Comparative Study on Prediction Models for Crack Opening Degree in Concrete Dam

In recent years, classical statistical models and machine learning models have been developed in parallel in the field of dam safety monitoring. However, there are some deficiencies in the predictive power of the former and the theoretical explanation of the latter. In this study, multiple linear re...

Full description

Saved in:
Bibliographic Details
Main Authors: HUANG Song, WU Jie, FANG Zhanchao, CHU Huaping, WU Yan'gang, XUE Zilong, HE Linbo
Format: Article
Language:zho
Published: Editorial Office of Pearl River 2025-03-01
Series:Renmin Zhujiang
Subjects:
Online Access:http://www.renminzhujiang.cn/thesisDetails?columnId=76417573&Fpath=home&index=0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850252420322426880
author HUANG Song
WU Jie
FANG Zhanchao
CHU Huaping
WU Yan'gang
XUE Zilong
HE Linbo
author_facet HUANG Song
WU Jie
FANG Zhanchao
CHU Huaping
WU Yan'gang
XUE Zilong
HE Linbo
author_sort HUANG Song
collection DOAJ
description In recent years, classical statistical models and machine learning models have been developed in parallel in the field of dam safety monitoring. However, there are some deficiencies in the predictive power of the former and the theoretical explanation of the latter. In this study, multiple linear regression, stepwise regression, and random forest algorithm were used to establish models for the crack opening degree of a concrete gravity dam based on the monitoring data of the crack opening degree of the concrete gravity dam. The results show that three models for predicting crack opening degree are successfully established based on the crack opening degree dataset measured in 2022. The random forest model has the best predictive ability (determination coefficient (<italic>R</italic><sup>2</sup>) is 0.995; root mean square error (<italic>E</italic><sub>RMS</sub>) and mean absolute error (<italic>E</italic><sub>MA</sub>) are 0.174 mm and 0.124 mm, respectively), followed by the stepwise regression model (<italic>R</italic><sup>2</sup> is 0.989; <italic>E</italic><sub>RMS</sub><italic> </italic>and <italic>E</italic><sub>MA</sub><italic> </italic>are 0.192 mm and 0.151 mm). Three models both indicate that the temperature component is the main factor affecting the crack opening degree of the concrete gravity dam; by decomposing the multiple linear regression model item by item, the variation patterns of crack opening degree of the concrete gravity dam, temperature component, hydraulic pressure component, and time component are obtained. This study can provide a reference for the operation and management of the concrete gravity dam and the construction of the forecasting, early warning, drilling, and emergency plan (FEDE) platform, with a relatively high theoretical and practical significance.
format Article
id doaj-art-b4b96e5ef9d9433dbded1d67094bd78a
institution OA Journals
issn 1001-9235
language zho
publishDate 2025-03-01
publisher Editorial Office of Pearl River
record_format Article
series Renmin Zhujiang
spelling doaj-art-b4b96e5ef9d9433dbded1d67094bd78a2025-08-20T01:57:39ZzhoEditorial Office of Pearl RiverRenmin Zhujiang1001-92352025-03-0146253176417573Comparative Study on Prediction Models for Crack Opening Degree in Concrete DamHUANG SongWU JieFANG ZhanchaoCHU HuapingWU Yan'gangXUE ZilongHE LinboIn recent years, classical statistical models and machine learning models have been developed in parallel in the field of dam safety monitoring. However, there are some deficiencies in the predictive power of the former and the theoretical explanation of the latter. In this study, multiple linear regression, stepwise regression, and random forest algorithm were used to establish models for the crack opening degree of a concrete gravity dam based on the monitoring data of the crack opening degree of the concrete gravity dam. The results show that three models for predicting crack opening degree are successfully established based on the crack opening degree dataset measured in 2022. The random forest model has the best predictive ability (determination coefficient (<italic>R</italic><sup>2</sup>) is 0.995; root mean square error (<italic>E</italic><sub>RMS</sub>) and mean absolute error (<italic>E</italic><sub>MA</sub>) are 0.174 mm and 0.124 mm, respectively), followed by the stepwise regression model (<italic>R</italic><sup>2</sup> is 0.989; <italic>E</italic><sub>RMS</sub><italic> </italic>and <italic>E</italic><sub>MA</sub><italic> </italic>are 0.192 mm and 0.151 mm). Three models both indicate that the temperature component is the main factor affecting the crack opening degree of the concrete gravity dam; by decomposing the multiple linear regression model item by item, the variation patterns of crack opening degree of the concrete gravity dam, temperature component, hydraulic pressure component, and time component are obtained. This study can provide a reference for the operation and management of the concrete gravity dam and the construction of the forecasting, early warning, drilling, and emergency plan (FEDE) platform, with a relatively high theoretical and practical significance.http://www.renminzhujiang.cn/thesisDetails?columnId=76417573&Fpath=home&index=0concrete damcrack opening degreestatistical modelrandom forest algorithm
spellingShingle HUANG Song
WU Jie
FANG Zhanchao
CHU Huaping
WU Yan'gang
XUE Zilong
HE Linbo
Comparative Study on Prediction Models for Crack Opening Degree in Concrete Dam
Renmin Zhujiang
concrete dam
crack opening degree
statistical model
random forest algorithm
title Comparative Study on Prediction Models for Crack Opening Degree in Concrete Dam
title_full Comparative Study on Prediction Models for Crack Opening Degree in Concrete Dam
title_fullStr Comparative Study on Prediction Models for Crack Opening Degree in Concrete Dam
title_full_unstemmed Comparative Study on Prediction Models for Crack Opening Degree in Concrete Dam
title_short Comparative Study on Prediction Models for Crack Opening Degree in Concrete Dam
title_sort comparative study on prediction models for crack opening degree in concrete dam
topic concrete dam
crack opening degree
statistical model
random forest algorithm
url http://www.renminzhujiang.cn/thesisDetails?columnId=76417573&Fpath=home&index=0
work_keys_str_mv AT huangsong comparativestudyonpredictionmodelsforcrackopeningdegreeinconcretedam
AT wujie comparativestudyonpredictionmodelsforcrackopeningdegreeinconcretedam
AT fangzhanchao comparativestudyonpredictionmodelsforcrackopeningdegreeinconcretedam
AT chuhuaping comparativestudyonpredictionmodelsforcrackopeningdegreeinconcretedam
AT wuyangang comparativestudyonpredictionmodelsforcrackopeningdegreeinconcretedam
AT xuezilong comparativestudyonpredictionmodelsforcrackopeningdegreeinconcretedam
AT helinbo comparativestudyonpredictionmodelsforcrackopeningdegreeinconcretedam