• 한국인터넷방송통신학회논문지
• /
• 제22권4호
• /
• pp.157-163
• /
• 2022

최근 산업 분야 자동화의 발전에 따라 이상 징후 검출에 대한 연구가 활발하게 진행 중이다. 공장 자동화에 사용되는 이상 징후 검출의 응용분야로 카메라를 사용한 결함 검사가 있다. 비전 카메라 검사는 공장 자동화에서 높은 성능과 효율성을 보이지만, 조명과 환경조건의 불안정성을 극복하기가 어렵다. 딥러닝을 이용한 카메라 검사가 훨씬 더 높은 성능을 보이면서 비전 카메라 검사의 문제를 해결할 수 있지만 학습을 위해 엄청난 양의 정상 데이터 및 비정상 데이터를 요구하기 때문에 실제 산업 분야에 적용하기가 어렵다. 따라서 본 연구는 정상 데이터만을 사용한 72개의 기하학적 변환 딥러닝 방법으로 비정상 데이터 수집 문제를 극복하고, 성능 개선을 위한 특이치 노출 방법을 추가한 네트워크를 제안한다. 이를 자동차 부품 데이터 및 이상치 검출용 데이터베이스인 MVTec 데이터 셋에 적용하고 검증함에 의해 실제 산업 현장에서 적용할 수 있음을 보인다.

• 산업공학
• /
• 제16권spc호
• /
• pp.82-86
• /
• 2003

This paper traces the expanding role of simulation from its early beginning on mainframe computers to the $21^{st}$ Century's enterprise manufacturing environment of remote access and control. It includes an examination of the current and future role of integrated graphic animation as a primary medium of technical communications. The paper concludes with an example application of distance learning in the design, analysis, and operation of Programmable Logic Controllers on the Factory Floor of the future.

• 한국산업정보학회논문지
• /
• 제25권2호
• /
• pp.73-85
• /
• 2020

우리나라는 최근까지 양적투입 위주의 제조업 성장 방식을 취해왔을 뿐만 아니라 Fast-follower 전략으로 제조 강국 반열에 올라섰지만 선진국의 제조업 부흥 정책과 신흥국의 산업구조 고도화로 인해 한계에 직면하게 되었다. 최근 4차산업혁명의 도래와 수요의 복잡화로 인해 시장의 변화를 사전에 빠르게 감지해 생산전략에 반영하는 체제가 요구됨에 따라 ICT를 활용하여 제조업의 경쟁력 강화를 위해 스마트 팩토리를 도입은 선택이 아닌 필수가 되어가고 있다. 본 연구는 정보기술혁신 제품인 스마트 팩토리의 지속사용의도에 영향을 미치는 주요 요인들이 무엇인지를 기술수용모형을 토대로 살펴보고자 한다. 이를 위해 본 연구는 스마트 팩토리를 운영 중인 기업들을 대상으로 온라인과 오프라인으로 설문조사를 실시하였으며 122부의 표본으로 분석하였다. 구체적으로 CEO의 리더십, 조직학습, 지각된 전환비용이 기술수용모형의 주요 신념변수인 지각된 사용 용이성과 지각된 유용성을 매개하여 지속사용의도에 미치는 영향을 살펴보았다.

• 품질경영학회지
• /
• 제49권4호
• /
• pp.551-567
• /
• 2021

Purpose: The purpose of this paper is to present implications by analyzing research trends on smart factories by text analysis and visual analysis(Comprehensive/ Fields / Years-based) which are big data analyses, by collecting data based on previous studies on smart factories. Methods: For the collection of analysis data, deep learning was used in the integrated search on the Academic Research Information Service (www.riss.kr) to search for "SMART FACTORY" and "Smart Factory" as search terms, and the titles and Korean abstracts were scrapped out of the extracted paper and they are organize into EXCEL. For the final step, 739 papers derived were analyzed using the Rx64 4.0.2 program and Rstudio using text mining, one of the big data analysis techniques, and Word Cloud for visualization. Results: The results of this study are as follows; Smart factory research slowed down from 2005 to 2014, but until 2019, research increased rapidly. According to the analysis by fields, smart factories were studied in the order of engineering, social science, and complex science. There were many 'engineering' fields in the early stages of smart factories, and research was expanded to 'social science'. In particular, since 2015, it has been studied in various disciplines such as 'complex studies'. Overall, in keyword analysis, the keywords such as 'technology', 'data', and 'analysis' are most likely to appear, and it was analyzed that there were some differences by fields and years. Conclusion: Government support and expert support for smart factories should be activated, and researches on technology-based strategies are needed. In the future, it is necessary to take various approaches to smart factories. If researches are conducted in consideration of the environment or energy, it is judged that bigger implications can be presented.

• International journal of advanced smart convergence
• /
• 제8권2호
• /
• pp.116-125
• /
• 2019

The fire should extinguish as soon as possible because it causes economic loss and loses precious life. In this study, we propose a new atypical fire and smoke detection algorithm using deep learning and color histogram of fire and smoke. First, input frame images obtain from the ONVIF surveillance camera mounted in factory search motion candidate frame by motion detection algorithm and mean square error (MSE). Second deep learning (Faster R-CNN) is used to extract the fire and smoke candidate area of motion frame. Third, we apply a novel algorithm to detect the fire and smoke using color histogram algorithm with local area motion, similarity, and MSE. In this study, we developed a novel fire and smoke detection algorithm applied the local motion and color histogram method. Experimental results show that the surveillance camera with the proposed algorithm showed good fire and smoke detection results with very few false positives.

• 로봇학회논문지
• /
• 제14권1호
• /
• pp.1-7
• /
• 2019

Recently, smart factories have attracted much attention as a result of the 4th Industrial Revolution. Existing factory automation technologies are generally designed for simple repetition without using vision sensors. Even small object assemblies are still dependent on manual work. To satisfy the needs for replacing the existing system with new technology such as bin picking and visual servoing, precision and real-time application should be core. Therefore in our work we focused on the core elements by using deep learning algorithm to detect and classify the target object for real-time and analyzing the object features. We chose YOLO CNN which is capable of real-time working and combining the two tasks as mentioned above though there are lots of good deep learning algorithms such as Mask R-CNN and Fast R-CNN. Then through the line and inside features extracted from target object, we can obtain final outline and estimate object posture.

• Nuclear Engineering and Technology
• /
• 제56권1호
• /
• pp.222-232
• /
• 2024

New modular factory-built methodologies implemented in the construction and industrial plant industries may bring down costs for modular reactors. A factory-built environment brings about benefits such as; improved equipment, tools, quality, shift patterns, training, continuous improvement learning, environmental control, standardisation, parallel working, the use of commercial off shelf equipment and much of the commissioning can be completed before leaving the factory. All these benefits combine to reduce build schedules, increase certainty, reduce risk and make financing easier and cheaper.Currently, the construction and industrial chemical plant industries have implemented successful modular design and construction techniques. Therefore, the objectives of this paper are to understand and analyse the state of the art research in these industries through a systematic literature review. The research can then be assessed and applied to modular reactors.The literature review highlighted analysis methods that may prove to be useful. These include; modularisation decision tools, stakeholder analysis, schedule, supply chain, logistics, module design tools and construction site planning. Applicable research was highlighted for further work exploration for designers to assess, develop and efficiently design their modular reactors.

• 공학교육연구
• /
• 제15권5호
• /
• pp.54-59
• /
• 2012

It is reported that the constructivistic learning method (CLM) enhances the understanding of the students in the learning process, especially in engineering classes. In CLM-based classes, the students can take the initiative in the learning process, which is called the student-centered model of the learning process. This is different from the traditional learning method based on the teacher-centered model, where a teacher plays the central role in the learning process of students. The authors have applied the method of CLM to one of the Engineering classes, namely production planning and inventory control (PPIC) class for undergraduate students. The PPIC class provides multimedia-based study materials and factory visits as well as regular lecture sections to cover the whole subject of inventory control theory and practice. In the review sessions, students are divided into several groups, and question-and-answer discussions were actively carried out among these groups under the support of the teacher as a facilitator. It was observed that the student engagement in the class was very active compared to the conventional lecture-based classes. As for further support of students understanding on the subject, simulation-based materials are also under study for the class. This paper presents the review of case study of CLM-based PPIC class and discusses the feasibility of simulation-based study materials for further improvement of the class.

• 한국방송∙미디어공학회:학술대회논문집
• /
• 한국방송∙미디어공학회 2022년도 추계학술대회
• /
• pp.1-3
• /
• 2022

최근 기존의 영상 압축 파이프라인 대신 신경망의 종단 간 학습을 통해 압축을 수행하는 알고리즘의 연구가 활발히 진행되고 있다. 본 논문은 종단 간 학습 기반 공간적 스케일러블 압축 기술을 제안한다. 보다 구체적으로 본 논문은 신경망의 각 계층에서 하위 계층의 학습된 특징 (feature)을 융합하여 상위 계층으로 전달하는 다중 스케일 특징 융합 (multi-scale feature fusion) 모듈을 도입해 상위 계층이 더욱 풍부한 특징 정보를 학습하고 계층 사이의 특징 중복성을 더욱 잘 제거할 수 있도록 한다. 기존 방법 대비 향상 계층(enhancement layer)에서 1.37%의 BD-rate가 향상된 결과를 볼 수 있다.

• 산업경영시스템학회지
• /
• 제46권4호
• /
• pp.181-189
• /
• 2023

In this paper, we present a case study of developing MVIS (Machine Vision Inspection System) designed for exterior quality inspection of stamping dies used in the production of automotive exterior components in a small to medium-sized factory. While the primary processes within the factory, including machining, transportation, and loading, have been automated using PLCs, CNC machines, and robots, the final quality inspection process still relies on manual labor. We implement the MVIS with general-purpose industrial cameras and Python-based open-source libraries and frameworks for rapid and low-cost development. The MVIS can play a major role on improving throughput and lead time of stamping dies. Furthermore, the processed inspection images can be leveraged for future process monitoring and improvement by applying deep learning techniques.