• Journal of the Korean Society for Nondestructive Testing
• /
• v.18 no.6
• /
• pp.464-476
• /
• 1998

Determination of location, shape and size of a flaw from its eddy current testing signal is one of the fundamental issues in eddy current nondestructive evaluation of steam generator tubes. Here, we propose an approach to this problem; an inversion of eddy current flaw signal using neural networks trained by finite element model-based synthetic signatures. Total 216 eddy current signals from four different types of axisymmetric flaws in tubes are generated by finite element models of which the accuracy is experimentally validated. From each simulated signature, total 24 eddy current features are extracted and among them 13 features are finally selected for flaw characterization. Based on these features, probabilistic neural networks discriminate flaws into four different types according to the location and the shape, and successively back propagation neural networks determine the size parameters of the discriminated flaw.

• Journal of Korea Multimedia Society
• /
• v.11 no.11
• /
• pp.1501-1514
• /
• 2008

The face shape extracted by the depth values has different appearance as the most important facial information. The face images decomposed into frequency subband are signified personal features in detail. In this paper, we develop a method for recognizing the range face images by multiple frequency domains for each depth image using the modified fuzzy c-mean algorithm. For the proposed approach, the first step tries to find the nose tip that has a protrusion shape on the face from the extracted face area. And the second step takes into consideration of the orientated frontal posture to normalize. Multiple contour line areas which have a different shape for each person are extracted by the depth threshold values from the reference point, nose tip. And then, the frequency component extracted from the wavelet subband can be adopted as feature information for the authentication problems. The third step of approach concerns the application of eigenface to reduce the dimension. And the linear discriminant analysis (LDA) method to improve the classification ability between the similar features is adapted. In the last step, the individual classifiers using the modified fuzzy c-mean method based on the K-NN to initialize the membership degree is explained for extracted coefficient at each resolution level. In the experimental results, using the depth threshold value 60 (DT60) showed the highest recognition rate among the extracted regions, and the proposed classification method achieved 98.3% recognition rate, incase of fuzzy cluster.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.1
• /
• pp.95-103
• /
• 2015

This paper presents the effects of the tool shape on the geometrical characteristics of flat end-milled side walls. A tool shape is characterized by such parameters as helix angle, number of cutting edges, and diameter. The geometrical characteristics of the side walls are represented by the surface profiles in the feed and axial directions, which are orthogonal to each other. The geometrical defects in each direction are estimated based on the instantaneous apparent cutting areas, which are represented by the interference area between the tool and workpiece and that between the cutting edge and workpiece. It is confirmed that a geometrical defect in the feed direction is formed when the tool leaves the workpiece and the curvature of the tool path changes. Defects in the axial direction are also found in the side walls, except for the defect zone in the feed direction. An up-cut using an end-mill with a steeper helix angle, a greater number of cutting edges, and a smaller diameter are thus found to improve the geometrical accuracy of end-milled side walls.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.7 no.5
• /
• pp.37-46
• /
• 2003

Response analysis of buried pipeline subjected to permanent ground deformation(PGD) due to liquefaction is mainly executed by use of numerical analysis or semi-analytical relationship, Especially for the semi-analytical relationship considering transverse PGD, it has somewhat limited applicability : since it has different formula according to the width of PGD and does not reflect various patterns of PGD which is caused by the decrease of soil stiffness, Therefore, in this study, the applicability of existing analytical relationship is closely investigated through the comparison of FEM results at first. And then, based on meaningful contemplation, improved analytical relationship is proposed. The proposed one models the system behavior of buried pipeline as the combination of cable and beam, and thus it is applicable to arbitrary width of PGD, Moreover, it does reflect various patterns of PGD by introducing interaction pattern coefficient. Through the comparison of numerical results using the FEM and the proposed analytical relationship, rational applicability is objectively verified and noticeable considerations are discussed, Moreover, analyses considering the change of PGD magnitude and patterns are performed.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.553-555
• /
• 2003

사람의 얼굴을 검출 및 인식을 하는 여러 가지 다양한 알고리즘이 소개되고 있다. 본 논문에서는 사람의 피부색을 이용한 컬러정보(Color Information)와 국부 최적 임계치 기법을 사용하여 얼굴의 형상정보를 검출하고 얼굴 영역을 검출하는 방법을 사용한다. 컬러정보를 사용하여 얼굴의 후보영역을 선정한 후에 그 후보영역에서 얼굴의 특징인 눈, 눈썹, 입을 찾는 방법을 제안한다. 피부색은 일정한 분포를 가지고 있기 때문에 후보영역을 비교적 정확히 찾을 수 있으며, 국부 최적 임계치 기법은 효과적인 얼굴 특징 검출방법이다.

• Proceedings of the KIEE Conference
• /
• 1999.11c
• /
• pp.775-777
• /
• 1999

흉부 단순 X선 사진에 있어서 폐의 간질성 음영의 특징을 컴퓨터를 이용하여 해석하는 시스템을 구축하여 그 정확도를 검토하였다. 이 시스템에서는 X선 사진을 디지털화 해서 관심영역을 설정하여 4방향 라플라시안-가우시안 형상필터를 행하여 2치화 한후, 계속해서 선상음영 판정처리 및 선상음영 차분처리를 행해 간질성 음영의 특징을 나타내는 몇가지 물리적인 지표를 계산 하였다. 82명의 정상예와 이상예에 대하여 이들 물리적 지표의 ROC 해석을 행하여 간질성 폐질환 변화의 양호한 검출결과를 얻었다.

• Proceedings of the IEEK Conference
• /
• 1998.06a
• /
• pp.725-728
• /
• 1998

흉부 단순 X선 사진에 있어서 폐의 간질성 음영의 특징을 컴퓨터를 이용하여 해석하는 시스템을 구축하여 그 정확도를 검토하였다. 이 시스템에서는 X선 사진을 디지털화 해서 관심영역을 설정하여, 4방향 라플라시안 -가우시안 형상필터를 행하여 2치화 한후, 계속해서 선상음영 판정처리 및 선상음영 차분처리를 햐해 간질성 음영의 특징을 나타내는 몇가지 물리적인 지표를 계산하였다. 82명의 정상예와 이상예에 대하여 이들 물리적 지표의 ROC 해석을 행하여 간질성 폐질환 변화의 양호한 검출결과를 얻었다.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.26 no.9B
• /
• pp.1251-1258
• /
• 2001

본 논문은 2차 다항식을 이용하여 3차원 물체의 표면 특징을 추출하고 표현하는 방법을 제안한다. 본 연구는 수정된 스캔 라인 기법을 이용하여 에지 맵을 얻는다. 에지 맵으로부터 3차원 물체의 각 면들을 분리하기 위해 레이블링 연산을 하고 각 면에서 중심점과 모서리 점들을 추출한다. 그 다음에, 평면 방정식으로부터 각 면이 평면인지 곡면인지를 판단한다. 3차원 물체를 표현하기 위해 각 면의 평면 또는 곡면의 계수 및 특징들을 추출한다. 합성영상과 실측영상을 통해서 제안된 기법의 성능을 알아보았고, 또한 제안된 기법으로 3차원 물체를 재구성하였다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2003.10b
• /
• pp.598-600
• /
• 2003

기존의 재활용기계는 광센서. 근접센서, 자장센서를 이용하여 캔의 부분적인 정보들을 수집하고 캔의 종류를 구별하였다[l]. 이는 시스템 제작비용이 저렴하고 수행속도가 빠르다는 장점이 있지만 오인식 확률이 크기 때문에 제품화 하였을 때 위험부담이 크다는 한계를 지닌다. 따라서, 이와 같은 문제점을 해결하기 위해 본 논문에서는 기계 내부에 카메라를 설치하여 획득된 캔 영상의 특징을 분석하고, 파쇄 가능한 일반 캔과 파쇄해서는 안될 부탄가스 캔을 선별하기 위한 영상처리 기법을 제안한다.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.34 no.8
• /
• pp.1083-1089
• /
• 2010

Shape memory alloys (SMAs) are smart materials. The unique characteristics of SMAs enable the production of large force and displacement. Hence, SMAs can be used in many applications such as in actuators and active structural acoustic controllers; the SMAs can also be used for dynamic tuning and shape control. A SMA torque tube actuator consisting of SMA tubes and superelastic springs is proposed, and the behaviors of the actuator are investigated. From the results of heat transfer analysis, it is proved that the SMA torque tube actuator with both resistive heating of SMA itself and a separate conventional heating rod in the tube core has good performance. The behavior of an actuator system was analyzed by performing a contact analysis, and the twisting motion was noticed when checking the actuation. 3D SMA nonlinear constitutive equations were formulated numerically and implemented by performing a nonlinear analysis by using Abaqus UMAT.