未找到相关数据
A multi-index fusion prediction method for dynamic seismic damage of an arch dam
被引：0
作者：
Qin, Lijun
[1
,2
]
Chen, Jianyun
[1
,2
]
Xu, Qiang
[1
,2
]
Cao, Xiangyu
[3
]
Li, Jing
[1
,2
]
机构：
[1] State Key Laboratory of Coastal and Offshore Engineering, Dalian University of Technology, Dalia,116024, China
[2] School of Hydraulic Engineering, Institute of Earthquake Engineering, Dalian University of Technology, Dalian,116024, China
[3] Nanjing Hydraulic Research Institute, Nanjing,210029, China
基金：
中国国家自然科学基金;
关键词：
Acceleration - Arch dams - Arches - Damage detection - Error analysis - Nanocantilevers - Seismology;
D O I：
暂无
中图分类号：
学科分类号：
摘要：
To establish the correlation between monitoring indexes and damage indexes for the purpose of rapid assessment of dam damage, this paper takes the Baihetan arch dam as an example and establishes a three-dimensional finite element model for dynamic analysis. Focusing on the crown cantilever, the study analyzes the correlation between different monitoring indexes and damage indexes using DCCA correlation coefficient, and constructs a Random Forest prediction model based on time history information of indexes. Using this model, the paper predicts the volume ratio of damage for the crown cantilever over time and its maximum value, comparing the results with those obtained from a model based on maximum value information, through error analysis. The results of the correlation analysis indicate a close relationship between the increase in the maximum upstream displacement, maximum upstream acceleration, and the widening of the transverse joint opening width, and the development of damage in the monolith. The error analysis results demonstrate that the prediction network established based on time history information performs well in both point prediction and interval prediction. The research presented in this paper provides a feasible approach for the comprehensive assessment of real-time seismic damage in arch dams. © 2024 Elsevier Ltd
引用
收藏
相关论文