The Surrogate Model

Author(s):  
Francesco Archetti ◽  
Antonio Candelieri
Keyword(s):  
Author(s):  
Marcelo Salles Olinger ◽  
Ana Paula Melo ◽  
Letícia Oliveira Neves ◽  
Roberto Lamberts

Water ◽  
2021 ◽  
Vol 13 (1) ◽  
pp. 87
Author(s):  
Yongqiang Wang ◽  
Ye Liu ◽  
Xiaoyi Ma

The numerical simulation of the optimal design of gravity dams is computationally expensive. Therefore, a new optimization procedure is presented in this study to reduce the computational cost for determining the optimal shape of a gravity dam. Optimization was performed using a combination of the genetic algorithm (GA) and an updated Kriging surrogate model (UKSM). First, a Kriging surrogate model (KSM) was constructed with a small sample set. Second, the minimizing the predictor strategy was used to add samples in the region of interest to update the KSM in each updating cycle until the optimization process converged. Third, an existing gravity dam was used to demonstrate the effectiveness of the GA–UKSM. The solution obtained with the GA–UKSM was compared with that obtained using the GA–KSM. The results revealed that the GA–UKSM required only 7.53% of the total number of numerical simulations required by the GA–KSM to achieve similar optimization results. Thus, the GA–UKSM can significantly improve the computational efficiency. The method adopted in this study can be used as a reference for the optimization of the design of gravity dams.


Author(s):  
Lorenzo Scandola ◽  
Christoph Büdenbender ◽  
Michael Till ◽  
Daniel Maier ◽  
Michael Ott ◽  
...  

AbstractThe optimal design of the tools in bulk metal forming is a crucial task in the early design phase and greatly affects the final accuracy of the parts. The process of tool geometry assessment is resource- and time-consuming, as it consists of experience-based procedures. In this paper, a compensation method is developed with the aim to reduce geometrical deviations in hot forged parts. In order to simplify the transition process between the discrete finite-element (FE) mesh and the computer-aided-design (CAD) geometry, a strategy featuring an equivalent surrogate model is proposed. The deviations are evaluated on a reduced set of reference points on the nominal geometry and transferred to the FE nodes. The compensation approach represents a modification of the displacement-compatible spring-forward method (DC-SF), which consists of two elastic FE analyses. The compatible stress originating the deviations is estimated and subsequently applied to the original nominal geometry. After stress relaxation, an updated nominal geometry of the part is obtained, whose surfaces represent the compensated tools. The compensation method is verified by means of finite element simulations and the robustness of the algorithm is demonstrated with an additional test geometry. Finally, the compensation strategy is validated experimentally.


2021 ◽  
Vol 1043 (5) ◽  
pp. 052049
Author(s):  
X Zhang ◽  
H Li ◽  
G Xiang ◽  
H W Xu
Keyword(s):  

Sign in / Sign up

Export Citation Format

Share Document