• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2000년도 추계학술대회논문집A
• /
• pp.766-771
• /
• 2000

As using of insulating material of plastic to industrial electric field, thermoset has been gradually substituted for thermoplastic. But changing the material with crystalline has some problem, which is strength or warpage, Especially getting a strength to endure inner pressure is necessary when arc is occurred. So we use the material that is composed of glass fiber to compensate strength. By the way as the reinforced glass-fiber material is used in injection molding, unstableness of dimension is appeared frequently and it is difficult to know warpage pattern. So this paper will be contributed to know warpage pattern of mold product that is upper frame of magnetic contactor caused by glass-fiber orientation with fixed gate-system, when glass-fiber reinforced material with classification of poly-amide is used in injection molding.

• 경영과학
• /
• 제18권2호
• /
• pp.25-38
• /
• 2001

The well-known back-propagation algorithm for multi-layered neural network has successfully been applied to pattern c1assification problems with remarkable flexibility. Recently. the multi-layered neural network is used as a powerful data mining tool. Nevertheless, in many cases with complex boundary of classification, the successful learning is not guaranteed and the problems of long learning time and local minimum attraction restrict the field application. In this paper, an Improved learning procedure of multi-layered neural network is proposed. The procedure is based on the generalized delta rule but it is particular in the point that the architecture of network is not fixed but enlarged during learning. That is, the number of hidden nodes or hidden layers are increased to help finding the classification boundary and such procedure is controlled by entropy evaluation. The learning speed and the pattern classification performance are analyzed and compared with the back-propagation algorithm.

• Communications for Statistical Applications and Methods
• /
• 제9권1호
• /
• pp.155-166
• /
• 2002

Neural networks have been studied as a popular tool for classification and they are very flexible. Also, they are used for many applications of pattern classification and pattern recognition. This paper focuses on Bayesian approach to feed-forward neural networks with single hidden layer of units with logistic activation. In this model, we are interested in deciding the number of nodes of neural network model with p input units, one hidden layer with m hidden nodes and one output unit in Bayesian setup for fixed m. Here, we use the latent variable into the prior of the coefficient regression, and we introduce the 'sequential step' which is based on the idea of the data augmentation by Tanner and Wong(1787). The MCMC method(Gibbs sampler and Metropolish algorithm) can be used to overcome the complicated Bayesian computation. Finally, a proposed method is applied to a simulated data.

• 공학교육연구
• /
• 제16권2호
• /
• pp.24-30
• /
• 2013

This paper deals with the measurement theory and technique of linear expansion coefficient for solid material using Michelson interferometer. The Michelson interferometer produces interference fringes by splitting a beam of monochromatic light so that one beam strikes a fixed mirror and the other a movable mirror. When the reflected beams are brought back together, an interference pattern results. Precise distance measurements until a quarter of wave length can be made with the Michelson interferometer by moving the mirror and counting the interference fringes which move by a photo diode. This paper represents the application of Michelson interferometer for measuring infinitesimal length system and shows the measurement method of linear expansion coefficients for various materials like copper, aluminum and iron. the results are good agreement with theoretical value within margin of error for each materials.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1998년도 추계학술대회 논문집 학회본부 B
• /
• pp.481-483
• /
• 1998

In general, spatial filtering method was proposed to simplify measurement system through parallel Processing hardware. Spatial filtering is a method of detection that we can get a spatial pattern information, as we process a special space pattern, to say, as we process spatial parallel process by using the spatial weighting function. The important processing characteristics will be depended in according to how ire design a spatial weighting function, a spatial sensitive distribution. The form of the weighting function which is realized from the generally used spatial filtering is fixed and the weighting value was already became a binary-value. In this paper, we propose a new method in order to construct adaptive measurement systems. This method is a weighting function design to make multi-valued and variable.

• Structural Engineering and Mechanics
• /
• 제31권2호
• /
• pp.153-162
• /
• 2009

The reduction of the dynamic response of an offshore structure subjected to wind-generated random ocean waves is of extreme significance in the aspects of serviceability, fatigue life and safety of the structure. In this study, a new neuro-control scheme is applied to the vibration control of a fixed offshore platform under random wave loads to examine the applicability of the proposed method. It is called the Lattice Probabilistic Neural Network (LPNN), as it utilizes lattice pattern of state vectors as the training data of PNN. When control results of the LPNN are compared with those of the NN and PNN, LPNN showed better performance in effectively suppressing the structural responses in a shorter computational time.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2006년도 추계 학술발표회 논문집
• /
• pp.381-384
• /
• 2006

In order to evaluate the seismic performance of a reinforced concrete building structure, four different analyses are carried out. Firstly, conventional pushover analysis with code-specified inverted triangular load pattern is conducted. Secondly, the pushover analysis with uniform load pattern is performed. Thirdly, adaptive pushover analyses with spectral amplification for both EC 8 artificial and Northridge earthquake are carried out. Lastly, incremental dynamic analyses under a number of scaled PGA for both EC 8 artificial and Northridge earthquake record are performed. Comparative studies demonstrate that the adaptive pushover analysis may be able to explain the response characteristics that conventional pushover analysis with fixed load distribution fails to capture.

• 한국정보처리학회논문지
• /
• 제3권3호
• /
• pp.429-438
• /
• 1996

본 논문에서는 주어진 문제를 해결하기 위해 사용될 최적의 다충 퍼센트론을 구성 하기 위한 하나의 점진적 학습 방법을 제시한다. 고정된 크기의 트레이닝 패턴 집합을 반복적으로 사용하는 기존의 알고리즘들과는 달리, 제시되는 방법에서는 학습 패턴의 수를 점차 증가시키면서 전체 데이터를 학습하기 위해 필요하고도 충분한 은닉뉴런의 수를 찾는다. 이와 같이 신경망 크기의 최적화에 학습 패턴을 점차적으로 선택하여 늘려나감으로써 일반화 능력과 학습 속도가 기존의 방법에서보다 향상됨을 필기체 숫자인식 문제에 있어서 실험적으로 보여준다.

• 한국전기전자재료학회논문지
• /
• 제25권11호
• /
• pp.857-861
• /
• 2012

FPN (fixed-pattern-noise) mainly comes from the device or pattern mismatches in pixel and color filter, pixel photodiode leakage in CMOS image sensor. In this paper, optical stack module related pixel FPN was investigated and the classification of pixel FPN contribution with the individual optical module process was presented. The methodology and procedure would be helpful in reducing the greater pixel FPN and distinguishing the complex FPN sources with respect to various noise factors.

• 한국진공학회지
• /
• 제15권6호
• /
• pp.594-604
• /
• 2006

일정한 기체 공급 압력에서 정해진 만큼 밸브를 개방하는 방식과 밸브를 조절하여 일정한 유량을 흐르도록 하는 두 가지 기체 주입 방식의 작동특성에 대한 시뮬레이션을 통해 공급 압력, 밸브 컨덕턴스, 유량 등 시스템 조건 및 기체 수송관의 길이와 굵기에 따라 기체흐름의 유형이 어떻게 바뀌는지 조사했다.