• 한국공작기계학회논문집
• /
• 제12권5호
• /
• pp.53-58
• /
• 2003

Wear debris can be collected from the lubricants of operating machinery and its morphology is directly related to the fiction condition of the interacting materials from which the wear particles originated in lubricated machinery. But in order to predict and estimate working conditions, it is need to analyze the shape characteristics of wear debris and to identify. Therefore, if the shape characteristics of wear debris is identified by computer image analysis and the neural network, The four parameter (50% volumetric diameter, aspect, roundness and reflectivity) of wear debris are used as inputs to the network and learned the friction. It is shown that identification results depend on the ranges of these shape parameters learned. The three kinds of the wear debris had a different pattern characteristic and recognized the friction condition and materials very well by neural network. We resented how the neural network recognize wear debris on driving condition.

• 한국정보과학회논문지:시스템및이론
• /
• 제34권5_6호
• /
• pp.176-186
• /
• 2007

상호연결망은 그래프로 모델링 할 수 있다: 노드는 정점으로 대응시키고, 링크는 에지로 대응시킨다. 상호연결망(그래프)의 지름은 서로 다른 모든 두 정점 사이의 최단경로 길이 중 최대이다. 상호연결망의 고장지름이란 연결도-1 개 이하의 임의의 정점에 고장이 있을 경우, 이들 고장 정점들을 제거한 연결망에서 모든 두 정점사이의 최단경로 길이 중 최대이다. 지름이 3이상이고 연결도가 r인 r-정규(regular) 그래프의 고장지름은 지름+1이상이다. 이 논문에서는 $m,n{\geq}3$ 인 2-차원 $m{\times}n$ 토러스에서 m=3 혹은 n=3일 때 고장지름은 max(m,n)이고, m,n>3일 때 고장지름은 지름 +1임을 보인다. 그리고 $k_i{\geq}3(1{\leq}i{\leq}d)$이고 $d{\geq}3$인 d- 차원 $k_1{\times}k_2{\times}{\cdots}{\times}k_d$ 토러스에서 서로 다른 임의의 두 정점 사이에 길이가 지름+1이하인 서로소인 경로들이 2d 개 존재함을 보인다. 두 정점 u와 v 사이의 서로소인 경로들이란, 공통의 정점들이 u와 v만 있는 경로들을 말한다. 이들 서로소인 경로들을 이용하여 $k_i{\geq}3(1{\leq}i{\leq}d)$이고 $d{\geq}3$인 d-차원 $k_1{\times}k_2{\times}{\cdots}{\times}k_d$ 토러스의 고장지름이 지름+1임을 보인다.

• 정보처리학회논문지A
• /
• 제17A권1호
• /
• pp.1-8
• /
• 2010

고장 지름은 상호연결망의 통신 능률과 신뢰도를 평가하는 중요한 척도 중의 하나이다. 이형옥 외 4인[Folded 하이퍼-스타 그래프의 병렬 경로, 한국정보처리학회논문지, Vol.6, No.7, pp.1756-1769, 1999]은 폴디드 하이퍼-스타 FHS(2n,n)의 노드 중복 없는 경로를 제안하였고, FHS(2n,n)의 고장 지름이 2n-1 이하임을 증명하였다. 본 논문에서는 폴디드 하이퍼-스타 FHS(2n,n)의 개선된 노드 중복 없는 경로를 제안한다. 그리고 FHS(2n,n)의 광역 지름이 dist(U,V)+4이고, 고장 지름이 n+2 이하임을 증명한다.

• 한국정밀공학회지
• /
• 제15권3호
• /
• pp.133-140
• /
• 1998

The neural network was applied to identify wear debris generated from the lubricated machine surface. The wear test was carried out under different experimental conditions. In order to describe characteristics of debris of various shapes and sizes, the four shape parameter(50％ volumetric diameter, aspect, roundness and reflectivity) of wear debris are used as inputs to the network and learned the friction condition of five values(material 3, applied load 1, sliding distance 1). It is shown that identification results depend on the ranges of these shape parameter learned. The three kinds of the wear debris had a different pattern characteristics and recognized the friction condition and materials very well by neural network.

• 한국정보과학회논문지:시스템및이론
• /
• 제35권9_10호
• /
• pp.421-428
• /
• 2008

[1]에서 A. Ghafoor는 고장허용 다중컴퓨터에 대한 하나의 모형으로 이븐 연결망 $E_d$를 소개하였고, 최단거리를 갖는 노드 중복 없는 경로를 포함한 여러 가지 성질들을 발표하였다. [1]에서 제안한 노드 중복 없는 경로에 의해 고장 지름을 구하면, 고장 지름은 d+2(d=홀수)와 d+3(d=짝수)이다. 그러나 [1]에서 증명한 노드 중복 없는 경로는 최단 거리가 아니다. 본 논문에서는 이븐 연결망 $E_d$가 노드 대칭임을 보이고, 순환적 교환 순서를 이용하여 이븐 연결망의 최단 거리를 갖는 노드 중복 없는 경로를 제시하고, 고장지름이 d+1임을 증명한다.

• 한국정보통신학회논문지
• /
• 제21권7호
• /
• pp.1327-1334
• /
• 2017

버블정렬 그래프는 노드 대칭이며 데이터 정렬 알고리즘에 활용 할 수 있다. 본 연구에서는 버블정렬 그래프의 망 비용을 개선한 하프 버블정렬 그래프를 제안하고 분석한다. 하프 버블정렬 그래프 $HB_n$의 노드수는 n!이고 분지수는 ${\lfloor}n/2{\rfloor}+1$이다. 하프 버블정렬 그래프의 분지수는 버블정렬 그래프의 분지수의 $${\sim_=}0.5$$배 이고, 지름은 $${\sim_=}0.9$$배 이다. 버블정렬 그래프의 망 비용은 $${\sim_=}0.5n^3$$이고, 하프 버블정렬 그래프의 망 비용은 $${\sim_=}0.2n^3$$이다. 하프 버블정렬 그래프는 버블정렬 그래프의 서브 그래프임을 증명하였다. 추가로 라우팅 알고리즘을 제안하였고 지름을 분석하였다. 마지막으로 버블정렬 그래프와 망 비용을 비교 하였다.

• 대한기계학회논문집B
• /
• 제31권8호
• /
• pp.663-671
• /
• 2007

In this work, shape optimization of a wire-wrapped fuel assembly in a liquid metal reactor has been carried out by combining a three-dimensional Reynolds-averaged Navier-Stokes analysis with the radial basis neural network method, a well known surrogate modeling technique for optimization. Sequential Quadratic Programming is used to search the optimal point from the constructed surrogate. Two geometric design variables are selected for the optimization and design space is sampled using Latin Hypercube Sampling. The optimization problem has been defined as a maximization of the objective function, which is as a linear combination of heat transfer and friction loss related terms with a weighing factor. The objective function value is more sensitive to the ratio of the wire spacer diameter to the fuel rod diameter than to the ratio of the wire wrap pitch to the fuel rod diameter. The optimal values of the design variables are obtained by varying the weighting factor.

• 한국공작기계학회논문집
• /
• 제12권5호
• /
• pp.1-7
• /
• 2003

In order to predict vibrations occurred during end-milling processes, the cutting dynamics was modelled by using neural network and combined with structural dynamics by considering dynamic cutting state. Specific cutting force constants of the cutting dynamics model were obtained by averaging cutting forces. Tool diameter, cutting speed, fled, axial and radial depth of cut were considered as machining factors in neural network model of cutting dynamics. Cutting farces by test and by neural network simulation were compared and the vibration displacement during end-milling was simulated.

• KSTLE International Journal
• /
• 제2권1호
• /
• pp.65-70
• /
• 2001

The wear debris is fall off the moving surfaces in oil-lubricated systems and its morphology is directly related to the damage and failure to the interacting surfaces. The morphology of the wear particles are therefore directly indicative of wear processes occurring in tribological system. The computer image processing and artificial neural network was applied to shape study and identify wear debris generated from the lubricated moving system. In order to describe the characteristics of various wear particles, four representative parameter (50％ volumetric diameter, aspect, roundness and reflectivity) from computer image analysis for groups of randomly sampled wear particles, are used as inputs to the network and learned the friction condition of five values (material 3, applied load 1, sliding distance 1). It is shown that identification results depend on the ranges of these shape parameters learned. The three kinds of the wear debris had a different pattern characteristics and recognized the friction condition and materials very well by neural network. We discuss how these approach can be applied to condition diagnosis of the oil-lubricated tribological system.

• Design & Manufacturing
• /
• 제15권4호
• /
• pp.24-31
• /
• 2021

In this study, an artificial neural network model was constructed to convert CAE analysis data into similar experimental data. In the analysis and experiment, the injection molding data for 50 conditions were acquired through the design of experiment and random selection method. The injection molding conditions and the weight, height, and diameter of the product derived from CAE results were used as the input parameters for learning of the convert model. Also the product qualities of experimental results were used as the output parameters for learning of the convert model. The accuracy of the convert model showed RMSE values of 0.06g, 0.03mm, and 0.03mm in weight, height, and diameter, respectively. As the next step, additional randomly selected conditions were created and CAE analysis was performed. Then, the additional CAE analysis data were converted to similar experimental data through the conversion model. An artificial neural network model was constructed to predict the quality of injection molded product by using converted similar experimental data and injection molding experiment data. The injection molding conditions were used as input parameters for learning of the predicted model and weight, height, and diameter of the product were used as output parameters for learning. As a result of evaluating the performance of the prediction model, the predicted weight, height, and diameter showed RMSE values of 0.11g, 0.03mm, and 0.05mm and in terms of quality criteria of the target product, all of them showed accurate results satisfying the criteria range.