Variable fidelity design based surrogate and artificial bee colony algorithm for sheet metal forming process

Crashworthiness analysis and design of multi-cell hexagonal columns under multiple loading cases

“…Design of Experiment (DoE) has been a widely-used technique to address how to select minimum number of training points for mapping the entire design space properly. In this study, the optimal Latin Hypercube sampling (OLHS) [48,49] is employed to generate 80 training points, because it can efficiently generate uniformly-distributed sampling points. Then, the EA and F max at these training points are evaluated using FEA.…”

An adaptive global variable fidelity metamodeling strategy using a support vector regression based scaling function

“…Generally, type 1 and type 2 can be used in local VF modeling approaches, type 2 can also be used globally by adopting global metamodels to approximate the scaling function Cðx; aÞ, e.g., Kriging scaling [20][21][22], RBF scaling methods [23][24][25], etc. These two types of VF metamodeling have been successfully applied to the field of design optimization, and type 3 is based on a deeper understanding of a process being modeled, which can be useful but is problem dependent.…”

“…The main shortcoming of these approaches is that they are only suitable for local optimization problems [17][18][19]. While in global VF modeling approaches, the scaling function is approximated using global metamodels, e.g., Kriging scaling methods [20][21][22], RBF scaling methods [23][24][25] and Bayesian-Gaussian scaling methods [19,[26][27][28]. Since global VF modeling approaches can mimic the behavior of the system on the entire domain and cope with multiple optimum problems sophisticatedly, there has been widespread concern about these approaches [12,29].…”

Performance Comparison of Parametric and Non-Parametric Regression Models for Uncertainty Analysis of Sheet Metal Forming Processes

“…In particular, the 2 of 12 artificial neural network (ANN), support vector machine (SVM), and Gaussian process (GPs) have been applied to various sheet metal forming processes. Sun et al [3] applied SVM, alongside RSM and Kriging (a particular case of GP), in the optimization of the forming process of an automobile inner panel. Teimouri et al [4] explored various ANN algorithms in a springback optimization problem, and compared them with the RSM, concluding that the ANN algorithms showed better performance.…”