Supervised domain adaptation in prediction of peak shear strength of rock fractures

IF 7 1区 工程技术 Q1 ENGINEERING, GEOLOGICAL International Journal of Rock Mechanics and Mining Sciences Pub Date : 2024-09-20 DOI:10.1016/j.ijrmms.2024.105921
Jinfan Chen , Zhihong Zhao , Yue Shen , Jun Wu , Jintong Zhang , Zhina Liu
{"title":"Supervised domain adaptation in prediction of peak shear strength of rock fractures","authors":"Jinfan Chen ,&nbsp;Zhihong Zhao ,&nbsp;Yue Shen ,&nbsp;Jun Wu ,&nbsp;Jintong Zhang ,&nbsp;Zhina Liu","doi":"10.1016/j.ijrmms.2024.105921","DOIUrl":null,"url":null,"abstract":"<div><p>It is of great importance to determine peak shear strength (PSS) of rock fractures, and data-driven criteria have showed advances in fitting capability in recent years. However, the generalization ability of existing data-driven criteria is limited by dataset size and fracture roughness characterization, which is negative to predictive power and robustness of models. Here we proposed a novel data-driven criterion to predict PSS of rock fractures, with high generalization ability on real experimental data. We first created large-scale low-fidelity dataset by discrete-element modeling, and small-scale high-fidelity dataset by laboratory direct shear tests. The numeric features include normal stress, mechanical properties (including PSS of intact and flat-fracture rock specimens), secondary properties (including internal friction angle, cohesion strength and basic friction angle), and the matrixed feature is topography data. We then established domain adaptation (DA) models for cross-domain knowledge transfer between the low- and high-fidelity datasets, and roughness features were automatically extracted by convolution kernels. The best DA-based model is weighting adversarial neural network, outranking other models by error indicator, and the average relative error on experimental data of new rock types is within 10.0 %. Finally, the sensitivity of input features is investigated, which further proves the promising potential of the developed data-driven PSS criterion of rock fractures in engineering practice.</p></div>","PeriodicalId":54941,"journal":{"name":"International Journal of Rock Mechanics and Mining Sciences","volume":"183 ","pages":"Article 105921"},"PeriodicalIF":7.0000,"publicationDate":"2024-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Rock Mechanics and Mining Sciences","FirstCategoryId":"5","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1365160924002867","RegionNum":1,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ENGINEERING, GEOLOGICAL","Score":null,"Total":0}
引用次数: 0

Abstract

It is of great importance to determine peak shear strength (PSS) of rock fractures, and data-driven criteria have showed advances in fitting capability in recent years. However, the generalization ability of existing data-driven criteria is limited by dataset size and fracture roughness characterization, which is negative to predictive power and robustness of models. Here we proposed a novel data-driven criterion to predict PSS of rock fractures, with high generalization ability on real experimental data. We first created large-scale low-fidelity dataset by discrete-element modeling, and small-scale high-fidelity dataset by laboratory direct shear tests. The numeric features include normal stress, mechanical properties (including PSS of intact and flat-fracture rock specimens), secondary properties (including internal friction angle, cohesion strength and basic friction angle), and the matrixed feature is topography data. We then established domain adaptation (DA) models for cross-domain knowledge transfer between the low- and high-fidelity datasets, and roughness features were automatically extracted by convolution kernels. The best DA-based model is weighting adversarial neural network, outranking other models by error indicator, and the average relative error on experimental data of new rock types is within 10.0 %. Finally, the sensitivity of input features is investigated, which further proves the promising potential of the developed data-driven PSS criterion of rock fractures in engineering practice.

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
岩石裂缝峰值剪切强度预测中的监督域适应
确定岩石裂缝的峰值剪切强度(PSS)非常重要,近年来数据驱动标准在拟合能力方面取得了进步。然而,现有数据驱动准则的泛化能力受到数据集大小和断裂粗糙度特征的限制,这对模型的预测能力和稳健性不利。在此,我们提出了一种新颖的数据驱动准则来预测岩石裂缝的 PSS,该准则在真实实验数据上具有较高的泛化能力。我们首先通过离散元建模创建了大规模低保真数据集,并通过实验室直接剪切试验创建了小规模高保真数据集。数值特征包括法向应力、力学性质(包括完整和平断裂岩石试样的 PSS)、次要性质(包括内摩擦角、内聚强度和基本摩擦角),矩阵特征为地形数据。然后,我们建立了领域适应(DA)模型,用于低保真和高保真数据集之间的跨领域知识转移,并通过卷积核自动提取粗糙度特征。基于 DA 的最佳模型是加权对抗神经网络,其误差指标优于其他模型,对新岩石类型实验数据的平均相对误差在 10.0% 以内。最后,研究了输入特征的敏感性,这进一步证明了所开发的数据驱动岩石裂缝 PSS 准则在工程实践中的巨大潜力。
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
CiteScore
14.00
自引率
5.60%
发文量
196
审稿时长
18 weeks
期刊介绍: The International Journal of Rock Mechanics and Mining Sciences focuses on original research, new developments, site measurements, and case studies within the fields of rock mechanics and rock engineering. Serving as an international platform, it showcases high-quality papers addressing rock mechanics and the application of its principles and techniques in mining and civil engineering projects situated on or within rock masses. These projects encompass a wide range, including slopes, open-pit mines, quarries, shafts, tunnels, caverns, underground mines, metro systems, dams, hydro-electric stations, geothermal energy, petroleum engineering, and radioactive waste disposal. The journal welcomes submissions on various topics, with particular interest in theoretical advancements, analytical and numerical methods, rock testing, site investigation, and case studies.
期刊最新文献
Mutual feedback and fracturing effect of hydraulic fractures in composite coal−rock reservoirs under different fracturing layer sequence conditions Experimental study on the interaction mechanism of two dynamic cracks under blasting loading Thermo-Hydro-Mechanical (THM) wellbore analysis under sub-zero CO2 injection The effect of strain rate on inelastic strain development in porous sandstones deformed under reservoir conditions Integration of automatic discontinuity identification and multi-scale hierarchical modeling for stability analysis of highly-jointed rock slopes
×
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