地下采矿引起的沉降预测:基于人工神经网络的方法

IF 2.8 Q2 MINING & MINERAL PROCESSING Mining of Mineral Deposits Pub Date : 2023-12-30 DOI:10.33271/mining17.04.045
Long Quoc Nguyen, Tam Thanh Thi Le, Trong Gia Nguyen, Dinh Trong Tran
{"title":"地下采矿引起的沉降预测:基于人工神经网络的方法","authors":"Long Quoc Nguyen, Tam Thanh Thi Le, Trong Gia Nguyen, Dinh Trong Tran","doi":"10.33271/mining17.04.045","DOIUrl":null,"url":null,"abstract":"Purpose. Mining-induced land subsidence is a significant concern in areas with extensive underground mining activities. Therefore, the prediction of land subsidence is crucial for effective land management and infrastructure planning. This research applies an artificial neural network (ANN) to predict land subsidence over the Mong Duong underground coal mine in Quang Ninh, Vietnam Methods. In the ANN model proposed in this research, four features are used as the model inputs to predict land subsi-dence, i.e., model outputs. These features include the positions of ground points in the direction of the trough main cross-section, the distance from the chamber (goaf) center to the ground monitoring points, the accumulated exploitation volume of extraction space, and the measured/recorded time. The entire dataset of 12 measured epochs, covering 22 months with a 2-month repetition time period, is divided into the training set for the first 9 measured epochs and the test set for the last 3 measured epochs. k-fold cross-validation is first applied to the training set to determine the best model hyperparameters, which are then adopted to predict land subsidence in the test set. Findings. The best model hyperparameters are found to be 5 hidden layers, 64 hidden nodes and 240 iterated epochs. Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of the predicted land subsidence depend on the time separated between the last measured epoch and the predicted epoch. Within 2 months from the last measurements, RMSE and MAE are at 22 and 13 mm for Epoch 10, which increase to 31 and 20 mm for Epoch 11 (4 months from the last measurement) and 37 and 24 mm for Epoch 12 (6 months from the last measurement). Originality. A new ANN model with associated “optimal” hyperparameters to predict underground mining-induced land subsidence is proposed in this research. Practical implications. The ANN model proposed in this research is a good and convenient tool for estimating mining-induced land subsidence, which can be applied to underground mines in Quang Ninh province, Vietnam.","PeriodicalId":43896,"journal":{"name":"Mining of Mineral Deposits","volume":" 20","pages":""},"PeriodicalIF":2.8000,"publicationDate":"2023-12-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Prediction of underground mining-induced subsidence: Artificial neural network based approach\",\"authors\":\"Long Quoc Nguyen, Tam Thanh Thi Le, Trong Gia Nguyen, Dinh Trong Tran\",\"doi\":\"10.33271/mining17.04.045\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Purpose. Mining-induced land subsidence is a significant concern in areas with extensive underground mining activities. Therefore, the prediction of land subsidence is crucial for effective land management and infrastructure planning. This research applies an artificial neural network (ANN) to predict land subsidence over the Mong Duong underground coal mine in Quang Ninh, Vietnam Methods. In the ANN model proposed in this research, four features are used as the model inputs to predict land subsi-dence, i.e., model outputs. These features include the positions of ground points in the direction of the trough main cross-section, the distance from the chamber (goaf) center to the ground monitoring points, the accumulated exploitation volume of extraction space, and the measured/recorded time. The entire dataset of 12 measured epochs, covering 22 months with a 2-month repetition time period, is divided into the training set for the first 9 measured epochs and the test set for the last 3 measured epochs. k-fold cross-validation is first applied to the training set to determine the best model hyperparameters, which are then adopted to predict land subsidence in the test set. Findings. The best model hyperparameters are found to be 5 hidden layers, 64 hidden nodes and 240 iterated epochs. Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of the predicted land subsidence depend on the time separated between the last measured epoch and the predicted epoch. Within 2 months from the last measurements, RMSE and MAE are at 22 and 13 mm for Epoch 10, which increase to 31 and 20 mm for Epoch 11 (4 months from the last measurement) and 37 and 24 mm for Epoch 12 (6 months from the last measurement). Originality. A new ANN model with associated “optimal” hyperparameters to predict underground mining-induced land subsidence is proposed in this research. Practical implications. The ANN model proposed in this research is a good and convenient tool for estimating mining-induced land subsidence, which can be applied to underground mines in Quang Ninh province, Vietnam.\",\"PeriodicalId\":43896,\"journal\":{\"name\":\"Mining of Mineral Deposits\",\"volume\":\" 20\",\"pages\":\"\"},\"PeriodicalIF\":2.8000,\"publicationDate\":\"2023-12-30\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Mining of Mineral Deposits\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.33271/mining17.04.045\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"MINING & MINERAL PROCESSING\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Mining of Mineral Deposits","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.33271/mining17.04.045","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"MINING & MINERAL PROCESSING","Score":null,"Total":0}
引用次数: 0

摘要

目的。在有大量地下采矿活动的地区,采矿引起的土地沉降是一个重大问题。因此,预测土地沉降对于有效的土地管理和基础设施规划至关重要。本研究采用人工神经网络(ANN)来预测越南广宁省 Mong Duong 地下煤矿的土地沉降。在本研究提出的人工神经网络模型中,有四个特征作为模型输入来预测土地沉降,即模型输出。这些特征包括槽主横截面方向上的地面点位置、腔室(鹅卵石)中心到地面监测点的距离、开采空间的累计开采量以及测量/记录的时间。整个数据集有 12 个测量历元,涵盖 22 个月,重复时间为 2 个月,分为前 9 个测量历元的训练集和后 3 个测量历元的测试集。首先对训练集进行 k 倍交叉验证,以确定最佳模型超参数,然后采用这些超参数预测测试集中的地面沉降。结果最佳模型超参数为 5 个隐藏层、64 个隐藏节点和 240 个迭代历元。预测土地沉降的均方根误差(RMSE)和平均绝对误差(MAE)取决于最后测量历元与预测历元之间的时间间隔。在距最后一次测量的 2 个月内,第 10 个纪元的 RMSE 和 MAE 分别为 22 毫米和 13 毫米,第 11 个纪元(距最后一次测量的 4 个月)的 RMSE 和 MAE 分别为 31 毫米和 20 毫米,第 12 个纪元(距最后一次测量的 6 个月)的 RMSE 和 MAE 分别为 37 毫米和 24 毫米。独创性。本研究提出了一种新的方差网络模型,该模型具有相关的 "最佳 "超参数,可用于预测地下采矿引起的地面沉降。实际意义。本研究提出的 ANN 模型是估算采矿引起的地面沉降的一个良好而便捷的工具,可用于越南广宁省的地下矿山。
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
Prediction of underground mining-induced subsidence: Artificial neural network based approach
Purpose. Mining-induced land subsidence is a significant concern in areas with extensive underground mining activities. Therefore, the prediction of land subsidence is crucial for effective land management and infrastructure planning. This research applies an artificial neural network (ANN) to predict land subsidence over the Mong Duong underground coal mine in Quang Ninh, Vietnam Methods. In the ANN model proposed in this research, four features are used as the model inputs to predict land subsi-dence, i.e., model outputs. These features include the positions of ground points in the direction of the trough main cross-section, the distance from the chamber (goaf) center to the ground monitoring points, the accumulated exploitation volume of extraction space, and the measured/recorded time. The entire dataset of 12 measured epochs, covering 22 months with a 2-month repetition time period, is divided into the training set for the first 9 measured epochs and the test set for the last 3 measured epochs. k-fold cross-validation is first applied to the training set to determine the best model hyperparameters, which are then adopted to predict land subsidence in the test set. Findings. The best model hyperparameters are found to be 5 hidden layers, 64 hidden nodes and 240 iterated epochs. Root Mean Square Error (RMSE) and Mean Absolute Error (MAE) of the predicted land subsidence depend on the time separated between the last measured epoch and the predicted epoch. Within 2 months from the last measurements, RMSE and MAE are at 22 and 13 mm for Epoch 10, which increase to 31 and 20 mm for Epoch 11 (4 months from the last measurement) and 37 and 24 mm for Epoch 12 (6 months from the last measurement). Originality. A new ANN model with associated “optimal” hyperparameters to predict underground mining-induced land subsidence is proposed in this research. Practical implications. The ANN model proposed in this research is a good and convenient tool for estimating mining-induced land subsidence, which can be applied to underground mines in Quang Ninh province, Vietnam.
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
Mining of Mineral Deposits
Mining of Mineral Deposits MINING & MINERAL PROCESSING-
CiteScore
5.20
自引率
15.80%
发文量
52
期刊最新文献
Analyzing stability of protective structures as the elements of geotechnical tailing pond safety Mining of non-metallic mineral deposits in the context of Ukraine’s reconstruction in the war and post-war periods Optimizing the blast fragmentation quality of discontinuous rock mass: Case study of Jebel Bouzegza Open-Cast Mine, North Algeria Use of solid mining waste to improve water retention capacity of loamy soils Deformation as a process to transform shape and volume of protective structures of the development mine workings during coal-rock mass off-loading
×
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