoeconomics; Alternative and renewable energy sources; Internal combustion engines; (Geo) thermal energy storage and conversion systems; Fundamental combustion of fuels; Energy resource recovery from biomass and solid wastes; Carbon capture; Land and offshore wells drilling; Production and reservoir engineering;, Economics of energy resource exploitation
期刊最新文献
Modeling and influence factors analysis of refueling emissions for plug-in hybrid electric vehicles Structure optimization and performance evaluation of downhole oil-water separation tools: a novel hydrocyclone Effects of Trapped Gas in Fracture-Pore Carbonate Reservoirs Shale Oil-water Two-phase Flow Simulation based on Pore Network Modeling Investigation on the effects of nanorefrigerants in a combined cycle of ejector refrigeration cycle and Kalina cycle
×
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