Abstract
The creep parameters of rockfill materials obtained from engineering analogy method or indoor tests often cannot accurately reflect the long-term deformation of high Concrete-Faced Rockfill Dams (CFRDs). This paper introduces an optimized inversion method based on multi-population genetic algorithm-improved BP neural network and response surface method (MPGA-BPNN RSM). The parameters used for inversion are determined by parameter sensitivity analysis based on the statistical orthogonal test method. MPGA-BPNN RSM, validated by root-mean-square error, mean absolute percentage error, squared correlation coefficient (R2), etc., completely reflects the response between the creep parameters and the settlement calculation values obtained by finite element method (FEM). MPGA optimized the objective function to obtain the optimal creep parameters. The results show that the settlement values of Xujixia CFRD calculated by FEM using the inversion parameters has great consistency with the monitored values both in size and in distribution, suggesting that the model parameters obtained by the introduced creep parameter inversion method are feasible and effective. The introduced method can improve the inversion efficiency and the prediction accuracy in FEM applications.
Highlights
High Concrete Faced Rockfill Dams (CFRDs) has become one of the most popular dams in water conservancy projects due to the advantages of strong terrain capability, low cost, convenient construction, and short construction circle (Sukkarak et al 2017; Xu et al 2012)
This paper introduced an optimized inversion method for creep parameters with MPGA-BPNN RSM
MPGA-BPNN RSM established the relationship between creep parameters and Finite Element Method (FEM) settlement increment, which can improve the accuracy of inversion
Summary
High Concrete Faced Rockfill Dams (CFRDs) has become one of the most popular dams in water conservancy projects due to the advantages of strong terrain capability, low cost, convenient construction, and short construction circle (Sukkarak et al 2017; Xu et al 2012). The creep parameters determined by engineering analogy (Huang et al 2015) and indoor test with size effect (Shao et al 2020; Zhou et al 2019) often fail to reflect the actual longterm deformation characteristics of the target dam. It is necessary for the inversion of model parameters based on the monitoring data. Section (4) introduces the specific implementation process of parameter inversion based on MPGA-BPNN RSM and MPGA optimization theory in detail. Section (5) and (6) are discussions of some future research and conclusions, improving the efficiency and accuracy of parameter inversion
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have