• Proceedings of the Korean Society of Machine Tool Engineers Conference
• /
• 1998.03a
• /
• pp.40-52
• /
• 1998

Among the non-traditional machining methods, Abrasive waterjet machining process shows big promise in drilling difficult-to-machine materials due to its numerous advantages such as absence of heat affect zone and thermal distortion. Acoustic emission signal technique is used to understand about material removal mechanisms during abrasive waterjet drilling process. More information about the drilling process is derived through frequency decomposition of auto regressive moving average modeling representing acoustic emission signals.

• Archives of design research
• /
• v.14
• /
• pp.109-119
• /
• 1996

One of the most important factors in the work environment of the industrial design is the design process which can systematically synthesize the informations of related fields. Because the computer technology is being radically developed, industrial should not only positively be able to cope with new technologies, but also should positively be able to take part in the development of the integrated system for the process by the new technologies. Recently in the industrial design field, designers are often using the computer~applied-3D modeling techniques in the development process of industrial design products, especially in the visualization level of the design development. In this paper, we studied the workstation modeling process to understand the computer~applied-3D modeling and presented the methods of transfer of the 3D-modeling data of a workstation(SGI) to the AutoCAD data of a personal computer which is generally being used as a drawing tool in mechanism parts. Through the development process of an electronic taxi meter as a practical case study, we check the possibility whether the 3D-modeling data transferred from an industrial design part to a mechanism part can directly be used as the mechanism data. For this, we transferred the 3D-modeling data of an electronic taxi meter created with a workstation(SGI) to the AutoCAD data of a personal computer and checked the usefulness of data transferred from an industrial design part to a mechanism part. Through these processes of data transfer, we aimed to find out the basic principles which can be rationally applied to a mechanism part or a production part.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1773-1793
• /
• 2023

Automated machine learning, often referred to as "AutoML," is the process of automating the time-consuming and iterative procedures that are associated with the building of machine learning models. There have been significant contributions in this area across a number of different stages of accomplishing a data-mining task, including model selection, hyper-parameter optimization, and preprocessing method selection. Among them, preprocessing method selection is a relatively new and fast growing research area. The current work is focused on the recommendation of preprocessing methods, i.e., feature subset selection (FSS) algorithms. One limitation in the existing studies regarding FSS algorithm recommendation is the use of a single learner for meta-modeling, which restricts its capabilities in the metamodeling. Moreover, the meta-modeling in the existing studies is typically based on a single group of data characterization measures (DCMs). Nonetheless, there are a number of complementary DCM groups, and their combination will allow them to leverage their diversity, resulting in improved meta-modeling. This study aims to address these limitations by proposing an architecture for preprocess method selection that uses ensemble learning for meta-modeling, namely AutoFE-Sel. To evaluate the proposed method, we performed an extensive experimental evaluation involving 8 FSS algorithms, 3 groups of DCMs, and 125 datasets. Results show that the proposed method achieves better performance compared to three baseline methods. The proposed architecture can also be easily extended to other preprocessing method selections, e.g., noise-filter selection and imbalance handling method selection.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.10a
• /
• pp.1410-1413
• /
• 2004

Finite element method is very effective method to simulate the forming processes with good prediction of the deformation behaviour. For the finite element modeling of sheet mental forming the accurate tool model is required. Due to the geometrical complexity of real-size part stamping tools it is hard to make FE model for real-size auto-body stamping parts. In this paper, it was focussed on the drawability factors on auto-body panel stamping by AUTOFORM with using tool planning alloy to reduce law price as well as high precision from Design Optimization of die. According to this study, the results of simulation will give engineers good information to access the Design Optimization of die.

• Journal of ILASS-Korea
• /
• v.5 no.4
• /
• pp.66-71
• /
• 2000

The present study is mainly motivated to investigate the vaporization, auto-ignition and combustion processes in the high-pressure engine conditions. The high-pressure vaporization model is developed to realistically simulate the spray dynamics and vaporization characteristics in high-pressure and high-temperature environment. The interaction between chemistry and turbulence is treated by employing the Representative Interactive Flamelet (RIF) Model. The detailed chemistry of 114 elementary steps and 44 chemical species is adopted for the n-heptane/air reaction. In order to account for the spatial inhomogeneity of the scalar dissipation rate, the multiple RIFs are introduced. Numerical results indicate that the RIF approach together with the high-pressure vaporization model successfully predicts the ignition delay time and location as well as the essential features of a spray ignition and combustion processes.

• Proceedings of the IEEK Conference
• /
• 2001.06b
• /
• pp.257-260
• /
• 2001

Routing region modeling methods for PCB auto-routing system in Shape based type(non-grid method) used region process type and the shape located in memory as a individual element, and this element consumed small memory due to unique data size. In this paper we design PCB(Printed Circuit Board) auto-routing system using the auction algorithm method that 1) Could be reached by solving the shortest path from single original point to various destination, and 2) Shaped based type without any memory dissipation with the best speed. Also, the auto-routing system developed by Visual C++ in Window environment, and can be used in IBM Pentium computer or in various individual PC system.

• Proceedings of the KIEE Conference
• /
• 2006.04a
• /
• pp.99-101
• /
• 2006

Auto-Cross Correlated time series (ACTS) model was constructed by using the backpropagation neural network. The performance of ACTS model was evaluated with sensor information collected from a large volume, industrial plasma-enhanced chemical vapor deposition system. A total of 18 sensor information were collected. The effect of inclusion of past and future information were examined. For all but three sensor information with a large data variance demonstrated a prediction error less than 3%. By integrating ACTS model into equipment software, process quality can be more stringently monitored while improving device throughput.

• Transactions of Materials Processing
• /
• v.18 no.5
• /
• pp.371-376
• /
• 2009

An equivalent drawbead model(EDM) for sheet metal forming analysis, which replaces complex drawbead geometries with drawbead forces in modeling the stamping dies with finite elements, is experimentally verified and applied to the numerical simulation of auto-panel stamping process. The drawbead restraining and opening forces of elliptical drawbead, circular drawbead, square drawbead, and step drawbead are obtained by performing the drawbead pulling test and compared with those of EDM and commercial code models(CCM). Better agreement with experimental measurements is found in EDM than CCM. Furthermore, the excellence of EDM is demonstrated in its application to the auto-body stamping analysis.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.9 no.6
• /
• pp.152-159
• /
• 2001

In multibody dynamic analysis including contact and impact, there are two major analysis methods, i.e., piecewise analysis and continuous analysis. Modeling of contact phenomena is mainly classified with a Kelvin-Voigt model or a model of Hertz contact model. In this paper, a contact module fur AutoDyn7 program was developed and implemented. Both the Kelvin-Voigt model and a model of Hertz contact law were developed. The process of this module is composed of contact distinction and the contact force calculation. Two examples were verified and compared to the commercial program DADS.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 2009.05a
• /
• pp.389-392
• /
• 2009

The application of an equivalent drawbead model(EDM) for sheet metal forming analysis, which adopts the forces instead of complex geometries in modeling the drawbead, to the numerical simulation of auto-panel stamping process is introduced in this study. In terms of the thinning and draw-in, better agreement with experimental measurements was found in EDM than in commercial code models so that the excellence of EDM in the accuracy of drawbead forces for the simulation of auto-body stampings was revealed.