检索结果-南通市图书馆

Machine learning of element geochemical anomalies for adverse geology identification in tunnels

在线全文

学校读者我要写书评

暂无评论

Journal of Earth Science 2024年

作者： Ruiqi Shao Peng Lin Zhenhao Xu Fumin Liu Yilong Liu School of Qilu Transportation， Shandong University State Key Laboratory for Tunnel Engineering Jinan Institute of Geotechnical and Underground Engineering， Shandong University

Geological analysis， despite being a long-term method for identifying adverse geology in tunnels， has significant limitations due to its reliance on empirical analysis. The quantitative aspects of geochemical anomalies associated with adverse geology provide a novel strategy for addressing these limitations. However， statistical methods for identifying geochemical anomalies are insufficient for tunnel engineering. In contrast， data mining techniques such as machine learning have demonstrated greater efficacy when applied to geological data. Herein， a method for identifying adverse geology using machine learning of geochemical anomalies is proposed. The method was identified geochemical anomalies in tunnel that were not identified by statistical methods. We by employing robust factor analysis and self-organizing maps to reduce the dimensionality of geochemical data and extract the anomaly elements combination (AEC). Using the AEC sample data， we trained an isolation forest model to identify the multi-element anomalies， successfully. We analyzed the adverse geological features based the multi-element anomalies. This study， therefore， extends the traditional approach of geological analysis in tunnels and demonstrates that machine learning is an effective tool for intelligent geological analysis. Correspondingly， the research offers new insights regarding the adverse geology and the prevention of hazards during the construction of tunnels and underground engineering projects.

关键词：

一种改进的算术优化算法及其在水文地质参数智能反演中的应用

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

应用基础与工程科学学报 2024年第3期32卷 721-739页

作者：许振浩范永辉王文扬董唯杰申艳军潘东东山东大学岩土与结构工程研究中心山东济南250061 山东大学齐鲁交通学院山东济南250061 山东大学土建与水利学院山东济南250061 西南交通大学交通隧道工程教育部重点实验室四川成都610031 西安科技大学地质与环境学院陕西西安710054 山东大学苏州研究院江苏苏州215123

水文地质参数的高效、准确、智能化获取对地下水资源科学管理和地下工程安全建设具有重要意义,因此提出一种新的水文地质参数智能反演方法.首先,提出了改进的算术优化算法(Chaotic Simplex Arithmetic Optimization Algorithm,CSAOA),... 详细信息

水文地质参数的高效、准确、智能化获取对地下水资源科学管理和地下工程安全建设具有重要意义,因此提出一种新的水文地质参数智能反演方法.首先,提出了改进的算术优化算法(Chaotic Simplex Arithmetic Optimization Algorithm,CSAOA),在搜索空间中使用混沌理论初始化粒子位置,引入随机优化的超参数自适应调整策略,同时使用单纯形法优化粒子位置更新法则,进一步提高算法的局部开发能力和勘探能力,减小算法陷入局部最优的概率.其次,选取8个基准函数进行数值实验,结果表明CSAOA算法在前期勘探收敛速度和后期局部开发收敛精度方面优于其他对比算法.再次,将传统的人工配线法转化为基于优化算法的全局最优化问题,构建基于CSAOA算法的水文地质参数反演模型,提出了基于CSAOA算法的水文地质参数智能反演方法.最后,将该方法应用于泰斯和汉图什井流模型参数反演实例进行验证,快速准确反演得到了水文地质参数,实现了水文地质参数智能识别.结果证实了该方法的可靠性与先进性,为解决水文地质参数反演问题提供了一种新的方案.

关键词：算术优化算法混沌映射自适应策略单纯形法水文地质参数智能优化

隧道不良地质识别:方法、现状及智能化发展方向

在线全文

学校读者我要写书评

暂无评论

地球学报 2024年第1期45卷 5-24页

作者：许振浩邵瑞琦林鹏李术才向航韩涛李珊山东大学岩土与结构工程研究中心山东济南250061 山东大学齐鲁交通学院山东济南250061

随着隧道施工对于不良地质识别精度要求的不断提高以及人工智能技术的发展,融合多源信息的不良地质智能化识别已成为发展趋势。本文首先阐述了常见的6种隧道不良地质类型及其地质成因,回顾分析了隧道主要的不良地质识别方法及现状,详细... 详细信息

随着隧道施工对于不良地质识别精度要求的不断提高以及人工智能技术的发展,融合多源信息的不良地质智能化识别已成为发展趋势。本文首先阐述了常见的6种隧道不良地质类型及其地质成因,回顾分析了隧道主要的不良地质识别方法及现状,详细介绍了笔者在不良地质智能化识别方面的探索性研究:基于机器学习利用图像识别技术对隧道围岩岩性与裂隙特征进行智能识别;融合图像和光谱特征进行不良地质识别;将地化分析融入到传统的超前钻探中,融合随钻参数和地化信息进行不良地质随钻识别,既可以发挥超前钻探在感知岩体质量和地层信息变化方面的优势,又可以发挥地化分析在岩性和不良地质异常识别方面的优势;基于地质与物探联合反演进行不良地质识别,旨在实现掌子面前方不良地质体“形”(位置、形态、规模)和“性”(性质和类型)的精确识别。最后,对隧道不良地质智能化识别的发展趋势进行了展望。

关键词：不良地质识别光谱测试地化测试随钻技术联合反演

Extraction and imaging of indicator elements for non-destructive,in-situ,fast identification of adverse geology in tunnels

同方期刊数据库博看期刊评论

在线全文

学校读者我要写书评

暂无评论

International Journal of Mining Science and Technology 2023年第12期33卷 1437-1449页

作者： Fumin Liu Peng Lin Zhenhao Xu Ruiqi Shao Tao Han School of Qilu Transportation Shandong UniversityJinan 250061China Geotechnical and Structural Engineering Research Center Shandong UniversityJinan 250061China

The lag in quantitative methods and detection techniques for geologic information has resulted in time-consuming and human-experienced geologic analysis in *** indicators of rocks can be used to identify adverse geology and to explain the intrinsic causes of damage to normal *** study proposes a method to identify adverse geology by extracting and imaging the indicator *** mapping relationship between rock components and geologic bodies is quickly determined by indicator element extraction based on factor analysis,and then the data are gridded for image *** location and size of the target adverse geology are visually identified through the distribution images of the indicator elements,thus reducing data dimensions and analysis time.A non-destructive,in-situ and fast element detection technique in tunnels was adopted to speed up the process of geology *** accuracy of the detection was validated by comparing field and laboratory test *** study further confirms and refines the previous research,and the results provide references for geological,mining and underground projects.

关键词： Adverse geology identification Indicator elements Rock geochemistry Tunnel engineering Geological analysis