Seite - 904 - in Book of Full Papers - Symposium Hydro Engineering

COMMISSION INTERNATIONALE DES GRANDS BARRAGES ------- VINGT-SIXIÈME CONGRÈS DES GRANDS BARRAGES Autriche, juillet 2018 ------- DAM DEFORMATION MONITORING MODEL AND FORECAST BASED ON PCA- RBF NEURAL NETWORK* Chaoning Lina, Tongchun Lib, Siyu Chena, Xiaoqing Liua, Siling Lianga aCollege of Water Resources and Hydropower Engineering, HOHAI UNIVERSITY bNational Engineering Research Center of Water Resources Efficient Utilization and Engineering Safety, HOHAI UNIVERSITY CHINA SUMMERY The safety assessment of a dam requires a wide range of information that is acquired from monitoring systems. Usually, there are many instruments equipped in the dam and its surroundings for monitoring the water level, temperature, deformation and other aspects. The behavior of the dam structure depends on the synergy of multiple factors. It is therefore necessary to detect the significant indicators that have a greater influence on the dam performance. In this paper, a monitoring model based on principal component analysis (PCA) and radial basis function (RBF) neural network is put forward to analyze the displacement trend of the concrete dam. The method of principal component is used to reduce the dimension of the dataset and simplify the multi- correlation of the components. On the basis, the in-situ monitoring displacement and the extracted components is taken as the input of the RBF neural network to build the forecasting model. An example analysis based on the proposed monitoring model is performed on a prototype concrete dam, and the results show that the proposed model is reasonable and practical. Keywords: Gravity dam; Monitoring; Numerical model; Safety 904