Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter Optimization
In this study, a seepage prediction model was established for roller-compacted concrete dams using support vector regression (SVR) with hybrid parameter optimization (HPO). The model includes data processing via HPO and machine learning through SVR. HPO benefits from the correlation extraction capab...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-10-01
|
Series: | Water |
Subjects: | |
Online Access: | https://www.mdpi.com/2073-4441/15/19/3511 |
_version_ | 1797575123734102016 |
---|---|
author | Mei-Yan Zhuo Jinn-Chyi Chen Ren-Ling Zhang Yan-Kun Zhan Wen-Sun Huang |
author_facet | Mei-Yan Zhuo Jinn-Chyi Chen Ren-Ling Zhang Yan-Kun Zhan Wen-Sun Huang |
author_sort | Mei-Yan Zhuo |
collection | DOAJ |
description | In this study, a seepage prediction model was established for roller-compacted concrete dams using support vector regression (SVR) with hybrid parameter optimization (HPO). The model includes data processing via HPO and machine learning through SVR. HPO benefits from the correlation extraction capability of grey relational analysis and the dimensionality reduction technique of principal component analysis. The proposed model was trained, validated, and tested using 22 years of monitoring data regarding the Shuidong Dam in China. We compared the performance of HPO with other popular methods, while the SVR method was compared with the traditional time-series prediction method of long short-term memory (LSTM). Our findings reveal that the HPO method proves valuable real-time dam safety monitoring during data processing. Meanwhile, the SVR method demonstrates superior robustness in predicting seepage flowrate post-dam reinforcement, compared with LSTM. Thus, the developed model effectively identifies the factors related to seepage and exhibits high accuracy in predicting fluctuation trends regarding the Shuidong Dam, achieving a determination coefficient <i>R</i><sup>2</sup> > 0.9. Further, the model can provide valuable guidance for dam safety monitoring, including diagnosing the efficacy of monitoring parameters or equipment, evaluating equipment monitoring frequency, identifying locations sensitive to dam seepage, and predicting seepage. |
first_indexed | 2024-03-10T21:33:00Z |
format | Article |
id | doaj.art-f7b15b2f7e10450b866fb36a07409ac7 |
institution | Directory Open Access Journal |
issn | 2073-4441 |
language | English |
last_indexed | 2024-03-10T21:33:00Z |
publishDate | 2023-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Water |
spelling | doaj.art-f7b15b2f7e10450b866fb36a07409ac72023-11-19T15:15:51ZengMDPI AGWater2073-44412023-10-011519351110.3390/w15193511Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter OptimizationMei-Yan Zhuo0Jinn-Chyi Chen1Ren-Ling Zhang2Yan-Kun Zhan3Wen-Sun Huang4School of Hydraulic Engineering, Fujian College of Water Conservancy and Electric Power, Yongan 366000, ChinaSchool of Hydraulic Engineering, Fujian College of Water Conservancy and Electric Power, Yongan 366000, ChinaFujian Shuikou Power Generation Group, Youxi Basin Power Generation Co., Ltd., Sanming 365100, ChinaFujian Shuikou Power Generation Group, Youxi Basin Power Generation Co., Ltd., Sanming 365100, ChinaSchool of Hydraulic Engineering, Fujian College of Water Conservancy and Electric Power, Yongan 366000, ChinaIn this study, a seepage prediction model was established for roller-compacted concrete dams using support vector regression (SVR) with hybrid parameter optimization (HPO). The model includes data processing via HPO and machine learning through SVR. HPO benefits from the correlation extraction capability of grey relational analysis and the dimensionality reduction technique of principal component analysis. The proposed model was trained, validated, and tested using 22 years of monitoring data regarding the Shuidong Dam in China. We compared the performance of HPO with other popular methods, while the SVR method was compared with the traditional time-series prediction method of long short-term memory (LSTM). Our findings reveal that the HPO method proves valuable real-time dam safety monitoring during data processing. Meanwhile, the SVR method demonstrates superior robustness in predicting seepage flowrate post-dam reinforcement, compared with LSTM. Thus, the developed model effectively identifies the factors related to seepage and exhibits high accuracy in predicting fluctuation trends regarding the Shuidong Dam, achieving a determination coefficient <i>R</i><sup>2</sup> > 0.9. Further, the model can provide valuable guidance for dam safety monitoring, including diagnosing the efficacy of monitoring parameters or equipment, evaluating equipment monitoring frequency, identifying locations sensitive to dam seepage, and predicting seepage.https://www.mdpi.com/2073-4441/15/19/3511support vector regressionhybrid parameter optimizationgrey relational analysisprincipal component analysisroller-compacted concrete damseepage |
spellingShingle | Mei-Yan Zhuo Jinn-Chyi Chen Ren-Ling Zhang Yan-Kun Zhan Wen-Sun Huang Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter Optimization Water support vector regression hybrid parameter optimization grey relational analysis principal component analysis roller-compacted concrete dam seepage |
title | Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter Optimization |
title_full | Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter Optimization |
title_fullStr | Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter Optimization |
title_full_unstemmed | Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter Optimization |
title_short | Seepage Prediction Model for Roller-Compacted Concrete Dam Using Support Vector Regression and Hybrid Parameter Optimization |
title_sort | seepage prediction model for roller compacted concrete dam using support vector regression and hybrid parameter optimization |
topic | support vector regression hybrid parameter optimization grey relational analysis principal component analysis roller-compacted concrete dam seepage |
url | https://www.mdpi.com/2073-4441/15/19/3511 |
work_keys_str_mv | AT meiyanzhuo seepagepredictionmodelforrollercompactedconcretedamusingsupportvectorregressionandhybridparameteroptimization AT jinnchyichen seepagepredictionmodelforrollercompactedconcretedamusingsupportvectorregressionandhybridparameteroptimization AT renlingzhang seepagepredictionmodelforrollercompactedconcretedamusingsupportvectorregressionandhybridparameteroptimization AT yankunzhan seepagepredictionmodelforrollercompactedconcretedamusingsupportvectorregressionandhybridparameteroptimization AT wensunhuang seepagepredictionmodelforrollercompactedconcretedamusingsupportvectorregressionandhybridparameteroptimization |