期刊名称：IOP Conference Series: Earth and Environmental Science
印刷版ISSN：1755-1307
电子版ISSN：1755-1315
出版年度：2020
卷号：474
期号：7
DOI：10.1088/1755-1315/474/7/072003
语种：English
出版社：IOP Publishing
摘要：The high-performance concrete dam deformation prediction model serves as an important reference for structural safety behavior diagnosis, early warning, and scientific decision-making, and it is also one of the guarantee measures to fully exert the benefits of the project. This paper aims at the subjectivity of factor selection, multicollinearity among factors, and poor generalization of the concrete dam deformation monitoring model. It combines rough set and random forest theory to achieve feature attribute reduction, importance evaluation, and high-precision prediction. In terms of rough set and random forest advantages, a concrete dam deformation prediction model based on RS-RF was established. The application of engineering examples shows that the deformation monitoring model of concrete dams based on RS-RF can reduce the influence factor set, give the importance of each factor, and do well than commonly used models based on SVM and RF in prediction accuracy. Therefore, the deformation prediction model of concrete dam based on RS-RF achieves optimization of influence factors, which makes up for the shortcomings of intelligent prediction model in quantitative analysis and prediction generalization, and has strong engineering practicability.
