• 제목/요약/키워드: Precision Machine

검색결과 2,979건 처리시간 0.023초

GLCM을 이용한 의료영상 특징정보 추출 (Feature extraction of medical image using GLCM)

  • 박용성;정수영;김욱;임일한;강주현;임상무;우상근
    • 한국컴퓨터정보학회:학술대회논문집
    • /
    • 한국컴퓨터정보학회 2017년도 제55차 동계학술대회논문집 25권1호
    • /
    • pp.239-240
    • /
    • 2017
  • 본 연구는 의료영상내 특징정보를 추출 및 평가함으로서 정밀의료 실현 가능성을 확인하고자 하였다. 영상화는 PET/CT 및 MRI 스캐너를 이용하여 암환자의 기능적 정보와 해부학적 정보를 획득하고 관심영역을 설정하였으며 각각의 영상내 특징정보를 추출하였다. 영상내 특징정보는 GLCM을 이용하여 에너지, 대비, 엔트로피, 균질성을 획득하였고, 획득된 영상 데이터에 따른 관심영역 설정 차이를 확인하였다. 영상내 특징 정보는 MRI 영상의 해부학적 정보를 이용한 분석결과에서 엔트로피 및 균질성이 PET 보다 증가 하였고 대비는 감소함을 확인하였다. 추후연구는 다양한 영상내 특징 정보를 획득하고 정밀의료를 위한 기계학습에 활용할 예정이다.

  • PDF

곡면 Fitting을 이용한 고속가공 표면거칠기의 최소화 (Minimization of Surface Roughness for High Speed Machining by Surface Fitting)

  • 정종윤;조혜영;이춘만;문덕희
    • 산업경영시스템학회지
    • /
    • 제27권2호
    • /
    • pp.37-43
    • /
    • 2004
  • High speed machining is a machining process which cuts materials with the fast movement and rotation of a spindle in a machine tool. It reduces machining time because of the high feed and the high speed of a spindle. In addition it gets rid of post processes for high precision machining. When the high speed machining is applied to especially hardened steel, operators should select the proper parameters of machining. This can produce machining surfaces which is qualified with good surface roughness. This paper presents a method for selecting machining parameters to minimize surface roughness with high speed machining in cutting the hardened steels. Experimental data for surface roughness are collected in a machining shop based on the cutting feed and the spindle rotation. The data fits in hi-cubic polynomial surface of mathematical form. From the model this research minimize the surface roughness to find the optimal values of the feed and the spindle speed. This paper presents a program which automatically generates optimal solutions from the raw data of experiments.

레이저 스폿의 칼날주사 방법에 의한 복사계 개구 면적의 정밀측정 (Precision measurements of radiometric aperture area by laser spot scanning along the edge of the aperture)

  • 강창호;김석원;박승남
    • 한국광학회지
    • /
    • 제15권3호
    • /
    • pp.258-262
    • /
    • 2004
  • 검출기의 분광감응도 표준으로부터 출발하여 SI 기본 단위의 하나인 칸델라(candela)눈금의 불확도는 복사계 개구의 면적 측정 불확도에 의해서 제한을 받는다. 칸델라 눈금을 새로 실현하기 위하여 다이아몬드 선삭가공기를 사용하여 개구의 가장자리가 칼날과 같도록 가공하였다. 이 개구를 디지털 되먹임 알고리듬을 채용한 x-y 이송대에 설치한 후, 출력이 안정화된 레이저 광선을 빔 허리가 5 $\mu\textrm{m}$ 이하가 되도록 집속시키고, 이송대를 이동하면서 개구의 가장자리 좌표를 칼날주사 방법으로 검출하였다. 이 좌표들을 지나는 최적의 타원을 최소 제곱법으로 결정하여 개구의 면적으로 구하였다. 측정 불확도를 분석한 결과 제작한 장치의 면적 측정의 상대 측정 표준 불확도(k=1)는 8${\times}$$10^{-5}$이다.

금형가공을 위한 초정밀 나노가공기의 구조해석 (Structure analysis of ultra precision nano-scale machine for mold processing)

  • 백승엽;김선용
    • Design & Manufacturing
    • /
    • 제1권1호
    • /
    • pp.51-56
    • /
    • 2007
  • As various manufacturing technology of optical glass is developed, the aspheric lenses are supplied to many fields. Electronic or measuring instruments equipped with aspheric lens have recently been used since aspheric lens is more effective than spheric one. However, it is still difficult manufacture glass lens because of high cost and the short life of core. The demands of the aspheric glass lenses increase since it is difficult to obtain the desirable performance in the plastic lens. For the mass production of aspheric lens, specific molds with precisely machined cores should be prepared. In order to obtain competitiveness in the field of industrial manufacturing, a reduction in the development period for the batch machining of products is required. It is essential to analyze the stress distribution and deformations of machining system which is used for manufacturing the aspheric lens using FEM software ANSYS. Finite element simulations have been performed in order to study the influence of machining system which is developed in this study on structures. It is very important to understand the structural behavior of machining system. This paper investigated the static analysis and dynamic analysis of machining system for aspheric lens to predict the damage due to loading.

  • PDF

CNx코팅된 강의 회전접촉피로에 미치는 코팅두께의 영향 (Effect of Coating Thickness on Rolling Contact Fatigue of CNx Coated Steel)

  • 최병영;노리츠구 우메하라
    • 열처리공학회지
    • /
    • 제13권5호
    • /
    • pp.355-359
    • /
    • 2000
  • Ion beam assisted deposition system was used to deposit CNx coatings with various thickness on the substrates of high-frequency induction hardened steels. Rolling contact fatigue tests were performed using Polymet RCF-1 machine with a constant supply of lubricant. Rolling contact fatigue life was substantially different in the steels with various thickness of CNx coatings. The optimum thickness of CNx coating was found to be $8.9{\mu}m$, showing the longest fatigue life, mainly caused by higher resistance to initiation of cracks and protective overcoat remaining to the surface failure during rolling contact fatigue. Cracks were initiated in the substrates under the surface of wear track and propagated to the surface, which eventually resulted in the failure. The reduction of fatigue life observed in the specimen with elimination of CNx coating during rolling contact fatigue was explained by the substrates deformation.

  • PDF

개량형 인바합금의 미세조직에 미치는 열처리 및 Ti 첨가 영향 (Effects of Heat Treatment and Ti addition on Microstructures in Modified Invar Alloys)

  • 허민선;이정한;이찬규;이재현
    • 열처리공학회지
    • /
    • 제13권6호
    • /
    • pp.412-419
    • /
    • 2000
  • There has been a considerable attention on Invar alloys due to its low thermal expansion property. A low thermal expansion property of Invar alloys, lower than $10^{-6}$ near the room temperature, is attractive for electric transmission lines and precision machine tools. However, the expansion property of Invar alloys is limited below about 520K, and mechanical properties are relatively low to apply to electric transmission line. In order to improve mechanical properties in this alloy, Ti alloying element was added to the $Ni_{38}-Mo_2-Cr_1-Fe$ invar alloy. The microstructure Ti added alloy showed finer than that of the unalloyed one. It was found that the (Mo, Ti), Mo carbide formed by Ti addition obstacled grain growth by pinning effect and supplyed recrystallization sites during heat-treatment. Optimum heat-treatment conditions with Ti addition were also discussed in the modified Invar alloy.

  • PDF

노즐특성에 따른 MIST-COOLING 열전달에 관한 실험적 연구 (The Effect of Nozzle Characteristics on the Mist-Cooling Heat Transfer)

  • 이진원;강영규;백병준;박복춘
    • 열처리공학회지
    • /
    • 제5권3호
    • /
    • pp.171-178
    • /
    • 1992
  • The effect of nozzle characterristics on the mist-cooling heat transfer was investigated under the various flow conditions. Two different types of twin fluid nozzle were used, one is a $90^{\circ}$ angle tip nozzle with needle and the other is a $90^{\circ}$ angle tip non-needle nozzle. The cooling rate from the heated surface was measured and obtained the boiling curve as a function of surface temperature. An immersion sampling was employed for the measurement of droplet size of the spray. As a result of this experiment, the liquid sheet type nozzle shows better atomization when the mass ratio Mr>2.0, and collects more liquid droplets on the heated surface that results in better cooling effect. It was found that the maximum heat flux and heat transfer coefficient increased with increase in the volumetric flow rate, whereas the maximum heat flux decreased with increase in spray distance. The cooling effect depends upon the amount of collected droplet and droplet size, but it strongly depends upon the amount of collected droplet.

  • PDF

고객 감성 분석을 위한 학습 기반 토크나이저 비교 연구 (Comparative Study of Tokenizer Based on Learning for Sentiment Analysis)

  • 김원준
    • 품질경영학회지
    • /
    • 제48권3호
    • /
    • pp.421-431
    • /
    • 2020
  • Purpose: The purpose of this study is to compare and analyze the tokenizer in natural language processing for customer satisfaction in sentiment analysis. Methods: In this study, a supervised learning-based tokenizer Mecab-Ko and an unsupervised learning-based tokenizer SentencePiece were used for comparison. Three algorithms: Naïve Bayes, k-Nearest Neighbor, and Decision Tree were selected to compare the performance of each tokenizer. For performance comparison, three metrics: accuracy, precision, and recall were used in the study. Results: The results of this study are as follows; Through performance evaluation and verification, it was confirmed that SentencePiece shows better classification performance than Mecab-Ko. In order to confirm the robustness of the derived results, independent t-tests were conducted on the evaluation results for the two types of the tokenizer. As a result of the study, it was confirmed that the classification performance of the SentencePiece tokenizer was high in the k-Nearest Neighbor and Decision Tree algorithms. In addition, the Decision Tree showed slightly higher accuracy among the three classification algorithms. Conclusion: The SentencePiece tokenizer can be used to classify and interpret customer sentiment based on online reviews in Korean more accurately. In addition, it seems that it is possible to give a specific meaning to a short word or a jargon, which is often used by users when evaluating products but is not defined in advance.

2단계공정을 이용한 헬리컬기어 압출에 관한 연구 (A Study on Extrusion of Helical Gears by a Two-step Process)

  • 정성윤;박준홍;김철;김창호;최재찬;최상호
    • 한국소성가공학회:학술대회논문집
    • /
    • 한국소성가공학회 2002년도 제7회 단조 심포지엄
    • /
    • pp.85-91
    • /
    • 2002
  • Of all the many types of machine elements which exist today, gears are among the most commonly used. Many researches have been done to manufacture helical gears by cold forging and extrusion. Although cold forging and extrusion were applied to some bevel, spur, and helical gears, problems in connection with reducing forming load and tool life still make it difficult for the related methods to be commercialized. In this study, focusing on reducing load in forming helical gears, extrusion of helical gears by a two-step process is proposed. The process is composed of an extrusion step of spur gears used as preform and a torsion step of the preform to make helical gears. Upper-bound analysis for the two-step process is performed and compared with results of experiments. The newly proposed method can be used as an advanced forming technique to remarkably reduce the forming load and replace the conventional forming process of helical gears.

  • PDF

품질기능전개와 신경망 회로를 이용한 사출성형 공정변수의 예측 (Estimation of Process Parameters Using QFD and Neural Networks in Injection Molding)

  • 고범욱;김종성;최후곤
    • 산업공학
    • /
    • 제21권2호
    • /
    • pp.221-228
    • /
    • 2008
  • The injection molding process is able to produce high precision manufactures as a single process with fast speed. However, the prices of both the mold and the molding machine are expensive, and the single process is very complex and difficult to compose of the exact relationship between the process setting conditions and the product quality. Therefore, the quality of a molded product often depends on a skillful engineer's operations in the design of both parts and molds. In this paper, the relationship between the process conditions and the defectiveness is built for better manufactures under settings of the appropriate parameters, and so it can reduce the setup time in the injection molding process. Quality Function Deployment (QFD) provides severe defectiveness factors along with the related process parameters. Also, neural networks estimate the relationship between defective factors and process setting parameters, and lead to reduce the defectiveness of molded parts.