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：2018
卷号：189
期号：2
页码：022018
DOI：10.1088/1755-1315/189/2/022018
语种：English
出版社：IOP Publishing
摘要：To realize real-time forecast and early-warning of osmotic pressure of concrete-faced rockfill dams, this research analyses factors that influence fluctuation of osmotic pressure and builds a statistical model for the osmotic pressure. A three-layer RBF neural network-based osmotic pressure forecast model for the concrete-faced rockfill dam is built with the 16 standardized variables as input-layer factors and the osmotic pressure as the output-layer factor. With 12 groups of actually-measured data from different sections of the dam as samples, this research analyses the fitting and forecast accuracy of the model via SPSS and the RBF neural network. In light of actual engineering demand, the model is applied to the 3D visual monitoring information system, and with the early-warning indicators determined, it can realize real-time monitoring.
Loading...
