Open AccessPredicting Maximum Crest Settlement of Concrete Face Rockfill Dams Using a New Ensemble Learning Model
Author(s) -
Lifeng Wen,
Haiyang Zhang,
Yanlong Li
Publication year - 2021
Publication title -
iop conference series. earth and environmental science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.179
H-Index - 26
eISSN - 1755-1307
pISSN - 1755-1315
DOI - 10.1088/1755-1315/643/1/012071
Subject(s) - crest , settlement (finance) , generalization , face (sociological concept) , support vector machine , computer science , nonlinear system , ensemble learning , deformation (meteorology) , ensemble forecasting , regression analysis , artificial intelligence , geotechnical engineering , engineering , machine learning , geology , mathematics , mathematical analysis , social science , oceanography , physics , quantum mechanics , sociology , world wide web , payment
Deformation assessment and control are essential issues in the construction of concrete face rockfill dams (CFRDs). The design and construction of CFRDs require deformation behavior that can be estimated rapidly to support engineering optimization and safety assessment. Based on 87 case histories of in-service CFRDs, a new ensemble learning model has been developed to predict maximum crest settlement ( CS ) of CFRDs. The model is based on the support vector machine regression algorithm (SVR) combined with multiple variables, and then the foundation model is integrated by the weighted average integration method. It is demonstrated here that the new ensemble learning model weakens the nonlinear characteristics of case data, makes up for the instability of single regression algorithm, improves the generalization ability, and provides a new idea for predicting the CS of CFRDs.