-
- 박정수 교수의 현미경 '스마트팩토리'-[137] 가트너가 주목한 '하이퍼 오토메이션'
- 박정수 교수의 현미경 '스마트팩토리'-[137] 가트너가 주목한 '하이퍼 오토메이션'
-
- 작성일 2022-06-27
- 조회수 5048
-
- [연구] 석사과정 양민열, SCI 논문지(MDPI applied sciences/Q2) 게재
- 석사과정 양민열 학생(지도교수: 정종필)의 연구(Design and Implementation of an Explainable Bidirectional LSTM Model Based on Transition System Approach for Cooperative AI-Workers)가 MDPI applied sciences(Impact Factor: 2.679 (2020); 5-Year Impact Factor: 2.736 (2020))에 게재됐다. https://doi.org/10.3390/app12136390 / https://www.mdpi.com/2076-3417/12/13/6390 논문요약 - Recently, interest in the Cyber-Physical System (CPS) has been increasing in the manufacturing industry environment. Various manufacturing intelligence studies are being conducted to enable faster decision-making through various reliable indicators collected from the manufacturing process. Artificial intelligence (AI) and Machine Learning (ML) have advanced enough to give various possibilities of predicting manufacturing time, which can help implement CPS in manufacturing environments, but it is difficult to secure reliability because it is difficult to understand how AI works, and although it can offer good results, it is often not applied to industries. In this paper, Bidirectional Long Short Term Memory (BI-LSTM) is used to predict process execution time, which is an indicator that can be used as a basis for CPS in the manufacturing process, and the Shapley Additive Explanations (SHAP) algorithm is used to explain how artificial intelligence works. The experimental results of this paper, applying manufacturing data, prove that the results derived from SHAP are effective for workers and AI to collaborate.
-
- 작성일 2022-06-23
- 조회수 5518
-
- 박정수 교수의 현미경 '스마트팩토리'-[136] 바이오산업과 스마트팩토리
- 박정수 교수의 현미경 '스마트팩토리'-[136] 바이오산업과 스마트팩토리
-
- 작성일 2022-06-20
- 조회수 4988
-
- 박정수 교수의 현미경 '스마트팩토리'-[135] 고객경험의 피지털(physital)
- 박정수 교수의 현미경 '스마트팩토리'-[135] 고객경험의 피지털(physital)
-
- 작성일 2022-06-13
- 조회수 4986
-
- [연구] 석사과정(졸업생) 김동현, SCI 논문지(MDPI applied sciences/Q2) 게재
- 석사과정(졸업생) 김동현 학생(지도교수 : 정종필)의 연구(SSA-CAE-Based Abnormal Data Classification Method in Edge Intelligence Device of CNC Machine)가 MDPI applied sciences(Impact Factor: 2.679 (2020); 5-Year Impact Factor: 2.736 (2020))에 게재됐다. https://doi.org/10.3390/app12125864 / https://www.mdpi.com/2076-3417/12/12/5864 논문요약 - Smart factories and big data are important factors in the Fourth Industrial Revolution. Smart factories aim for automation and integration; however, the most important part is the application of data. Despite extensive research on the maintenance and quality management of big data-based production equipment, industrial data gathered for analysis contain more normal data than abnormal data. In addition, a significant amount of energy is expended in the data pre-processing process to analyze the acquired data. Therefore, to maintain production equipment and quality management, data classification technology that allows easy data analysis by classifying abnormal data into normal data is required. In this paper, we propose an abnormal data classification architecture for cycle data sets gathered from production facilities through SSA-CAE along with data storage methods for each product unit. SSA-CAE is a hybrid technique that combines singular spectrum analysis (SSA) techniques that are effective in reducing noise in time series data with convolutional auto encoder (CAE) that have performed well in time series.
-
- 작성일 2022-06-09
- 조회수 5487
-
- 박정수 교수의 현미경 '스마트팩토리'-[134] 디지털이 바이오산업에 미치는 영향
- 박정수 교수의 현미경 '스마트팩토리'-[134] 디지털이 바이오산업에 미치는 영향
-
- 작성일 2022-06-07
- 조회수 5091
-
- KIAT 기술사업화 매거진 박정수 교수 스페셜 칼럼 '미래 먹거리, 국내 바이오산업 육성을 위한 전략'
- 기사 전문은 첨부파일을 이용하여 주시기 바랍니다. 감사합니다.
-
- 작성일 2022-05-26
- 조회수 5448
-
- 박정수 교수의 현미경 '스마트팩토리'-[132] 세상을 바꾸는 전략적 장소
- 박정수 교수의 현미경 '스마트팩토리'-[132] 세상을 바꾸는 전략적 장소
-
- 작성일 2022-05-21
- 조회수 5172
-
- [연구] 석사과정 박민우, SSCI/SCIE 논문지(MDPI Sustainability/Q2) 게재
- 석사과정 박민우 학생(지도교수 : 정종필)의 연구(Design and Implementation of Machine Vision-Based Quality Inspection System in Mask Manufacturing Process)가 MDPI Sustainability(Impact Factor: 3.251 (2020); 5-Year Impact Factor: 3.473 (2020))에 게재됐다. https://www.mdpi.com/2071-1050/14/10/6009 / https://doi.org/10.3390/su14106009 논문요약 - With the advent of the 4th Industrial Revolution, research on anomaly detection in the manufacturing process using deep learning and machine vision is being actively conducted. There have been various attempts to innovate the manufacturing site by adopting advance information technologies such as machine vision, machine learning, and deep learning in many manufacturing processes. However, there have been no cases of designing and implementing these technologies at the mask manufacturing site, which is essential to tackle COVID-19 pandemic. The originality of this paper is to implement sustainability in the mask manufacturing environment and industrial eco-system by introducing the latest computer technology into the manufacturing process essential for pandemic-related disasters. In this study, the intention is to establish a machine vision-based quality inspection system in actual manufacturing process to improve sustainable productivity in the mask manufacturing process and try a new technical application that can contribute to the overall manufacturing process industry in Korea in the future. Therefore, the purpose of this paper is to specifically present hardware and software system construction and implementation procedures for inspection process automation, control automation, POP (Point Of Production) manufacturing monitoring system construction, smart factory implementation, and solutions. This paper is an application study applied to an actual mask manufacturing plant, and is a qualitative analysis study focused on improving mask productivity. “Company A” is a mask manufacturing company that produces tons of masks everyday located in Korea. This company planned to automate the identification of good and defective products in the mask manufacturing process by utilizing machine vision technology. To this end, a deep learning and machine vision-based anomaly detection manufacturing environment is implemented using the LAON PEOPLE NAVI AI Toolkit. As a result, the productivity of “Company A”’s mask defect detection process can be dramatically improved, and this technology is expected to be applied to similar mask manufacturing processes in the future to make similar manufacturing sites more sustainable.
-
- 작성일 2022-05-16
- 조회수 6059