• Transactions of Materials Processing
• /
• v.27 no.1
• /
• pp.28-36
• /
• 2018

Electromagnetic forming is a type of high-speed forming process to deform a workpiece through a Lorentz force. As the high strain rate in an electromagnetic-forming simulation causes infeasibility in determining constitutive parameters, we employed inverse parameter estimation in the previous study. However, the inverse parameter estimation process required us to spend considerable time, which leads to an increase in computational cost. To overcome the computational obstacle, in this research, we applied two types of surrogate modeling methods and compared them to each other to evaluate which model is best for the electromagnetic-forming simulation. We exploited an artificial neural network and we reduced-order modeling methods. During the construction of a reduced-order model, we extracted orthogonal bases with proper orthogonal decomposition and predicted basis coefficients by utilizing an artificial neural network. After the construction of the surrogate models, we verified the artificial neural network and reduced-order models through training and testing samples. As a result, we determined the artificial neural network model is slightly more accurate than the reduced-order model. However, the construction of the artificial neural network model requires a considerably larger amount of time than that of the reduced-order model. Thus, a reduced order modeling method is more efficient than an artificial neural network for estimating the electromagnetic forming and for the rapid approximation of structural simulations which needs repetitive runs.

• Smart Structures and Systems
• /
• v.32 no.1
• /
• pp.61-81
• /
• 2023

This study presents an ensemble learning based Bayesian model updating approach for structural damage diagnosis. In the developed framework, the structure is initially decomposed into a set of substructures. The autoregressive moving average (ARMAX) model is established first for structural damage localization based structural motion equation. The wavelet packet decomposition is utilized to extract the damage-sensitive node energy in different frequency bands for constructing structural surrogate models. Four methods, including Kriging predictor (KRG), radial basis function neural network (RBFNN), support vector regression (SVR), and multivariate adaptive regression splines (MARS), are selected as candidate structural surrogate models. These models are then resampled by bootstrapping and combined to obtain an ensemble model by probabilistic ensemble. Meanwhile, the maximum entropy principal is adopted to search for new design points for sample space updating, yielding a more robust ensemble model. Through the iterations, a framework of surrogate ensemble learning based model updating with high model construction efficiency and accuracy is proposed. The specificities of the method are discussed and investigated in a case study.

• 유체기계공업학회:학술대회논문집
• /
• 2006.08a
• /
• pp.543-544
• /
• 2006

Shape optimization of a transonic axial compressor rotor operating at the design flow condition has been performed using three-dimensional Navier-Stokes analysis and three different surrogate models: i.e.., Response Surface Method(RSM), Kriging Method, and Radial Basis Function(RBF). Three design variables of blade sweep, lean and skew are introduced to optimize the three-dimensional stacking line of the rotor blade. The object function of the shape optimization is selected as an adiabatic efficiency. Throughout the shape optimization of the rotor blade, the adiabatic efficiency is increased for the three different surrogate models. Detailed flow characteristics at the optimal blade shape obtained by different optimization method are drawn and discussed.

• 한국전산유체공학회:학술대회논문집
• /
• 2010.05a
• /
• pp.187-194
• /
• 2010

Shape optimization of an upper plenum of PBMR type gas cooled nuclear reactor has been performed by using three-dimensional Reynolds-Averaged Navier-Stokes (RANS) analysis and surrogate modeling technique. The objective function is defined as a linear combination of uniformity of flow distribution in the core and pressure drop in the upper plenum and the core. The ratio of thickness of slot to diameter of rising channels, ratio of height of upper plenum to diameter of rising channels, and ratio of eight of the slot at inlet to outlet, are used as design variables for optimization. Design points are selected through Latin-hypercube sampling. The optimal point is determined through surrogate-based optimization method which uses 3-D RANS analyses at design points. The results show that the optimum shape represent remarkably improved performance in flow uniformity and friction loss than the reference shape.

• Journal of computational fluids engineering
• /
• v.15 no.3
• /
• pp.16-23
• /
• 2010

Shape optimization of an upper plenum of a PBMR type gas cooled nuclear reactor has been performed by using three-dimensional Reynolds-Averaged Navier-Stokes (RANS) analysis and surrogate modeling technique. The objective function is defined as a linear combination of uniformity of flow distribution in the core and pressure drop in the upper plenum and the core. The ratio of thickness of slot to diameter of rising channels, ratio of height of upper plenum to diameter of rising channels, and ratio of height of the slot at inlet to outlet, are used as design variables for optimization. Design points are selected through Latin-hypercube sampling. The optimal point is determined through surrogate-based optimization method which uses 3-D RANS analyses at design points. The results show that the optimum shape represent remarkably improved performance in flow uniformity and friction loss than the reference shape.

• The KSFM Journal of Fluid Machinery
• /
• v.11 no.1
• /
• pp.52-60
• /
• 2008

Staggered dimples printed on opposite walls of an internal cooling channel are formulated numerically and optimized to enhance heat transfer performance. Nusselt number and friction factor based objectives are considered and a weighted average surrogate model is used to approximate the data generated by numerical simulation. The dimpled channel shape is defined by three geometric design variables, and the design point within design space are selected using Latin hypercube sampling. A weighted-sum method for multi-objective optimization is applied to integrate multiple objectives into a single objective. By the optimization, the objective function value is improved largely and heat transfer rate is increase much higher than pressure loss increase due to shape deformation. Channel with vertically non-symmetric optimum dimples is tested and found that the best appears if dimples on opposite wall are displaced by one quarter of dimple spacing.

• Management Science and Financial Engineering
• /
• v.8 no.2
• /
• pp.21-31
• /
• 2002

In this paper, we explore a new class of cutting planes by extending the concept of fractional S-K (S-K) cuts. This class of cuts is derived by applying a suitable surrogate constraint analysis that incorporates a special multiplier adjustment method to the generalized Gomory's fractional cut. We present computational results to provide insights into the performance of these cuts in comparison with other well known classes of cuts.

• Management Science and Financial Engineering
• /
• v.18 no.2
• /
• pp.13-17
• /
• 2012

Set covering has widely been accepted as a staple tool for feature selection in data mining. We present a generalized version of this classical combinatorial optimization model to make it better suited for the purpose and propose a surrogate relaxation-based procedure for its meta-heuristic solution. Mathematically and also numerically with experiments on 25 set covering instances, we demonstrate the utility of the proposed model and the proposed solution method.

• Structural Engineering and Mechanics
• /
• v.66 no.6
• /
• pp.677-691
• /
• 2018

Reliability assessment of complex structures using simulation methods is time-consuming. Thus, surrogate models are usually employed to reduce computational cost. AK-MCS is a surrogate-based Active learning method combining Kriging and Monte-Carlo Simulation for structural reliability analysis. This paper proposes three modifications of the AK-MCS method to reduce the number of calls to the performance function. The first modification is related to the definition of an initial Design of Experiments (DoE). In the original AK-MCS method, an initial DoE is created by a random selection of samples among the Monte Carlo population. Therefore, samples in the failure region have fewer chances to be selected, because a small number of samples are usually located in the failure region compared to the safe region. The proposed method in this paper is based on a uniform selection of samples in the predefined domain, so more samples may be selected from the failure region. Another important parameter in the AK-MCS method is the size of the initial DoE. The algorithm may not predict the exact limit state surface with an insufficient number of initial samples. Thus, the second modification of the AK-MCS method is proposed to overcome this problem. The third modification is relevant to the type of regression trend in the AK-MCS method. The original AK-MCS method uses an ordinary Kriging model, so the regression part of Kriging model is an unknown constant value. In this paper, the effect of regression trend in the AK-MCS method is investigated for a benchmark problem, and it is shown that the appropriate choice of regression type could reduce the number of calls to the performance function. A stepwise approach is also presented to select a suitable trend of the Kriging model. The numerical results show the effectiveness of the proposed modifications.

• Nuclear Engineering and Technology
• /
• v.52 no.2
• /
• pp.287-295
• /
• 2020

Group method of data handling (GMDH) is considered one of the earliest deep learning methods. Deep learning gained additional interest in today's applications due to its capability to handle complex and high dimensional problems. In this study, multi-layer GMDH networks are used to perform uncertainty quantification (UQ) and sensitivity analysis (SA) of nuclear reactor simulations. GMDH is utilized as a surrogate/metamodel to replace high fidelity computer models with cheap-to-evaluate surrogate models, which facilitate UQ and SA tasks (e.g. variance decomposition, uncertainty propagation, etc.). GMDH performance is validated through two UQ applications in reactor simulations: (1) low dimensional input space (two-phase flow in a reactor channel), and (2) high dimensional space (8-group homogenized cross-sections). In both applications, GMDH networks show very good performance with small mean absolute and squared errors as well as high accuracy in capturing the target variance. GMDH is utilized afterward to perform UQ tasks such as variance decomposition through Sobol indices, and GMDH-based uncertainty propagation with large number of samples. GMDH performance is also compared to other surrogates including Gaussian processes and polynomial chaos expansions. The comparison shows that GMDH has competitive performance with the other methods for the low dimensional problem, and reliable performance for the high dimensional problem.