Modern data analysis technologies used for geomechanical monitoring. Review

IF 0.8 Q4 METALLURGY & METALLURGICAL ENGINEERING
O. Besimbayeva, E. Khmyrova, M. Tutanova, N. Flindt, R. R. Sharafutdinov
{"title":"Modern data analysis technologies used for geomechanical monitoring. Review","authors":"O. Besimbayeva, E. Khmyrova, M. Tutanova, N. Flindt, R. R. Sharafutdinov","doi":"10.31643/2023/6445.23","DOIUrl":null,"url":null,"abstract":"The paper considers the possibilities of modern technologies and software that make it possible to create continuity of geomechanical monitoring of man-made objects from shooting in automatic mode, robotic surveillance systems, transmitting information over the Internet to cloud storage, to performing stability calculations, determining the parameters of displacement and deformation of slopes of ledges and sides of quarries. The development of modern technologies for collecting and processing information allows the use of artificial neural networks that are adapted for modeling geodetic deformations. Technogenic objects, which are very complex systems, have a huge number of external factors affecting the stability of the mountain range, so it becomes incredibly difficult to take into account and determine the amount of displacement and deformation. Due to the complexity and variety of influencing factors, it becomes necessary to use a new system for assessing the state of objects, called \"neural networks\". The training of such a system is based on the already available research results collected during the direct operation of industrial enterprises. Neural networks can become an alternative to various methods of describing deformation processes, especially in the continuous monitoring of man-made objects, where there is no a priori knowledge of the underlying deformation processes. For effective monitoring and forecasting of deformation processes at a mining enterprise, a multiparametric monitoring method is needed, which includes a comprehensive system based on GPS measurements, supplemented with data from sensors for changes in water level and changes in stresses and deformations of the array. The results of automated survey and data recording sent to the cloud storage are distributed using \"Big Data\" technology and analyzed by geoinformation systems. In turn, the adaptation of neural networks to model deformations allows specialists to obtain a good alternative to the description of structural deformations of the mountain range.","PeriodicalId":29905,"journal":{"name":"Kompleksnoe Ispolzovanie Mineralnogo Syra","volume":" ","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Kompleksnoe Ispolzovanie Mineralnogo Syra","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.31643/2023/6445.23","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"METALLURGY & METALLURGICAL ENGINEERING","Score":null,"Total":0}
引用次数: 0

Abstract

The paper considers the possibilities of modern technologies and software that make it possible to create continuity of geomechanical monitoring of man-made objects from shooting in automatic mode, robotic surveillance systems, transmitting information over the Internet to cloud storage, to performing stability calculations, determining the parameters of displacement and deformation of slopes of ledges and sides of quarries. The development of modern technologies for collecting and processing information allows the use of artificial neural networks that are adapted for modeling geodetic deformations. Technogenic objects, which are very complex systems, have a huge number of external factors affecting the stability of the mountain range, so it becomes incredibly difficult to take into account and determine the amount of displacement and deformation. Due to the complexity and variety of influencing factors, it becomes necessary to use a new system for assessing the state of objects, called "neural networks". The training of such a system is based on the already available research results collected during the direct operation of industrial enterprises. Neural networks can become an alternative to various methods of describing deformation processes, especially in the continuous monitoring of man-made objects, where there is no a priori knowledge of the underlying deformation processes. For effective monitoring and forecasting of deformation processes at a mining enterprise, a multiparametric monitoring method is needed, which includes a comprehensive system based on GPS measurements, supplemented with data from sensors for changes in water level and changes in stresses and deformations of the array. The results of automated survey and data recording sent to the cloud storage are distributed using "Big Data" technology and analyzed by geoinformation systems. In turn, the adaptation of neural networks to model deformations allows specialists to obtain a good alternative to the description of structural deformations of the mountain range.
用于地质力学监测的现代数据分析技术。审查
本文考虑了现代技术和软件的可能性,这些技术和软件使得有可能对人造物体进行连续的地质力学监测,从自动模式拍摄,机器人监视系统,通过互联网将信息传输到云存储,进行稳定性计算,确定采石场边缘和侧面斜坡的位移和变形参数。收集和处理信息的现代技术的发展允许使用人工神经网络,适用于大地形变建模。技术成因对象是非常复杂的系统,有大量的外部因素影响山脉的稳定性,因此考虑和确定位移和变形量变得非常困难。由于影响因素的复杂性和多样性,有必要使用一种新的系统来评估物体的状态,称为“神经网络”。该系统的培训是基于在工业企业直接运营过程中收集的已有研究成果。神经网络可以成为描述变形过程的各种方法的替代方法,特别是在对人造物体的连续监测中,其中没有对潜在变形过程的先验知识。为了有效地监测和预测矿山企业的变形过程,需要一种多参数监测方法,其中包括以GPS测量为基础的综合系统,辅以传感器的水位变化和阵列的应力和变形变化数据。自动调查和数据记录的结果发送到云存储,使用“大数据”技术进行分发,并由地理信息系统进行分析。反过来,神经网络对变形模型的适应使专家能够获得山脉结构变形描述的良好替代方案。
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 求助全文
来源期刊
自引率
42.90%
发文量
55
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信