Metro Foundation Pit Deformation Prediction Method Based on CNN-GRU Neural Network under Incomplete Data Condition

[Objective] To address the issues of prediction delay and accuracy degradation caused by incomplete deformation monitoring data in metro foundation pits, a prediction method based on a CNN-GRU (convolutional neural network-gated recurrent unit) neural network is proposed and verified. [Method] A dat...

Full description

Saved in:
Bibliographic Details
Main Authors: ZHOU Yi, WANG Zhangqiong, ZOU Yuangeng, CAI Yonghui, XU Xiaoya, ZHAO Qilin
Format: Article
Language:zho
Published: Urban Mass Transit Magazine Press 2025-06-01
Series:Chengshi guidao jiaotong yanjiu
Subjects:
Online Access:https://umt1998.tongji.edu.cn/journal/paper/doi/10.16037/j.1007-869x.20230612.html
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849426488622841856
author ZHOU Yi
WANG Zhangqiong
ZOU Yuangeng
CAI Yonghui
XU Xiaoya
ZHAO Qilin
author_facet ZHOU Yi
WANG Zhangqiong
ZOU Yuangeng
CAI Yonghui
XU Xiaoya
ZHAO Qilin
author_sort ZHOU Yi
collection DOAJ
description [Objective] To address the issues of prediction delay and accuracy degradation caused by incomplete deformation monitoring data in metro foundation pits, a prediction method based on a CNN-GRU (convolutional neural network-gated recurrent unit) neural network is proposed and verified. [Method] A data sample set is constructed using incomplete foundation pit deformation monitoring data and missing monitoring data from nearby monitoring points, and then input into the CNN model to complete data imputation and obtain continuous and complete monitoring data. Wavelet decomposition is applied to extract low-frequency trend components and high-frequency error components from the deformation data. The GRU neural network model and ARMA (autoregressive moving average) model are respectively used to predict the low-frequency trend and noise components, which are then combined to yield the final deformation prediction results. The foundation pit project at a metro station in Nanjing is used as case study to verify the effectiveness of the proposed method. [Result & Conclusion] When the proposed CNN-GRU-based prediction method is applied to foundation pit deformation data imputation with missing rates of 18.5% and 10.1%, the resulting prediction errors are 1.926 6% and 1.274 6%, respectively, and the prediction accuracy improves by 35% and 6%, respectively. These results demonstrate strong data recovery capability and high reliability of this method. Compared to the GA-BP neural network and LSTM prediction methods, the proposed method improves prediction accuracy by more than 100% and effectively addresses the issue of prediction lag. The accuracy of this method could meet the requirements of practical engineering applications.
format Article
id doaj-art-8cb0d70fcf324b3387cc929b05328a3f
institution Kabale University
issn 1007-869X
language zho
publishDate 2025-06-01
publisher Urban Mass Transit Magazine Press
record_format Article
series Chengshi guidao jiaotong yanjiu
spelling doaj-art-8cb0d70fcf324b3387cc929b05328a3f2025-08-20T03:29:23ZzhoUrban Mass Transit Magazine PressChengshi guidao jiaotong yanjiu1007-869X2025-06-01286323610.16037/j.1007-869x.20230612Metro Foundation Pit Deformation Prediction Method Based on CNN-GRU Neural Network under Incomplete Data ConditionZHOU Yi0WANG Zhangqiong1ZOU Yuangeng2CAI Yonghui3XU Xiaoya4ZHAO Qilin5School of Civil Engineering and Architecture, Wuhan Institute of Technology, 430074, Wuhan ChinaSchool of Civil Engineering and Architecture, Wuhan Institute of Technology, 430074, Wuhan ChinaSinohydro Engineering Bureau 8 Co., Ltd., 410004, Changsha, ChinaSchool of Civil Engineering and Architecture, Wuhan Institute of Technology, 430074, Wuhan ChinaSchool of Civil Engineering and Architecture, Wuhan Institute of Technology, 430074, Wuhan ChinaSchool of Civil Engineering and Architecture, Wuhan Institute of Technology, 430074, Wuhan China[Objective] To address the issues of prediction delay and accuracy degradation caused by incomplete deformation monitoring data in metro foundation pits, a prediction method based on a CNN-GRU (convolutional neural network-gated recurrent unit) neural network is proposed and verified. [Method] A data sample set is constructed using incomplete foundation pit deformation monitoring data and missing monitoring data from nearby monitoring points, and then input into the CNN model to complete data imputation and obtain continuous and complete monitoring data. Wavelet decomposition is applied to extract low-frequency trend components and high-frequency error components from the deformation data. The GRU neural network model and ARMA (autoregressive moving average) model are respectively used to predict the low-frequency trend and noise components, which are then combined to yield the final deformation prediction results. The foundation pit project at a metro station in Nanjing is used as case study to verify the effectiveness of the proposed method. [Result & Conclusion] When the proposed CNN-GRU-based prediction method is applied to foundation pit deformation data imputation with missing rates of 18.5% and 10.1%, the resulting prediction errors are 1.926 6% and 1.274 6%, respectively, and the prediction accuracy improves by 35% and 6%, respectively. These results demonstrate strong data recovery capability and high reliability of this method. Compared to the GA-BP neural network and LSTM prediction methods, the proposed method improves prediction accuracy by more than 100% and effectively addresses the issue of prediction lag. The accuracy of this method could meet the requirements of practical engineering applications.https://umt1998.tongji.edu.cn/journal/paper/doi/10.16037/j.1007-869x.20230612.htmlmetrofoundation pit deformation prediction methodcnn-gru neural networkincomplete data
spellingShingle ZHOU Yi
WANG Zhangqiong
ZOU Yuangeng
CAI Yonghui
XU Xiaoya
ZHAO Qilin
Metro Foundation Pit Deformation Prediction Method Based on CNN-GRU Neural Network under Incomplete Data Condition
Chengshi guidao jiaotong yanjiu
metro
foundation pit deformation prediction method
cnn-gru neural network
incomplete data
title Metro Foundation Pit Deformation Prediction Method Based on CNN-GRU Neural Network under Incomplete Data Condition
title_full Metro Foundation Pit Deformation Prediction Method Based on CNN-GRU Neural Network under Incomplete Data Condition
title_fullStr Metro Foundation Pit Deformation Prediction Method Based on CNN-GRU Neural Network under Incomplete Data Condition
title_full_unstemmed Metro Foundation Pit Deformation Prediction Method Based on CNN-GRU Neural Network under Incomplete Data Condition
title_short Metro Foundation Pit Deformation Prediction Method Based on CNN-GRU Neural Network under Incomplete Data Condition
title_sort metro foundation pit deformation prediction method based on cnn gru neural network under incomplete data condition
topic metro
foundation pit deformation prediction method
cnn-gru neural network
incomplete data
url https://umt1998.tongji.edu.cn/journal/paper/doi/10.16037/j.1007-869x.20230612.html
work_keys_str_mv AT zhouyi metrofoundationpitdeformationpredictionmethodbasedoncnngruneuralnetworkunderincompletedatacondition
AT wangzhangqiong metrofoundationpitdeformationpredictionmethodbasedoncnngruneuralnetworkunderincompletedatacondition
AT zouyuangeng metrofoundationpitdeformationpredictionmethodbasedoncnngruneuralnetworkunderincompletedatacondition
AT caiyonghui metrofoundationpitdeformationpredictionmethodbasedoncnngruneuralnetworkunderincompletedatacondition
AT xuxiaoya metrofoundationpitdeformationpredictionmethodbasedoncnngruneuralnetworkunderincompletedatacondition
AT zhaoqilin metrofoundationpitdeformationpredictionmethodbasedoncnngruneuralnetworkunderincompletedatacondition