• 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.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.12 no.6
• /
• pp.461-468
• /
• 2002

Computer simulation is essential to design the suspension elements of railway vehicle. By computer simulation, engineers can assess the feasibility of the given design factors and change them to get a better design. But if one wishes to perform complex analysis on the simulation, such as railway vehicle dynamic, the computational time can become overwhelming. Therefore, many researchers have used a surrogate model that has a regression model performed on a data sampling of the simulation. In general, metamodels(surrogate model) take the form y($\chi$)＝f($\chi$)＋$\varepsilon$, where y($\chi$) is the true output, f($\chi$) is the metamodel output, and is the error. In this paper, a second order polynomial equation is used as the RSM(response surface model) for high speed train that have twenty-nine design variables and forty-six responses. After the RSM is constructed, multi-objective optimal solutions are achieved by using a nonlinear programming method called VMM(variable matric method) This paper shows that the RSM is a very efficient model to solve the complex optimization problem.

• Communications for Statistical Applications and Methods
• /
• v.24 no.4
• /
• pp.383-396
• /
• 2017

The model in our approach assumes that computer responses are a realization of a Gaussian processes superimposed on a regression model called a Gaussian process regression model (GPRM). Selecting a subset of variables or building a good reduced model in classical regression is an important process to identify variables influential to responses and for further analysis such as prediction or classification. One reason to select some variables in the prediction aspect is to prevent the over-fitting or under-fitting to data. The same reasoning and approach can be applicable to GPRM. However, only a few works on the variable selection in GPRM were done. In this paper, we propose a new algorithm to build a good prediction model among some GPRMs. It is a post-work of the algorithm that includes the Welch method suggested by previous researchers. The proposed algorithms select some non-zero regression coefficients (${\beta}^{\prime}s$) using forward and backward methods along with the Lasso guided approach. During this process, the fixed were covariance parameters (${\theta}^{\prime}s$) that were pre-selected by the Welch algorithm. We illustrated the superiority of our proposed models over the Welch method and non-selection models using four test functions and one real data example. Future extensions are also discussed.

• Structural Engineering and Mechanics
• /
• v.67 no.3
• /
• pp.301-310
• /
• 2018

In this paper, a multi-objective multiparameter optimization procedure is developed by combining rigorously developed metamodels with an evolutionary search algorithm-Genetic Algorithm (GA). Response surface methodology (RSM) is used for developing the metamodels to replace the tedious finite element analyses. A nine-node isoparametric plate bending element is used for conducting the finite element simulations. Highly accurate numerical data from an author compiled FORTRAN finite element program is first used by the RSM to develop second-order mathematical relations. Four material parameters-${\frac{E_1}{E_2}}$, ${\frac{G_{12}}{E_2}}$, ${\frac{G_{23}}{E_2}}$ and ${\upsilon}_{12}$ are considered as the independent variables while simultaneously maximizing fundamental frequency, ${\lambda}_1$ and frequency separation between the $1^{st}$ two natural modes, ${\lambda}_{21}$. The optimal material combination for maximizing ${\lambda}_1$ and ${\lambda}_{21}$ is predicted by using a multi-objective GA. A general sensitivity analysis is conducted to understand the effect of each parameter on the desired response parameters.

• Computers and Concrete
• /
• v.18 no.6
• /
• pp.1065-1082
• /
• 2016

The main aim of this study is to predict the compressive and flexural strengths of self-compacting mortar (SCM) containing $nano-SiO_2$, $nano-Fe_2O_3$ and nano-CuO using wavelet-based weighted least squares-support vector machines (WLS-SVM) approach which is called WWLS-SVM. The WWLS-SVM regression model is a relatively new metamodel has been successfully introduced as an excellent machine learning algorithm to engineering problems and has yielded encouraging results. In order to achieve the aim of this study, first, the WLS-SVM and WWLS-SVM models are developed based on a database. In the database, nine variables which consist of cement, sand, NS, NF, NC, superplasticizer dosage, slump flow diameter and V-funnel flow time are considered as the input parameters of the models. The compressive and flexural strengths of SCM are also chosen as the output parameters of the models. Finally, a statistical analysis is performed to demonstrate the generality performance of the models for predicting the compressive and flexural strengths. The numerical results show that both of these metamodels have good performance in the desirable accuracy and applicability. Furthermore, by adopting these predicting metamodels, the considerable cost and time-consuming laboratory tests can be eliminated.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.22 no.2
• /
• pp.115-122
• /
• 2014

Injection pressure is one of factors that influence part quality. In this paper, injection pressure was minimized by optimizing valve gate locations. In order to perform design optimization, MAPS-3DTM (Mold Analysis and Plastic Solution-3D) was used for injection mold analysis and PIAnOTM (Process Integration, Automation and Optimization) was used as process integration and design optimization. Also we adapted meta models based on design of experiments for efficiency. By using introduced methodology, we were able to obtain a result so that maximum injection pressure reduced by 28% compared to the initial design. And the validity of the proposed method could also be demonstrated.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.9 no.2
• /
• pp.415-421
• /
• 2008

The increasing interest in ontologies is driven by the large volumes of information now available as well as by the increasing complexity and diversity of this information. These trends have also increased interest in automating many activities that were traditionally performed manually. We are currently engaged in this paper that have realized benefits in productivity and clarity by utilizing UML class diagrams to develop and to display complex OWL ontologies. UML has many features, such as profiles, global modularity and extension mechanisms that are not generally available in most ontology languages. However, ontology languages have some features that UML does not support. Our paper identifies the similarities and differences between UML and the ontology languages RDF and OWL. To reconcile these differences, we propose a modification to the UML metamodel to address some of the most problematic differences.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.1217-1233
• /
• 2017

Effective monitoring and testing during each step are essential for document verification in research and development (R&D) projects. In software development, proper testing is required to verify it carefully and constantly because of the invisibility features of software. However, not enough studies on test processes for R&D projects have been done. Thus, in this paper, we introduce a Test Maturity Model integration (TMMi)-based software field R&D test process that offers five integrity levels and makes the process compatible for different types of projects. The Software & Systems Process Engineering Metamodel (SPEM) is used widely in the software process-modeling context, but it lacks built-in enactment capabilities, so there is no tool or process engine that enables one to execute the process models described in SPEM. Business Process Model and Notation (BPMN)-based workflow engines can be a solution for process execution, but process models described in SPEM need to be converted to BPMN models. Thus, we propose an approach to support enactment of SPEM-based process models by converting them into business processes. We show the effectiveness of our approach through converting software R&D test processes specified in SPEM in a case study.

• Nuclear Engineering and Technology
• /
• v.45 no.5
• /
• pp.653-664
• /
• 2013

The design of computer-based instrumentation and control (I&C) systems is determined by the allocation of I&C functions to I&C systems and components. Due to the characteristics of computer-based technology, component failures can negatively affect several I&C functions, so that the reliability proof of the I&C systems requires the accomplishment of I&C system design analyses throughout the I&C life-cycle. On one hand, this paper proposes the restructuring of the sequential IEC 61513 I&C life-cycle according to the V-model, so as to adequately integrate the concept of verification and validation. On the other hand, based on a metamodel for the modeling of I&C systems, this paper introduces a method for the modeling and analysis of the effects with respect to the superposition of failure combinations and event sequences on the I&C system design, i.e. the temporal change of physical structure is analyzed. In the first step, the method is concerned with the modeling of the I&C systems. In the second step, the method considers the analysis of temporal change of physical structure, which integrates the concepts of the diversity and defense-in-depth analysis, fault tree analysis, event tree analysis, and failure mode and effects analysis.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.10 no.6
• /
• pp.661-669
• /
• 2018

Engineering system problems consist of multi-objective optimisation and the performance analysis is generally time consuming. To optimise the system concerning its performance, many researchers perform the optimisation using an approximation model. The Response Surface Method (RSM) is usually used to predict the system performance in many research fields, but it shows prediction errors for highly nonlinear problems. To create an appropriate metamodel for marine systems, Lee (2015) compares the prediction accuracy of the approximation model, and multi-objective optimal design framework is proposed based on a confirmed approximation model. The proposed framework is composed of three parts: definition of geometry, generation of approximation model, and optimisation. The major objective of this paper is to confirm the applicability/usability of the proposed optimal design framework and evaluate the prediction accuracy based on sensitivity analysis. We have evaluated the proposed framework applicability in derrick structure optimisation considering its structural performance.