• 시스템엔지니어링학술지
• /
• 제11권2호
• /
• pp.95-105
• /
• 2015

Manufacturing Execution System(MES) is in charge of manufacturing execution in the shop floor based on the inputs given by high level information such as ERP, etc. The typical MES implemented is not tightly interconnected with shop floor control system including real (or near real) time monitoring and control devices such as PLC. The lack of real-time interfaces is one of the major obstacles to achieve accurate and optimization of the total performance index of the shop floor system. Smart factory system in the paradigm of Industry 4.0 tries to solve the problems via CPS (Cyber Physical System) technology and FILS (Factory In-the-Loop System). In this paper, we conducted Systems Engineering Approach to design an advanced MES (namely Smart MES) that can accommodate CPS and FILS concept. Specifically, we tailored Systems Engineering Process (SEP) based on an International Standard formalized as ISO/IEC 15288 to develop Stakeholders' Requirements (StR), System Requirements (SyR). The deliverables of each process are modeled and represented by the SysML, UML customized to Systems Engineering. The results of the research can provide a conceptual framework for future MES that can play a crucial role in the Smart Factory.

• 정보화정책
• /
• 제25권3호
• /
• pp.3-28
• /
• 2018

본 연구의 목적은 국내 및 해외 공히 국가 차원에서 중요한 혁신 의제로 추진하고 있는 제 4차 산업혁명, 인더스트리 4.0, 스마트 제조 등에서 중요한 위치를 차지하고 있는 사이버 물리 시스템(Cyber Physical System: CPS) 분야의 연구 동향을 분석하고, 향후 연구 방향을 제시하는 것이다. 본 연구에서는 (1) 인더스트리4.0과 스마트 제조의 개념, CPS의 기본 개념과 역할 등을 정리하고, (2) 이 분야의 문헌을 분석하여 향후 연구 방향을 제시할 수 있는 분석 기준들을 설정하고, (3) 제조 CPS 관련 주요 연구 결과를 분석하고 향후 연구 방향을 제시한다. '구글 학술검색'을 통해서 식별된 2013년부터 2017년까지 발간된 제조 CPS에 대한 74 개의 해외문헌과 8개의 국내 문헌을 분석한 결과를 정리하면 다음과 같다. (1) 기존에 제시된 다양한 관점의 방법론과 프레임워크를 바탕으로 제조 CPS분야에 대한 공통의 방법론과 프레임워크를 제시하는 연구가 필요하다. (2) 제조 CPS 분야의 성숙도를 높이기 위해서는 기존의 시스템을 포함하여 CPS 시스템을 실제로 구현하고 운영하는데 관한 연구가 필요하다. (3) 제조 CPS 시스템을 진단하고 개선 방향을 제시할 수 있는 진단 방법론에 관한 연구가 필요하다. (4) 세부 모델 및 툴 측면에서는 CPS의 특성을 감안한 SCM 및 생산계획 모델과 인간 기계 협업에 관한 연구에 대한 강화가 필요하다.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.204-206
• /
• 2022

스마트 팩토리(Smart Factory) 고도화의 핵심으로 평가되는 디지털 트윈(Digital Twin)은 현실 세계의 자산과 동일한 속성 및 기능을 가지는 디지털 복제본을 가상의 세계에 구현하는 기술이다. 디지털 트윈 기술이 적용된 스마트팩토리는 생산공정의 실시간 모니터링, 생산공정 시뮬레이션, 생산설비 예지보전 등의 서비스를 지원할 수 있어 생산비용 절감 및 생산성 향상에 기여할 것으로 기대된다. AAS(Asset Administration Shell)는 디지털 트윈을 구현하기 위한 필수 기술로, 현실의 물리적 자산을 디지털로 표현하는 방법을 제공한다. 본 논문에서는 스마트팩토리 내 생산설비를 자산으로 간주하여, 운용 중인 실시간 CNC(Computer Numerical Control) 모니터링 시스템에서 활용할 제조 데이터 수집을 위한 AAS를 설계하였다.

• 산업경영시스템학회지
• /
• 제44권4호
• /
• pp.12-22
• /
• 2021

This article suggests the machine learning model, i.e., classifier, for predicting the production quality of free-machining 303-series stainless steel(STS303) small rolling wire rods according to the operating condition of the manufacturing process. For the development of the classifier, manufacturing data for 37 operating variables were collected from the manufacturing execution system(MES) of Company S, and the 12 types of derived variables were generated based on literature review and interviews with field experts. This research was performed with data preprocessing, exploratory data analysis, feature selection, machine learning modeling, and the evaluation of alternative models. In the preprocessing stage, missing values and outliers are removed, and oversampling using SMOTE(Synthetic oversampling technique) to resolve data imbalance. Features are selected by variable importance of LASSO(Least absolute shrinkage and selection operator) regression, extreme gradient boosting(XGBoost), and random forest models. Finally, logistic regression, support vector machine(SVM), random forest, and XGBoost are developed as a classifier to predict the adequate or defective products with new operating conditions. The optimal hyper-parameters for each model are investigated by the grid search and random search methods based on k-fold cross-validation. As a result of the experiment, XGBoost showed relatively high predictive performance compared to other models with an accuracy of 0.9929, specificity of 0.9372, F₁-score of 0.9963, and logarithmic loss of 0.0209. The classifier developed in this study is expected to improve productivity by enabling effective management of the manufacturing process for the STS303 small rolling wire rods.

• International Journal of Advanced Culture Technology
• /
• 제9권4호
• /
• pp.355-362
• /
• 2021

Through the Korean version of the New Deal 2.0, manufacturing-oriented SMEs are facing a new environmental change called smart factory construction. In addition, SMEs are facing new security threats along with a contactless environment due to COVID-19. However, it is practically impossible to apply the previously researched and developed security management system to protect the core technology of manufacturing-oriented SMEs due to the lack of economic capacity of SMEs. Therefore, through research on security management systems suitable for SMEs, it is necessary to strengthen their business competitiveness and ensure sustainability through proactive responses to security threats faced by SMEs. The security management system presented in this study is a security management system to prevent technology leakage applicable to SMEs by deriving and reflecting the minimum security requirements in consideration of technology protection point of view, smart factory, and remote access in a non-contact environment. It is also designed in a modular form. The proposed security management system is standardized and can be selectively used by SMEs.

• 센서학회지
• /
• 제24권5호
• /
• pp.299-305
• /
• 2015

Since the natural disasters such as floods, droughts, heat wave and cold wave are increasing, the need for risk management is necessary to minimize the damage with utilizing IT technology. Also, the monitoring services of disaster response type have been developed and applied. Recently, the open source hardware based on the signal of the sensor, or the monitoring studies have been carried. In this paper, by analyzing a low-cost open source hardware platform such as Beagle board, we examine the utilization of the hardware-based module for sensor monitoring.

• 대한안전경영과학회지
• /
• 제24권2호
• /
• pp.135-142
• /
• 2022

The smart factory is an important system that can reduce defects, maximize productivity, and respond to customer needs, from the labor-intensive era of traditional small and medium-sized manufacturing companies through the automation era to CPS using ICT. However, small and medium-sized manufacturers often fall short of the basic stage due to economic and environmental constraints, and there are many companies that do not even recognize the concept of a smart factory. In this situation, to expand the smart factory of small and medium-sized enterprises, the project to support the establishment of a smart factory for the win-win between large and small enterprises. The win-win smart factory construction support project provides a customized differentiation program support project according to the size and level of the company for all domestic manufacturing SMEs regardless of whether or not they are dealing with Samsung. In this study, we analyze the construction status and introduction performance of companies participating in the win-win smart factory support project to find out whether they have been helpful in management and to find efficient ways to improve support policies, and to suggest the direction of continuous support projects to improve the manufacturing competitiveness of SMEs in the future.

• 반도체디스플레이기술학회지
• /
• 제22권4호
• /
• pp.108-112
• /
• 2023

Precision manufacturing technology is rapidly developing due to the extreme miniaturization of semiconductor processes to comply with Moore's Law. Accurate and precise alignment, which is one of the key elements of the semiconductor pre-process and post-process, is very important in the semiconductor process. The center detection of wafer align marks plays a key role in improving yield by reducing defects and research on accurate detection methods for this is necessary. Methods for accurate alignment using traditional image sensors can cause problems due to changes in image brightness and noise. To solve this problem, engineers must go directly into the line and perform maintenance work. This paper emphasizes that the development of AI technology can provide innovative solutions in the semiconductor process as high-resolution image and image processing technology also develops. This study proposes a new wafer center detection method through variable thresholding. And this study introduces a method for detecting the center that is less sensitive to the brightness of LEDs by utilizing a high-performance object detection model such as YOLOv8 without relying on existing algorithms. Through this, we aim to enable precise wafer focus detection using artificial intelligence.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2012년도 춘계학술대회 논문집
• /
• pp.541-542
• /
• 2012

• 한국컴퓨터정보학회논문지
• /
• 제25권7호
• /
• pp.143-150
• /
• 2020

최근 모바일, 클라우드, 그리고 사물인터넷의 융합으로 다양한 스마트팩토리 서비스가 제공되고, 많은 기업에서도 관심을 가지고 있다. 그러나 대부분의 시스템은 근로자 관점에서 구현되지 않았기 때문에 근로자로부터 외면 받고 있다. 이에 본 논문은 스마트공장 서비스를 수요자들이 정의하여 사용할 수 있도록 서비스 제작을 현장 근로자가 직접할 수 있는 개발도구를 구현하였다. 서비스에 사용되는 제조데이터는 제조설비와 연결된 센서로부터 실시간으로 수집하여 스마트팩토리 플랫폼 내에 저장된다. 그리고 플랫폼에 저장된 제조데이터로부터 설비 모니터링, 공정상태분석, 설비 제어 등 다양한 스마트 공장 서비스를 근로자가 직접 드래그앤드롭 방식으로 매우 쉽게 만들 수 있다. 구현된 시스템은 특히 소규모 제조 기업에서 기업의 특정 목적에 맞게 수시로 서비스를 변경해야하는 환경에서 더욱더 큰 효과를 낼 것으로 예상된다. 또한, 현장 근로자의 스마트팩토리 운용 및 활용 능력 향상은 물론 중소기업의 스마트팩토리 인재 양성에 많은 도움이 될 것으로 기대된다.