A kernel principal component analysis-based approach for determining the spatial warning domain of dam safety
- PDF / 1,175,599 Bytes
- 11 Pages / 595.276 x 790.866 pts Page_size
- 29 Downloads / 269 Views
(0123456789().,-volV)(0123456789(). ,- volV)
METHODOLOGIES AND APPLICATION
A kernel principal component analysis-based approach for determining the spatial warning domain of dam safety Huaizhi Su1,2
•
Zhiping Wen3 • Jie Ren1,4
Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract It is important to determine the warning value of structural behavior for evaluating the service safety, identifying the potential risk and preventing the failure of dam engineering. However, more attention was paid to determining the security warning value of a single observation point on deformation, seepage or stress. And the correlation between the adjacent points or among all points in one dam section is usually lack of consideration. In this paper, the monitoring data of multipoints are taken to determine the spatial warning domain of dam safety. The warning mode of abnormal structural behavior is changed from the single point into the linked multi-points. First, the kernel principal component analysis method is adopted to identify the inherent characteristics among observation points in a dam section. Second, considering the correlation among observation points, the implementation process is proposed to determine the spatial warning domain of dam safety. Finally, an actual concrete gravity dam is taken as an example. The proposed approach is used to determine the spatial warning domains of deformation and seepage. The results, which are obtained by the proposed approach, the traditional method and the qualitative analysis for monitoring data, are compared. It is indicated that the proposed multipoints correlation-based approach is feasible and superior to determine the spatial warning domain of dam safety. Keywords Dam safety Structural behavior identification Spatial warning domain determination Monitoring data Kernel principal component analysis
1 Introduction According to monitoring data, it is an important way to monitor the service behavior of dams by determining the early warning index for monitoring effects of the dam (Sortis and Paoliani 2007; Wu et al. 2015). There are some traditional methods used to determine the warning index
Communicated by V. Loia. & Huaizhi Su [email protected] 1
State Key Laboratory of Hydrology-Water Resources and Hydraulic Engineering, Hohai University, Nanjing 210098, China
2
College of Water Conservancy and Hydropower Engineering, Hohai University, Nanjing, China
3
Department of Computer Engineering, Nanjing Institute of Technology, Nanjing, China
4
Geotechnical Engineering Department, Nanjing Hydraulic Research Institute, Nanjing, China
based on the monitoring data of single point, such as the small probability method, the confidence interval method and the structural analysis method (Gu and Wu 2006; Lei et al. 2011; Su et al. 2012, 2017; Liu et al. 2014). Taking the 13 # dam section of Foziling multi-arch concrete dam in China as an example (Gu and Wu 2006), the horizontal displacement monitoring index of the crest at was 5.28 mm, which was calculated
Data Loading...
