• Journal of the Korean Society for Precision Engineering
• /
• v.14 no.4
• /
• pp.145-150
• /
• 1997

A computer-aided process design system for axisymmetric deep drawing products has been developed. An approach to the system is based on the knowledge based system. The hypothesized process outline of the deep drawing operations is generated in the geometrical design module of the system. In this paper, the module has been expanded. The rules of process design sechems for complex cup drawings are formulated from handbooks, experimental results and empirical knowhow of the field experts. The input to the system is final sheet-metal objects geometry and the output from the system is process sequence with intermediate objects geometries and process parameters, such as drawing load, blank holding force, clearance and cup-drawing coefficient.

• Computers and Concrete
• /
• v.9 no.1
• /
• pp.63-79
• /
• 2012

The purpose of this study is to evaluate the behavior and strength of prestressed concrete deep beams using nonlinear analysis. By using a sophisticated nonlinear finite element analysis program, the accuracy and objectivity of the assessment process can be enhanced. A computer program, the RCAHEST (Reinforced Concrete Analysis in Higher Evaluation System Technology), was used for the analysis of reinforced concrete structures. Tensile, compressive and shear models of cracked concrete and models of reinforcing and prestressing steel were used to account for the material nonlinearity of prestressed concrete. The smeared crack approach was incorporated. A bonded or unbonded prestressing bar element is used based on the finite element method, which can represent the interaction between the prestressing bars and concrete of a prestressed concrete member. The proposed numerical method for the evaluation of behavior and strength of prestressed concrete deep beams is verified by comparing its results with reliable experimental results.

• The Journal of Information Systems
• /
• v.28 no.4
• /
• pp.271-291
• /
• 2019

Purpose The purpose of this study is to propose a methodology to derive positive keywords and negative keywords through deep learning to classify reviews into positive reviews and negative ones, and then refine the results of topic modeling using these keywords. Design/methodology/approach In this study, we extracted topic keywords by performing LDA-based topic modeling. At the same time, we performed attention-based deep learning to identify positive and negative keywords. Finally, we refined the topic keywords using these keywords as filters. Findings We collected and analyzed about 6,000 English reviews of Gyeongbokgung, a representative tourist attraction in Korea, from Tripadvisor, a representative travel site. Experimental results show that the proposed methodology properly identifies positive and negative keywords describing major topics.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1996.04a
• /
• pp.766-770
• /
• 1996

In this study, a CAD/CAM system for axisymmetric deep drawing processes has been developed. An approach to the system is based on the knowledge based system. Under the environment of CAD/CAM software of Personal Designer, the system has been written in UPL. The geometries of intermediate and final object in deep drawing process, including processes parameters are input for the CAD/CAM system. The input data can be obtained from the results of Pro-Deep. The parts drawing of die sets for each process is generatedin tool design module of the CAD/CAM system. Also, the die assemblydrawings can be obtained. NC commands for machining of the part can be generated in the developed CAD/CAM system.

• Proceedings of the Korean Society for Technology of Plasticity Conference
• /
• 1998.03a
• /
• pp.160-167
• /
• 1998

This article is aimed primarily at establishing a process planning method for complex circular shells. For the deep drawing of complex shaped shell, the optimum process design is required to reduce the trial cost, improve the quality, increase the productivity and shorten the delivery. The present approach which is related to the optimum process planning is based on the empirical knowledge through trial and error in the industrial field. In order to check the validity and the effectiveness of proposed work, a sample process design has been applied to the multi-stepped deep drawing of complex shell considering the process variables such as drawing rate, radius and blank development. In particular, the difference between the limiting drawing rate and the optimum drawing rate has been discussed and has been shown the usefulness of present suggestion.

• Structural Monitoring and Maintenance
• /
• v.4 no.3
• /
• pp.269-299
• /
• 2017

This paper presents a Level III damage evaluation methodology, which simultaneously, identifies the location, the extent, and the severity of stiffness damage in deep beams. Deep beams are structural elements with relatively high aspect (depth-to-length) ratios whose response are no longer based on the simplified Euler-Bernoulli theory. The proposed methodology is developed on the bases of the force-displacement relations of the Timoshenko beam theory and the concept of invariant stress resultants, which states that the net internal force existing at any cross-section of the beam is not affected by the inflicted damage, provided that the external loadings in the undamaged and damaged beams are identical. Irrespective of the aspect ratios, local changes in both the flexural and the shear stiffnesses of beam-type structures may be detected using the approach presented in this paper.

• Transactions of Materials Processing
• /
• v.5 no.1
• /
• pp.27-36
• /
• 1996

In this paper a computer-aided design system for axisymmetric deep drawing process will be described. An approach to the system is based on the knowledge based system. The system has been written in AutoLISP with personal computer. The system is composed of four main modules such as input geometrical design test & rectification and user modification. the system which aids designer provides powerful capabilities for the design of axisymmetric deep drawing process.

• Proceedings of the Korea Concrete Institute Conference
• /
• 2006.11a
• /
• pp.265-268
• /
• 2006

Recently, many design standards recommend the use of a strut-tie model approach for design of structural concrete with D-region(s). However, since the design standards of the conventional strut-tie model approaches are suggested on the assumption of using a determinate strut-tie model, it is difficult to apply an indeterminate strut-tie model in the design of continuous deep beams. In this study, an indeterminate strut-tie model for continuous deep beams is proposed to resolve the problem, and the ultimate strengths of 35 continuous deep beams tested to failure are evaluated for the validity check of the proposed indeterminate strut-tie model. The analytical results by the proposed model are compared with those by the conventional approaches of ACI 318-99 and ACI 318-05.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.7
• /
• pp.1100-1104
• /
• 2017

A detector-based approach shows the limited performances for the defect inspections such as shallow fine cracks and indistinguishable defects from background. Deep learning technique is widely used for object recognition and it's applications to detect defects have been gradually attempted. Deep learning requires huge scale of learning data, but acquisition of data can be limited in some industrial application. The possibility of applying CNN which is one of the deep learning approaches for surface defect inspection is investigated for industrial parts whose detection difficulty is challenging and learning data is not sufficient. VOV is adopted for pre-processing and to obtain a resonable number of ROIs for a data augmentation. Then CNN method is applied for the classification. Three CNN networks, AlexNet, VGGNet, and mofified VGGNet are compared for experiments of defects detection.

• Journal of Korea Multimedia Society
• /
• v.22 no.10
• /
• pp.1133-1141
• /
• 2019

Most of the previous studies for bark recognition have focused on the extraction of LBP-like statistical features. Deep learning approach was not well studied because of the difficulty of acquiring large volume of bark image dataset. To overcome the bark dataset problem, this study utilizes the MobileNet which was trained with the ImageNet dataset. This study proposes two approaches. One is to extract features by the pixel-wise convolution and classify the features with SVM. The other is to tune the weights of the MobileNet by flexibly freezing layers. The experimental results with two public bark datasets, BarkTex and Trunk12, show that the proposed methods are effective in bark recognition. Especially the results of the flexible tunning method outperform state-of-the-art methods. In addition, it can be applied to mobile devices because the MobileNet is compact compared to other deep learning models.