• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2008년도 추계학술대회 논문집 Vol.21
• /
• pp.160-160
• /
• 2008

In practical etching process, etch ant is sprayed on the metal-deposited panel through nozzles collectively connected to the manifold and that panel is usually composed of many PCB(printed circuit board)'s. The etching uniformity, the difference between individual PCB's on the same panel, has become one of most important features of etching process. In this paper, the prediction of nozzle trajectory has been performed by the combination of algebraic formula and numerical simulation. With the pre-determined geometrical factors of nozzle distribution, the trajectories of individual nozzles were predicted with the change of process operational factors such as panel speed, nozzle swing frequency and so on. As results, two dimensional distribution of impulsive force of etchant spray which could be considered as a key factor determining the etching performance have been successfully obtained. Though only qualitative prediction of etching uniformity have been predicted by the process developed in this study, the expansion to the quantitative prediction of etching uniformity is expected to be apparent by this study.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1997년도 추계학술대회 논문집
• /
• pp.1051-1055
• /
• 1997

Hot forging is widely used in the manufacturing of automotive component. The mechanical, thermal load and thermal softening which is happened by the high temperature die in hot forging. Tool life of hot forging decreases considerably due to the softening of the surface layer of a tool caused by a high thermal load and long contact time between the tool and workpieces. The service life of tools in hot forging process is to a large extent limited by wear, heat crack, plastic deformation. These are one of the main factors affecting die accuracy and tool life. It is desired to predict tool life by developing life prediction method by FE-simulation. Lots of researches have been done into the life prediction of cold forming die, and the results of those researches were trustworthy, but there have been little applications of hot forming die. That is because hot forming process has many factors influencing tool life, and there was not accurate in-process data. In this research, life prediction of hot forming die by wear analysis and plastic deformation has been carried out. To predict tool life, by experiment of tempering of die, tempering curve was obtained and hardness express a function of main tempering curve.

• Communications for Statistical Applications and Methods
• /
• 제24권4호
• /
• pp.383-396
• /
• 2017

The model in our approach assumes that computer responses are a realization of a Gaussian processes superimposed on a regression model called a Gaussian process regression model (GPRM). Selecting a subset of variables or building a good reduced model in classical regression is an important process to identify variables influential to responses and for further analysis such as prediction or classification. One reason to select some variables in the prediction aspect is to prevent the over-fitting or under-fitting to data. The same reasoning and approach can be applicable to GPRM. However, only a few works on the variable selection in GPRM were done. In this paper, we propose a new algorithm to build a good prediction model among some GPRMs. It is a post-work of the algorithm that includes the Welch method suggested by previous researchers. The proposed algorithms select some non-zero regression coefficients (${\beta}^{\prime}s$) using forward and backward methods along with the Lasso guided approach. During this process, the fixed were covariance parameters (${\theta}^{\prime}s$) that were pre-selected by the Welch algorithm. We illustrated the superiority of our proposed models over the Welch method and non-selection models using four test functions and one real data example. Future extensions are also discussed.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제2권4호
• /
• pp.281-290
• /
• 2013

IT자산은 조직의 경영목적을 지원해주는 핵심영역이며, IT자산의 장애 발생시 신속한 처리를 지원하는 것은 매우 중요하다. 본 연구에서는 IT자산의 장애가 발생할 경우, 장애해결을 위하여 기존의 장애 데이터를 기초로 장애처리 예측 기법을 제시한다. 제안한 장애처리 예측 기법은 첫째, 기존의 장애처리 데이터를 전처리하여 장애처리 유형별로 분류하고 둘째, 분류된 장애처리 유형과 장애 발생 후 접수된 내용을 키워드 매핑시키는 규칙을 제정하였으며 셋째, 제정된 규칙에 의하여 장애 발생 후 장애처리 방법이 사전에 예측 가능한 기계학습 프로세스를 제시하였다. 제시한 기계학습 프로세스의 유효성을 입증하기 위하여 A사에서 6개월 동안 접수된 33,000여건의 전산기기 장애 데이터를 실험한 결과 장애처리 예측의 적중률이 약 72%였으며, 지속적인 기계학습을 통하여 81%로 향상되었다.

• 대한산업공학회지
• /
• 제40권3호
• /
• pp.257-266
• /
• 2014

The semiconductor manufacturing industry is managed by a number of parameters from the FAB which is the initial step of production to package test which is the final step of production. Various methods for prediction for the quality and yield are required to reduce the production costs caused by a complicated manufacturing process. In order to increase the accuracy of quality prediction, we have to extract the significant features from the large amount of data. In this study, we propose the method for extracting feature from the cell level data of probe test process using OPTICS which is one of the density-based clustering to improve the prediction accuracy of the quality of the assembled chips that will be placed in a package test. Two features extracted by using OPTICS are used as input variables of quality prediction model because of having position information of the cell defect. The package test progress for chips classified to the correct quality grade by performing the improved prediction method is expected to bring the effect of reducing production costs.

• 한국전자거래학회지
• /
• 제15권4호
• /
• pp.303-317
• /
• 2010

본 논문에서는 KNN 대체와 LOF 알고리즘의 결합 모델을 확장하여 실시간 비즈니스 프로세스 모니터링을 위한 비정상 종료 예측 방법론을 제안하였다. 기존의 룰 기반 모니터링 방법론은 실시간 프로세스 진행 정도에 따른 비관측 정보에 기인하여 조기 경보 및 실시간 대응이 힘들다는 한계점을 안고 있다. 이를 해결하기 위하여 비관측 정보에 대한 가정 및 진행 중인 프로세스의 향후 경로 예측을 통해 종료 시점에서 예상되는 LOF를 추정하기 위한 알고리즘을 제안하였다. 이 알고리즘을 적용하여 실시간 비즈니스 프로세스 모니터링 과정에서 각 관측 시점마다 종료 시점에서의 결과를 예측함으로써, 전 시점에 걸친 추세를 살펴종료 패턴을 예측할 수 있다. 이를 통해 비즈니스 프로세스의 실시간 진척에 대한 정보를 가시화함으로써 기회 및 위협에 사전에 대응할 수 있게 하여 프로세스 관리 수준의 향상을 기대할 수 있을 것으로 예상된다.

• 한국정밀공학회지
• /
• 제21권9호
• /
• pp.95-102
• /
• 2004

A flexible incremental roll forming process has been developed by adopting the advantages of the incremental forming process and the roll forming process: i.e., inherent flexibility of the incremental forming process and continuous bending deformation of the roll forming process. It has an adjustable roll set as a forming tool composed of one upper center roll and two pairs of lower support rolls, which plays a key role during forming process. Through the experiments based on the various combinations of process parameters, it is shown that the incremental roll forming process is so effective as to manufacture various doubly curved sheet metals including concave-convex combination shapes in which there exists a line of inflection. The proposed relationship of the experimental parameters and the radius of curvature of the formed sheet boundary is found to be useful in prediction and control of the final shape.

• 한국공작기계학회:학술대회논문집
• /
• 한국공작기계학회 2004년도 춘계학술대회 논문집
• /
• pp.394-397
• /
• 2004

This paper presents a simple analytic method using 2D simulation program for predications of cutting force and machining temperature in dry type milling process. And also, comparison of cutting force and machining temperature obtained from experiment and simulation work is accomplished to distinguish of suitability.

• 소성∙가공
• /
• 제11권7호
• /
• pp.581-588
• /
• 2002

Among the processes to produce micro lens, the process using press molding is a new technology to simplify the process, but it contains many unknown variables. The press-molding process proposed in this paper was simplified into two step process, the first step is the pressing to design the preform for glass element, the second step is the annealing to reduce the residual stress. It is important to estimate the amount of shrinkage of glass gob and the residual stress during process. It Is difficult to evaluate the process variables as mentioned above through the experiment. The influences due to process variables was evaluated by using FEM parametric analysis. The results in this paper can be applicable to produce micro lens.

• Transactions on Control, Automation and Systems Engineering
• /
• 제3권1호
• /
• pp.10-14
• /
• 2001

We studied the use of time-related information, with and without prediction, to support human operators performing moni-toring and control tasks in the process. Based on monitoring and control techniques used for Project Management we developed a display design for the process industries. A simulated power plant was used to test the hypothesis that availability of predictions along with information on past trends can improve the performances of the human operator handling faults. Several designs of dis-plays were tested in the experiment in which human operators had to detect and handle two types of faults(local and systems wide) in the simulated electricity generation process. Analysis of the results revealed that temporal data, with and without prediction, signifi-cantly reduced response time. Our results encourage the integration of temporal information and prediction in displays used for the control processes to enhance the capabilities of the human operators. Based on the analysis we proposed some guidelines for the de-signer of the human interface of a process control system.