Search

It is very important to estimate the mechanical parameters based on monitoring data for investigating the operation behavior of concrete dams. In this paper, an advanced Bayesian parameter estimation method for concrete dams is proposed. The Empirical Mode Decomposition (EMD) is adopted to extract the aging component of the observed deformation sequence, and the hydrostatic component is separated from the remaining periodic term through the statistical regression model (SRM). A hybrid response surface method (HRSM) is proposed as a surrogate model for finite element method (FEM) simulation. The likelihood function, which reflects the error between the observed and simulated deformation, is constructed, then the Bayesian formula for parameter estimation is established. The transitional Markov chain Monte Carlo (TMCMC) algorithm is used to obtain the parameter posterior distribution. The proposed method is applied to estimate the elastic modulus of the GD concrete dam, the parameter posterior distribution is obtained through the fusion of monitoring information and parameter prior information. This method can also avoid the issues of multiple solutions and unreasonable parameter combinations, which may exist in traditional deterministic inversion methods. The case study shows that the proposed method has good applicability in the parameter estimation of concrete dams. [ABSTRACT FROM AUTHOR]

• Data-based models with EMD are proposed for deformation monitoring of concrete dams. • The proposed models can well simulate the irreversible component of concrete dam deformation and significantly decrease the over-fitting levels. • A new model selection criterion, namely Over-fitting coefficient, is proposed for evaluating and selecting dam health monitoring models. • The Over-fitting coefficient can better reflect over-fitting levels of individual monitoring models compared to traditional model selection criteria. Data-based models are extensively applied in concrete dam health monitoring. In this paper, the Empirical Mode Decomposition (EMD) is adopted to extract and visualize the irreversible component of deformation monitoring sequence. Consequently proper mathematical formulation of the irreversible component of deformation monitoring model for concrete dams can be established, and the problem of improperly assuming the mathematical form of irreversible component when constructing data-based models is well addressed. The periodic component of the deformation time series is modelled by regression and three machine learning algorithms (i.e., Extreme learning machine, Support Vector Machine based on Grid search and Cross-Verification, and Back Propagation Neural Networks optimized by Genetic Algorithm and Simulated Annealing) respectively. The data-based models with the EMD are able to effectively improve the performance of formulating irreversible component of concrete dam deformation and decrease the over-fitting levels. A new model selection criterion, namely Over-fitting coefficient, is proposed for evaluating and selecting the optimum model among candidate monitoring models. The Over-fitting coefficient can better reflect over-fitting levels of individual monitoring models compared to traditional model selection criteria. As a case study, the displacement and strain monitoring data from the YL gravity dam are modeled by data-based models with the EMD and machine learning algorithms. It is shown that data-based models with the EMD are of higher prediction accuracy and lower rate of false alarm in deformation monitoring than traditional models. The Over-fitting coefficient can better reflect over-fitting levels of monitoring models compared to the error measurement criteria and information criteria. The case study highlights the merits of the proposed data-based models and the model selection criterion for health monitoring of concrete dams. [ABSTRACT FROM AUTHOR]