• Proceedings of the Korean Society for Quality Management Conference
• /
• 2009.10a
• /
• pp.3-10
• /
• 2009

When the measurement method for a performance variable is destructive or expensive, it is profitable to replace the performance variable with a highly correlated surrogate variable. In this paper we propose screening procedures using a surrogate variable with specified producer's and consumer's risks. Blending the basic concepts of acceptance sampling plans and screening procedures, the proposed model can be used effectively by quality professionals. Two models are considered: the normal model with dichotomous performance and continuous surrogate variables, and the bivariate normal model with continuous performance and surrogate variables. It is assumed the surrogate variable given the performance variable is normally distributed in the normal model, and performance and surrogate variables are jointly normally distributed in the bivariate normal model. For the two models, Producer's and consumer's risks are derived, and methods of finding the optimal screening procedures are presented. Numerical examples are also given.

• Journal of Korean Society for Quality Management
• /
• v.37 no.4
• /
• pp.23-30
• /
• 2009

When the measurement method for a performance variable is destructive or expensive, it is profitable to replace the performance variable with a highly correlated surrogate variable. In this paper we propose screening procedures using a surrogate variable with specified producer's and consumer's risks. Blending the basic concepts of acceptance sampling plans and screening procedures, the proposed model can be used effectively by quality professionals. Two models are considered: the normal model with dichotomous performance and continuous surrogate variables, and the bivariate normal model with continuous performance and surrogate variables. It is assumed the surrogate variable given the performance variable is normally distributed in the normal model, and performance and surrogate variables are jointly normally distributed in the bivariate normal model. For the two models, producer's and consumer's risks are derived, and methods of finding the optimal screening procedures are presented. Numerical examples are also given.

• Nuclear Engineering and Technology
• /
• v.49 no.6
• /
• pp.1219-1225
• /
• 2017

In this work, a scalable algorithm for model calibration in nuclear engineering applications is presented and tested. The algorithm relies on the construction of surrogate models to replace the original model within the region of interest. These surrogate models can be constructed efficiently via reduced order modeling and subspace analysis. Once constructed, these surrogate models can be used to perform computationally expensive mathematical analyses. This work proposes a surrogate based model calibration algorithm. The proposed algorithm is used to calibrate various neutronics and thermal-hydraulics parameters. The virtual environment for reactor applications-core simulator (VERA-CS) is used to simulate a three-dimensional core depletion problem. The proposed algorithm is then used to construct a reduced order model (a surrogate) which is then used in a Bayesian approach to calibrate the neutronics and thermal-hydraulics parameters. The algorithm is tested and the benefits of data assimilation and calibration are highlighted in an uncertainty quantification study and requantification after the calibration process. Results showed that the proposed algorithm could help to reduce the uncertainty in key reactor attributes based on experimental and operational data.

• Advances in Computational Design
• /
• v.1 no.3
• /
• pp.235-251
• /
• 2016

We have performed a design optimization of a stiffened panel with curvilinear stiffeners using an artificial neural network (ANN) residual kriging based surrogate modeling approach. The ANN residual kriging based surrogate modeling involves two steps. In the first step, we approximate the objective function using ANN. In the next step we use kriging to model the residue. We optimize the panel in an iterative way. Each iteration involves two steps-shape optimization and size optimization. For both shape and size optimization, we use ANN residual kriging based surrogate model. At each optimization step, we do an initial sampling and fit an ANN residual kriging model for the objective function. Then we keep updating this surrogate model using an adaptive sampling algorithm until the minimum value of the objective function converges. The comparison of the design obtained using our optimization scheme with that obtained using a traditional genetic algorithm (GA) based optimization scheme shows satisfactory agreement. However, with this surrogate model based approach we reach optimum design with less computation effort as compared to the GA based approach which does not use any surrogate model.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2010.11a
• /
• pp.19-23
• /
• 2010

Injection characteristics of a kerosene swirl injector of liquid rocket engine operating at supercritical environment have been investigated. Kerosene surrogate models are proposed to model the kerosene properties. Turbulent numerical model is based on large eddy simulation and contains Soave modification of Redlich-Kwong equation of state and Chung's model. Numerical analysis results at supercritical environment are compared with the one at transcritical condition. Differences of density and viscosity are analyzed at both liquid film and core gas in the swirl injector.

• Proceedings of the KSME Conference
• /
• 2008.11b
• /
• pp.2440-2443
• /
• 2008

This paper presents a three dimensional shape optimization procedure for a low-speed axial flow fan blade with a weighted average surrogate model. Reynolds-averaged Navier-Stokes equations with shear stress transport turbulence model are discretized by finite volume approximations. Six variables from airfoil profile and lean are selected as design variables. 3D RANS solver is used to evaluate the objective functions of total pressure efficiency. Surrogate approximation models for optimization have been employed to find the optimal design of fan blade. A search algorithm is used to find the optimal design in the design space from the constructed surrogate models for the objective function. The total pressure efficiency is increased by 0.31% with the weighted average surrogate model.

• Structural Engineering and Mechanics
• /
• v.41 no.1
• /
• pp.25-41
• /
• 2012

Kriging surrogate model provides explicit functions to represent the relationships between the inputs and outputs of a linear or nonlinear system, which is a desirable advantage for response estimation and parameter identification in structural design and model updating problem. However, little research has been carried out in applying Kriging model to crack identification. In this work, a scheme for crack identification based on a Kriging surrogate model is proposed. A modified rectangular grid (MRG) is introduced to move some sample points lying on the boundary into the internal design region, which will provide more useful information for the construction of Kriging model. The initial Kriging model is then constructed by samples of varying crack parameters (locations and sizes) and their corresponding modal frequencies. For identifying crack parameters, a robust stochastic particle swarm optimization (SPSO) algorithm is used to find the global optimal solution beyond the constructed Kriging model. To improve the accuracy of surrogate model, the finite element (FE) analysis soft ANSYS is employed to deal with the re-meshing problem during surrogate model updating. Specially, a simple method for crack number identification is proposed by finding the maximum probability factor. Finally, numerical simulations and experimental research are performed to assess the effectiveness and noise immunity of this proposed scheme.

• Transactions of Materials Processing
• /
• v.29 no.2
• /
• pp.89-96
• /
• 2020

The finite element method has been widely applied in the sheet metal forming process. However, the finite element method is computationally expensive and time consuming. In order to tackle this problem, surrogate modeling methods have been proposed. An artificial neural network (ANN) is one such surrogate model and has been well studied over the past decades. However, when it comes to ANN with two or more layers, so called deep neural networks (DNN), there is distinct a lack of research. We chose to use DNNs our surrogate model to predict the behavior of sheet metal in the deep drawing process. Thickness variation is selected as an output of the DNN in order to evaluate workpiece feasibility. Input variables of the DNN are radius of die, die corner and blank holder force. Finite element analysis was conducted to obtain data for surrogate model construction and testing. Sampling points were determined by full factorial, latin hyper cube and monte carlo methods. We investigated the performance of the DNN according to its structure, number of nodes and number of layers, then it was compared with a radial basis function surrogate model using various sampling methods and numbers. The results show that our DNN could be used as an efficient surrogate model for the deep drawing process.

• Smart Structures and Systems
• /
• v.17 no.4
• /
• pp.611-629
• /
• 2016

This study presents a new approach of surrogate modeling for time-consuming finite element analysis. A surrogate model is widely used to reduce the computational cost under an iterative computational analysis. Although a variety of the methods have been widely investigated, there are still difficulties in surrogate modeling from a practical point of view: (1) How to derive optimal design of experiments (i.e., the number of training samples and their locations); and (2) diagnostics of the surrogate model. To overcome these difficulties, we propose a sequential surrogate modeling based on Gaussian process model (GPM) with self-adaptive sampling. The proposed approach not only enables further sampling to make GPM more accurate, but also evaluates the model adequacy within a sequential framework. The applicability of the proposed approach is first demonstrated by using mathematical test functions. Then, it is applied as a substitute of the iterative finite element analysis to Monte Carlo simulation for a response uncertainty analysis under correlated input uncertainties. In all numerical studies, it is successful to build GPM automatically with the minimal user intervention. The proposed approach can be customized for the various response surfaces and help a less experienced user save his/her efforts.

• Smart Structures and Systems
• /
• v.26 no.2
• /
• pp.175-184
• /
• 2020

Conventional Monte Carlo simulation-based methods for seismic risk assessment of water networks often require excessive computational time costs due to the hydraulic analysis. In this study, an Artificial Neural Network-based surrogate model was proposed to efficiently evaluate the flow-based system reliability of water distribution networks. The surrogate model was constructed with appropriate training parameters through trial-and-error procedures. Furthermore, a deep neural network with hidden layers and neurons was composed for the high-dimensional network. For network training, the input of the neural network was defined as the damage states of the k-dimensional network facilities, and the output was defined as the network system performance. To generate training data, random sampling was performed between earthquake magnitudes of 5.0 and 7.5, and hydraulic analyses were conducted to evaluate network performance. For a hydraulic simulation, EPANET-based MATLAB code was developed, and a pressure-driven analysis approach was adopted to represent an unsteady-state network. To demonstrate the constructed surrogate model, the actual water distribution network of A-city, South Korea, was adopted, and the network map was reconstructed from the geographic information system data. The surrogate model was able to predict network performance within a 3% relative error at trained epicenters in drastically reduced time. In addition, the accuracy of the surrogate model was estimated to within 3% relative error (5% for network performance lower than 0.2) at different epicenters to verify the robustness of the epicenter location. Therefore, it is concluded that ANN-based surrogate model can be utilized as an alternative model for efficient seismic risk assessment to within 5% of relative error.