Predictive Modeling of Surface Subsidence Considering Different Environmental Risk Zones

Insufficient knowledge and control of the surrounding environmental risks in the process of subway tunnel construction will lead to different degrees of surface settlement during construction, and it is of practical significance to grasp the impact of environmental risks on surface settlement and ma...

Full description

Saved in:
Bibliographic Details
Main Authors: Yunsong Li, Yongjun Qin, Liangfu Xie, Yangchun Yuan, Jie Ran
Format: Article
Language:English
Published: Wiley 2024-01-01
Series:Advances in Civil Engineering
Online Access:http://dx.doi.org/10.1155/adce/6633240
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846138786756427776
author Yunsong Li
Yongjun Qin
Liangfu Xie
Yangchun Yuan
Jie Ran
author_facet Yunsong Li
Yongjun Qin
Liangfu Xie
Yangchun Yuan
Jie Ran
author_sort Yunsong Li
collection DOAJ
description Insufficient knowledge and control of the surrounding environmental risks in the process of subway tunnel construction will lead to different degrees of surface settlement during construction, and it is of practical significance to grasp the impact of environmental risks on surface settlement and make predictions on this basis. There is a close connection between the surrounding environment of subway tunnel construction and the settlement monitoring data, and the high precision prediction of surface settlement through the surrounding environment before subway tunnel construction can guarantee the safety of subway tunnel construction. Therefore, this paper proposes a surface settlement prediction model based on environmental risk zoning. Establish the integrated impact zoning of underground mining environmental risk through spatial superposition and risk quantification, and divide the construction environment into high-risk, middle-risk, and low-risk region. Adopt four different noise reduction algorithms for data noise reduction on the raw data of the monitoring points at the intervals of different risk zones, and combine the time series prediction as well as the deep learning prediction method to get the prediction model for environmental risk zoning based on the environmental risk zoning. The monitoring data of Urumqi Metro Line 1 is analyzed as an example, and the suitable combination of prediction models for each region under the environmental risk zoning of the subway tunnel construction is obtained: high-risk region (singular value decomposition (SVD) + long and short-term memory (LSTM) neural network); middle-risk region (wavelet transform/Kalman filter + back propagation neural network (BPNN)); and low-risk region (mean filtering + autoregressive integrated moving average model (ARIMA)).
format Article
id doaj-art-d12da6fcfaf7481589698182abc731a3
institution Kabale University
issn 1687-8094
language English
publishDate 2024-01-01
publisher Wiley
record_format Article
series Advances in Civil Engineering
spelling doaj-art-d12da6fcfaf7481589698182abc731a32024-12-07T00:00:03ZengWileyAdvances in Civil Engineering1687-80942024-01-01202410.1155/adce/6633240Predictive Modeling of Surface Subsidence Considering Different Environmental Risk ZonesYunsong Li0Yongjun Qin1Liangfu Xie2Yangchun Yuan3Jie Ran4School of Civil Engineering and ArchitectureSchool of Civil Engineering and ArchitectureSchool of Civil Engineering and ArchitectureSchool of Civil Engineering and ArchitectureSchool of Civil Engineering and ArchitectureInsufficient knowledge and control of the surrounding environmental risks in the process of subway tunnel construction will lead to different degrees of surface settlement during construction, and it is of practical significance to grasp the impact of environmental risks on surface settlement and make predictions on this basis. There is a close connection between the surrounding environment of subway tunnel construction and the settlement monitoring data, and the high precision prediction of surface settlement through the surrounding environment before subway tunnel construction can guarantee the safety of subway tunnel construction. Therefore, this paper proposes a surface settlement prediction model based on environmental risk zoning. Establish the integrated impact zoning of underground mining environmental risk through spatial superposition and risk quantification, and divide the construction environment into high-risk, middle-risk, and low-risk region. Adopt four different noise reduction algorithms for data noise reduction on the raw data of the monitoring points at the intervals of different risk zones, and combine the time series prediction as well as the deep learning prediction method to get the prediction model for environmental risk zoning based on the environmental risk zoning. The monitoring data of Urumqi Metro Line 1 is analyzed as an example, and the suitable combination of prediction models for each region under the environmental risk zoning of the subway tunnel construction is obtained: high-risk region (singular value decomposition (SVD) + long and short-term memory (LSTM) neural network); middle-risk region (wavelet transform/Kalman filter + back propagation neural network (BPNN)); and low-risk region (mean filtering + autoregressive integrated moving average model (ARIMA)).http://dx.doi.org/10.1155/adce/6633240
spellingShingle Yunsong Li
Yongjun Qin
Liangfu Xie
Yangchun Yuan
Jie Ran
Predictive Modeling of Surface Subsidence Considering Different Environmental Risk Zones
Advances in Civil Engineering
title Predictive Modeling of Surface Subsidence Considering Different Environmental Risk Zones
title_full Predictive Modeling of Surface Subsidence Considering Different Environmental Risk Zones
title_fullStr Predictive Modeling of Surface Subsidence Considering Different Environmental Risk Zones
title_full_unstemmed Predictive Modeling of Surface Subsidence Considering Different Environmental Risk Zones
title_short Predictive Modeling of Surface Subsidence Considering Different Environmental Risk Zones
title_sort predictive modeling of surface subsidence considering different environmental risk zones
url http://dx.doi.org/10.1155/adce/6633240
work_keys_str_mv AT yunsongli predictivemodelingofsurfacesubsidenceconsideringdifferentenvironmentalriskzones
AT yongjunqin predictivemodelingofsurfacesubsidenceconsideringdifferentenvironmentalriskzones
AT liangfuxie predictivemodelingofsurfacesubsidenceconsideringdifferentenvironmentalriskzones
AT yangchunyuan predictivemodelingofsurfacesubsidenceconsideringdifferentenvironmentalriskzones
AT jieran predictivemodelingofsurfacesubsidenceconsideringdifferentenvironmentalriskzones