• 대한안전경영과학회지
• /
• 제9권6호
• /
• pp.181-191
• /
• 2007

The purpose of this paper is to develop an efficient production strategy with changing factors to influence the productivity. The factors would be the number of Multi-Function worker, the method of job dispatching, and lot size. A simulation model has been developed for this study. We used AutoMod simulation and the process activity was animated to follow the flow of process easily. The alternatives have been tested through the simulation model, and the various alternatives is proposed for the efficient production strategy. We hope that the system is applied to similar types of small and medium-sized enterprises to develop an efficient production strategy and to achieve the satisfactory result.

• 한국경영과학회:학술대회논문집
• /
• 대한산업공학회/한국경영과학회 2002년도 춘계공동학술대회
• /
• pp.632-638
• /
• 2002

In novelty detection, one attempts to discriminate abnormal patterns from normal ones. Novelty detection is quite difficult since, unlike usual two class classification problems, only normal patterns are available for training. Auto-Associative Multi-Layer Perceptron (AAMLP) has been shown to provide a good performance based upon the property that novel patterns usually have larger auto-associative errors. In this paper, we give a mathematical analysis of 2-layer AAMLP's output characteristics and empirical results of 2-layer and 4-layer AAMLPs. Various activation functions such as linear, saturated linear and sigmoid are compared. The 2-layer AAMLPs cannot identify non-linear boundaries while the 4-layer ones can. When the data distribution is multi-modal, then an ensemble of AAMLPs, each of which is trained with pre-clustered data is required. This paper contributes to understanding of AAMLP networks and leads to practical recommendations regarding its use.

• 대한안전경영과학회지
• /
• 제12권3호
• /
• pp.333-339
• /
• 2010

Data mining is the process of finding and analyzing data from a big database and summarizing it into useful information for a decision-making. A variety of data mining techniques have been being used for wide range of industries. One application of those is especially so for gathering meaningful information from process data in manufacturing factories for quality improvement. The purpose of this paper is to provide a methodology to improve manufacturing quality of fuel tanks which are auto-parts. The methodology is to analyse influential attributes and establish a model for optimal manufacturing condition of fuel tanks to improve the quality using decision tree, association rule, and feature selection.

• 한국경영정보학회:학술대회논문집
• /
• 한국경영정보학회 2007년도 International Conference
• /
• pp.184-189
• /
• 2007

Concerns about food safety continue to rise and under this situation, governments of some countries have reinforced their regulations more strictly for food safety. In order to prevent food safety incidents or, at least to minimize the impact, the preparedness is very important. As a consequence of this, traceability system has become an essential tool for food safety. Recently, it requires more prevention-based food safety control system. One of the most generally used systems for food safety control is Hazard Analysis and Critical Control Point (HACCP). Both traceability and HACCP systems can be integrated through Electronic Product Code (EPC) Sensor Network technologies which have four value propositions. In this paper, we will introduce the concept of product and process traceability system (P2TS) through the integration of three systems to improve food safety management. The final aim is to find out the added values of the P2TS.

• 디지털융복합연구
• /
• 제8권4호
• /
• pp.73-82
• /
• 2010

자동차 산업은 자동차에 소요되는 2만여가지 이상의 부품의 다양한 종류만큼 시스템적인 표준화가 매우 어려운 산업이다. 이미 완성차업계는 SAP과 같은 글로벌 ERP 패키지를 사용하고 있으며, 기준 정보관리 표준을 만들어 사용하고 있지만, 수많은 부품 공급사들은 기준체계가 없거나, 주먹구구식의 체계로 인해 PDM, ERP, MES등 시스템 도입 및 활용에 가장큰 장애사항이 되고 있다. 이에 본 연구는 국내 자동차 완성차 및 관련부품산업의 실질적인 표준 품번 체계가 통합된 표준 모델을 만들고, 표준화를 위한 지침서를 작성하기 위하여 완성차업계 및 타 산업군 사례기업의 표준체계를 조사하고, 자동차 부품회사를 샘플링하여 실증적으로 연구하여, 유의미코드와 무의미 일련번호의 합리적인 적용 기준을 제시함으로써 국내 자동차 관련 산업의 정보화에 필수적인 기준정보 관리수준의 표준화 체계를 제안한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2002년도 추계학술대회 논문집
• /
• pp.925-928
• /
• 2002

It is well blown that the product development time in manufacturing industry is critical. A new methodology for a product design knowledge management is required to reduce design errors and to optimize a design process. In this paper, Process-Related design knowledge management and Document Template are introduced to provide a design process to prevent previous design errors and a solution for the desist errors. Also the Document Template is more convenient interface in integrating the design knowledge into a system.

• 한국컴퓨터정보학회논문지
• /
• 제12권3호
• /
• pp.203-212
• /
• 2007

지금까지 재 제조에 필요한 자동차 중고부품은 주로 정비업체에서 회수하여 사용하였으나, 회수체계가 정비되어 있지 않아 자동차 중고부품 수집에 많은 시간과 경비가 소요되었으며, 폐차업체에서 생산되는 많은 자동차 중고부품은 재 제조에 활용되지 못하고 있는 실정이다. 본 시스템은 폐차장, 정비업체 등에서 자동차 중고부품 정보를 입력하고, 재 제조업체에서는 이들 정보를 이용하여 재 제조에 필요한 자동차 중고부품을 회수할 수 있게 함으로써 자동차 중고부품 회수체계를 확립하고 자동차 중고부품의 안정적 수급 방안을 마련할 수 있도록 설계하였다. 본 시스템은 자동차 부품 재 제조에 필요한 자동차 중고부품을 수집 관리하기 위한 물류정보시스템으로 DISRMPA(Distribution Information System for Recovery and Management of used Parts of an Automobile)라고 부른다.

• 산업경영시스템학회지
• /
• 제17권32호
• /
• pp.267-279
• /
• 1994

The Ministry of Transportation forecasts that the total number of automobiles in use in 1997 will be increased to about 10 million units. Until now, with the increase of domestic demand for automobiles, the customers' complaints have been raised frequently in relation with insufficient supply of auto parts for the repair and maintenance. At the same time, the industry came to face with new problems such as customers' requests of auto makers' quality services. Until now there were not any statistics on the registration of car age for each car type. So, for the auto makers' efficient aftersales management a system for collecting registration statistics was developed, and it has attributed remarkably to the improvement of the aftersales services, through easy anticipation of the requirements of parts being used for not only the small-produced but the massproduced car types. And a systematic instrument useful for auto industry, transportation and policy on environment is provided by timely supply of various statistics to the industry.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2021년도 제64차 하계학술대회논문집 29권2호
• /
• pp.5-6
• /
• 2021

본 논문에서는 Semi-supervised Learning 방식의 이상감지 방법을 제안한다. 취득한 소음 데이터를 이미지화 시킨 후 Convolution AutoEncoder 학습 방법을 이용하여 모델을 학습한다. 고장 데이터와 정상 데이터 간의 데이터 불균형 문제가 대두되기 때문에 정상 데이터만을 활용한 이상감지는 실제 산업현장의 상황에 알맞게 사용할 수 있을 것이라 기대한다.

• 디지털산업정보학회논문지
• /
• 제13권4호
• /
• pp.25-31
• /
• 2017

In this paper, we propose a study on DB-based automatic crop cultivation that obtains crop cultivation data using IOT and automatically controls the cultivation environment using it. A system for DB-based automatic crop cultivation that automatically controls the cultivation environment is composed of a management server and a local controller. The management server was implemented using the MySQL DB in the Linux server system, and the local controller was designed and manufactured using the WiFi module and ARM Coretax-3 series MCU and confirmed its operation in the laboratory. The purpose of this study is to provide the optimal cultivation data and to grasp the cultivation status in real time when the knowledge of professional cultivation is needed like the farmers of ear farm villages. Research should continue to enable the cultivation of crops to reflect the requirements of each user.