Construction and selection of deformation monitoring model for high arch dam using separate modeling technique and composite decision criterion.

Chen, Rengui; Wu, Zhenyu

Deformation prediction is important to ensure the safe and stable operation of arch dams. Statistical models are extensively applied in arch dam deformation monitoring models, which generally include hydrostatic pressure component, temperature component, and aging (irrecoverable) component. In traditional statistical models, aging component is misset, which will cause unreasonable mutual compensation of each component, resulting in overfitting of the overall model. In this paper, the deformation model based on separate modeling technology is, therefore, proposed mitigating the overfitting problem caused by misspecification of the expression of the aging component in traditional statistical models. Dam deformation components related to different effects are extracted from the deformation monitoring sequence with improved complete ensemble empirical mode decomposition with adaptive noise algorithm and equal water level condition. The correct components of the monitoring model are constructed separately. On the one hand, the fitting accuracy of the model is reflected by the coefficient of determination (R 2); on the other hand, the overfitting degree of the model is quantitatively evaluated by the overfitting coefficient (OC), so that the model with high fitting accuracy and prediction accuracy is determined, that is, the optimal model is selected by using the R 2-OC criterion. In this paper, displacement monitoring data from measurement points are used for analysis. The results show that the deformation monitoring model based on the separated modeling technique exhibits higher prediction accuracy and lower false alarm rate. The R 2-OC criterion better reflects the degree of overfitting of the monitoring model and the real situation of arch dam monitoring and warning, which improves the accuracy of model selection.

ARCH dams; HYDROSTATIC pressure; WATER levels; STATISTICAL models

Structural Health Monitoring, 2024, Vol 23, Issue 4, p2509

1475-9217

Academic Journal

10.1177/14759217231203243