• 정보처리학회논문지D
• /
• 제11D권3호
• /
• pp.709-716
• /
• 2004

본 논문에서는 다중 시계열 패턴인식 사용하여 생산장치의 상태자료부터 공정결과를 예측하여 정상 또는 비정상을 판정하는 지능형 감시시스템에 관하여 기술한다. 제안하는 감시스템은 초기화, 학습 그리고 인식의 세 단계로 구성된다. 초기화 단계에서는 감시대상의 생산장치가 가지는 인사들 각각의 가중치와 각 인자들이 가지는 시계열 자료 중에서 학습과 인식에 유효단계를 설정한다. 학습단계에서는 LBG알고리즘을 사용하여 이 생산장치에 의하여 생성되고 수집된 패턴들을 군집화 한다. 각 패턴은 시계열 형태의 자료와 처리 완료 후 계측기에 의하여 측정된 ACI로 구성된다. 인식단계에서는 DTW를 사용하여 실시간으로 입력된 패턴과 군집화된 패턴들 사이의 대응을 수행하여 가장 잘 정합되는 패턴을 찾는다. 다음은 이 패턴이 가지는 ACI, 차 그리고 가중치들의 조합으로 예측된 ACI 값을 산출한다. 최종적으로 예측된 ACI가 정상으로 수용할 수 있는 값 범위에 없는지 여부를 결정한다. 제안하는 시스템의 성능평가를 위하여 식각장치로부터 획득된 자료를 대상으로 실험하였다. 실험결과에서는 학습횟수가 증가함에 따라 예측 ACI값과 실측ACI값 사이의 오차가 현저히 감소함을 볼 수 있다

• 마이크로전자및패키징학회지
• /
• 제22권1호
• /
• pp.51-54
• /
• 2015

An electro-plating technology on a cured isotropic conductive pattern with a hybrid Cu paste composed of resin matrix, copper, and solder powders has been developed. In a conventional technology, Ag paste was used to perform a conductive pattern on a PCB or silicon substrate. From previous research, the electrical conductive mechanism and principle of the hybrid Cu paste were concisely investigated. The isotropic conductive pattern on the PCB substrate was performed using screen-printing technology. The optimum electro-plating condition was experimentally determined by processing parameters such as the metal content of the hybrid Cu paste, applied current density, and time for the electroplating in the plating bath. The surfaces and cross-sections were observed using optical and SEM photographs. In conclusion, the optimized processing conditions for Cu electro-plating technology on the conductive pattern were a current density of $40mA/cm^2$ and a plating time of 20min on the hybrid Cu paste with a metal content of 44 vol.%. More details of the mechanical properties and processing conditions will be investigated in further research.

• 정보처리학회논문지D
• /
• 제17D권4호
• /
• pp.253-258
• /
• 2010

지금까지의 빈발 패턴(Frequent Pattern) 마이닝에서는 각 항목들의 중요도(Weight)는 모든 같은 값으로 다루어 왔으나 실 환경에서는 각 항목들의 중요도가 다르게 적용되는 경우가 많이 있고 또 같은 항목이라도 시간에 따라 다른 중요도 값으로 다루어져야 할 경우가 있다. 비즈니스 데이터 분석 환경이나 웹 클릭 데이터 분석 환경과 같은 응용에서도 동적으로 변하는 중요도를 고려하여야 한다. 지금까지 항목의 중요도를 고려하는 여러 패턴 마이닝 기법들이 제안되고 있으나 동적으로 변하는 항목의 중요도를 고려하는 연구는 발표되지 않고 있다. 본 논문에서는 처음으로 동적인 항목들의 중요도(혹은 가중치)를 고려하는 빈발 패턴 마이닝 알고리즘을 제안한다. 제안하는 기법은 단 한번의 데이터베이스 스캔으로 처리되므로 스트림 데이터를 분석할 수 있다. 여러 실험을 통하여 제안하는 기법은 매우 효과적이며 확장성이 좋은 것임을 보인다.

• 한국산학기술학회논문지
• /
• 제3권2호
• /
• pp.110-114
• /
• 2002

주얼리 제조 공정중 마스터패턴 제조 공정은 전체 제조원가의 20%를 차지하기 때문에 매우 중요한 공정이다. 지금까지는 수작업으로 왁스 패턴을 제작하고 이를 이용하여 석고형을 만들고 석고형으로 마스터 패턴을 제작하는 복잡한 공정을 거쳐 제작하였다. 본 연구는 쾌속조형기를 이용하여 듀라폼 재질의 몰드를 만들고 저융점합금을 이용하여 마스터패턴을 직접 제작하는 새로운 공정을 개발하였다. 듀라폰의 용융진이 190℃ 이므로 용융점 70℃의 Pb-Sn-Bi-Cd 계의 저융점 합금을 주물재료로 이용하여 마스터패턴을 제작하였다.

• Design & Manufacturing
• /
• 제17권2호
• /
• pp.22-26
• /
• 2023

As Light-Emitting Diodes(LEDs) continue to advance in performance, their application in automotive lamps is increasing. Automotive LEDs utilize light guides not only for aesthetics but also to control light quantity and direction. Light guides employ patterns of a few hundred micrometers(㎛) to regulate the light, and the surface roughness(Ra) of these patterns can reach tens of nanometers(nm). Given that these light guides are produced through injection molding, mold processing technology with high surface quality micro-patterns is required. This study serves as a preliminary investigation into the development of high surface quality micro-pattern processing technology. It examines the surface roughness of the workpiece based on the cutting direction of the pattern and the cutting fluid type when cutting micro-patterns on STAVAX steel using cubic Boron Nitride(cBN) tools. The experiments involved machining a step-shaped micro-pattern with a height of 60 ㎛ and a pitch of 400 ㎛ in a 22×22 mm area under identical cutting conditions, with only the cutting direction and cutting fluid type being varied. The machining results of four cases were compared, encompassing two cases of cutting direction(parallel to the pattern, orthogonal to the pattern) and two cases of cutting fluid type (flood, mist). Consequently, the Ra value was found to be the highest(Ra 128.33 nm) when machining with the flood type in parallel to the pattern, while it was the lowest(Ra 95.22 nm) when machining with the mist type orthogonal to the pattern. These findings confirm that there is a difference of up to 25.8 % in the Ra value depending on the cutting direction and cutting fluid type.

• The Journal of the Acoustical Society of Korea
• /
• 제27권2E호
• /
• pp.51-56
• /
• 2008

In this paper, we propose an effective method for music summarization which automatically extracts a representative part of the music by using signal processing technology. Proposed method uses a vector quantization technique to extract several segments which can be regarded as the most important contents in the music. In general, there is a repetitive pattern in music, and human usually recognizes the most important or catchy tune from the repetitive pattern. Thus the repetition which is extracted using segment similarity is considered to express a music summary. The segments extracted are again combined to generate a complete music summary. Experiments show the proposed method captures the main theme of the music more effectively than conventional methods. The experimental results also show that the proposed method could be used for real-time application since the processing time in generating music summary is much faster than other methods.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.1101-1104
• /
• 1995

Through welding fabrication, user can feel an surficaial and capable unsatisfaction because of welded defects, Generally speaking, these are called weld defects. For checking these defects effectively without time loss effectively, weldability estimation system setup isan urgent thing for detecting whole specimen quality. In this study, by laser vision camera, catching a rawdata on welded specimen profiles, treating vision processing with these data, qualititative defects are estimated from getting these information at first. At the same time, for detecting quantitative defects, whole specimen weldability estimation is pursued by multifeature pattern recognition, which is a kind of fuzzy pattern recognition. For user friendly, by weldability estimation results are shown each profiles, final reports and visual graphics method, user can easily determined weldability. By applying these system to welding fabrication, these technologies are contribution to on-line weldability estimation.

• The Journal of the Acoustical Society of Korea
• /
• 제16권2E호
• /
• pp.27-31
• /
• 1997

This paper proposes a new rejection algorithm which distinguishes unregistered spoken words(or non-keywords) from registered vocabulary. Two kinds of garbage models are employed in this design ; the original garbage model and a new word garbage model. The original garbage model collects all non-keyword patterns where the new word garbage model collects patterns classified by recognizing each non-keyword pattern with registered vocabulary. These two types of garbage models work together to make a robust reject decision. The first stage of processing is the classification of an input pattern through the original garbage model. In the event that the first stage of processing is ambiguous, the new word dependent garbage model is used to classify thye input pattern as either a registered or non-registered word. This paper shows the efficiency of the new word dependent garbage model. A Dynamic Multisection method is used to test the performance of the algorithm. Results of this experiment show that the proposed algorithm performs at a higher level than that of the original garbage model.

• 한국생산제조학회지
• /
• 제20권5호
• /
• pp.666-672
• /
• 2011

In this paper, we describes the development of automatic inspection system for detecting the defects on photovoltaic wafer by using machine vision. Until now, The defect inspection process was manually performed by operators. So these processes caused the produce of poorly-made articles and inaccuracy results. To improve the inspection accuracy, the inspection system is not only configured, but the image processing algorithm is also developed. The inspection system includes dimensional verification and pattern matching which compares a 2-D image of an object to a pattern image the method proves to be computationally efficient and accurate for real time application and we confirmed the applicability of the proposed method though the experience in a complex environment.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2000년도 제15차 학술회의논문집
• /
• pp.294-294
• /
• 2000

In this paper, we would like to discuss the signal processing and the algorithm for ECG analysis. The ECG gives us information about the condition of the heart muscle, because myocardial abnormality or infarction is inscribed on the ECG during myocardial depolarization and repolarization. Analyzing the ECG signal, we can find heart disease, for example, arrhythmia and myocardial infarction, etc. Particularly, detecting arrhythmia is more important, because serious arrhythmia can take away the life from patients within ten minutes. The wavelet transform decomposes the ECG signal into high and low frequency component using wavelet function. Recomposing high frequency bands including QRS complex, we can detect QRS complex and eliminate the noise from the original ECG signal. To recognize the ECG signal pattern, we adopted the curve-fitting partially and statistical method. The ECG signal is divided into small parts based on QRS complex, and then, each part is approximated to the polynomials. Comparing the approximated ECG pattern with some kinds of heart disease ECG pattern, we can detect and classify the kind of heart disease.