-
- [교수동정] ① 제조산업의 미래경영전략: 스마트팩토리의 수단은 지능화
- [아주경제 칼럼] ① 제조산업의 미래경영전략: 스마트팩토리의 수단은 지능화
-
- 작성일 2022-07-27
- 조회수 4869
-
- [연구] 석사과정 김영수, SCI 논문지(MDPI applied sciences/Q2) 게재
- 석사과정 김영수 학생(지도교수: 정종필)의 연구(ML-Based JIT1 Optimization for Throughput Maximization in Cluster Tool Automation)가 MDPI applied sciences(Impact Factor: 2.838 (2021); 5-Year Impact Factor: 2.921 (2021))에 게재됐다. https://www.mdpi.com/2076-3417/12/15/7519 / https://doi.org/10.3390/app12157519 논문요약 - The semiconductor etch cluster facility is the most used facility platform in the semiconductor manufacturing process. Optimizing cluster facilities can depend on production schedules and can have a direct impact on productivity. According to the diversity of semiconductor processes, the complexity of optimization is also increasing. Various optimization methods have been studied in many papers for optimizing such a complex cluster facility. However, there is a lack of discussion of how these methods can apply to practical semiconductor manufacturing fabs and the actual performance results. Even now, data analysis and optimal parameter derivation for maximizing the productivity of cluster manufacturing in semiconductor manufacturing fabs are continuing. In this study, we propose an automated method for data collection and analysis of the cluster, which used to be done manually. In addition, the derivation of optimization parameters and application to facilities are addressed. This automated method could improve the manual analysis methods, such as simulation through data analysis using machine learning algorithms. It could also solve the inefficiency caused by manual analysis performed within the network inside the semiconductor manufacturing fabs.
-
- 작성일 2022-07-27
- 조회수 5191
-
- [교수동정] 박정수 교수의 현미경 '스마트팩토리' -[141] 마켓 5.0 시대
- 박정수 교수의 현미경 '스마트팩토리' -[141] 마켓 5.0 시대
-
- 작성일 2022-07-25
- 조회수 4849
-
- [연구] 석사과정 최병근, SCI 논문지(MDPI Electronics/Q2) 게재
- 석사과정 최병근 학생(지도교수 : 정종필)의 연구(ViV-Ano: Anomaly Detection and Localization Combining Vision Transformer and Variational Autoencoder in the Manufacturing Process)가 MDPI Electronics(Impact Factor: 2.690 (2021); 5-Year Impact Factor: 2.657 (2021))에 게재됐다. https://www.mdpi.com/2079-9292/11/15/2306 / https://doi.org/10.3390/electronics11152306 논문요약 - The goal of image anomaly detection is to determine whether there is an abnormality in an image. Image anomaly detection is currently used in various fields such as medicine, intelligent information, military fields, and manufacturing. The encoder–decoder structure, which learns a normal-looking periodic normal pattern and shows good performance in judging anomaly scores through reconstruction errors showing the differences between the reconstructed images and the input image, is widely used in the field of anomaly detection. The existing image anomaly detection method extracts normal information through local features of the image, but the vision transformer base and the probability distribution are generated by learning the global relationship between image anomaly detection and an image patch that can locate anomalies to extract normal information. We propose Vision Transformer and VAE for Anomaly Detection (ViV-Ano), an anomaly detection model that combines a model variational autoencoder (VAE) with Vision Transformer (ViT). The proposed ViV-Ano model showed similar or better performance when compared to the existing model on a benchmark dataset. In addition, an MVTec anomaly detection dataset (MVTecAD), a dataset for industrial anomaly detection, showed similar or improved performance when compared to the existing model.
-
- 작성일 2022-07-24
- 조회수 5332
-
- 박정수 교수의 현미경 '스마트팩토리'-[139] 디지털 트윈의 미래
- 박정수 교수의 현미경 '스마트팩토리'-[139] 디지털 트윈의 미래
-
- 작성일 2022-07-11
- 조회수 4840
-
- 성남산업진흥원 BIO HEALTH 박정수 교수 칼럼 '바이오/디지털헬스산업 동향과 생태계 조성을 위한 방향'
-
- 작성일 2022-07-04
- 조회수 5152
-
- 박정수 교수의 현미경 '스마트팩토리'-[138] 스마트 팩토리의 패러독스
- 박정수 교수의 현미경 '스마트팩토리'-[138] 스마트 팩토리의 패러독스
-
- 작성일 2022-07-04
- 조회수 4937
-
- [연구] 석사과정 김병수, SCI 논문지(MDPI applied sciences/Q2) 게재
- 석사과정 김병수 학생(지도교수: 정종필)의 연구(Design and Implementation of Cloud Docker Application Architecture Based on Machine Learning in Container Management for Smart Manufacturing)가 MDPI applied sciences(Impact Factor: 2.838 (2021); 5-Year Impact Factor: 2.921 (2021))에 게재됐다. https://www.mdpi.com/2076-3417/12/13/6737 / https://doi.org/10.3390/app12136737 논문요약 - Manufacturers are expanding their business-process innovation and customized manufacturing to reduce their information technology costs and increase their operational efficiency. Large companies are building enterprise-wide hybrid cloud platforms to further accelerate their digital transformation. Many companies are also introducing container virtualization technology to maximize their cloud transition and cloud benefits. However, small- and mid-sized manufacturers are struggling with their digital transformation owing to technological barriers. Herein, for small- and medium-sized manufacturing enterprises transitioning onto the cloud, we introduce a Docker Container application architecture, a customized container-based defect inspection machine-learning model for the AWS cloud environment developed for use in small manufacturing plants. By linking with open-source software, the development was improved and a datadog-based container monitoring system, built to enable real-time anomaly detection, was implemented.
-
- 작성일 2022-07-03
- 조회수 5593