-
- [일반] SKKU AI Colloquium 2022
- 안녕하세요. 이번 9월 22일 (목), 23일 (금) 양일에 자과캠 학술정보관 오디토리움에서 SKKU AI Colloquium을 아래와 같이 개최합니다. 네이버 AI랩과 카카오 브레인 초청강연과 최근 1년 동안 인공지능 관련된 주요 학술대회에 발표/발표예정인 논문 24편을 교수님 3분, 대학원생 21명이 직접 발표 예정입니다. 아래 링크를 통한 사전 등록자에게는 점심제공 및 추첨을 통한 경품 증정 예정이오니, 많은 참여를 부탁드립니다. (사전등록 기한 : 9/20(화) 16:00까지, 무료등록)https://sites.google.com/view/skkuai2022
-
- 작성일 2022-09-23
- 조회수 5351
-
- [교수동정] 박정수 교수의 현미경 '스마트팩토리' -[145]왜 디지털 전환은 필수적인가
- 박정수 교수의 현미경 '스마트팩토리' -[145]왜 디지털 전환은 필수적인가
-
- 작성일 2022-08-22
- 조회수 4683
-
- [교수동정] 박정수 교수의 현미경 '스마트팩토리' -[144]디지털 전략이 중요한 까닭
- 박정수 교수의 현미경 '스마트팩토리' -[144]디지털 전략이 중요한 까닭
-
- 작성일 2022-08-16
- 조회수 4790
-
- [연구] 석사과정 도상훈, SSCI/SCIE 논문지(MDPI Sustainability/Q2) 게재
- 석사과정 도상훈 학생(지도교수 : 정종필)의 연구(SaaMES: SaaS-Based MSA/MTA Model for Real-Time Control of IoT Edge Devices in Digital Manufacturing)가 MDPI Sustainability(Impact Factor: 3.889 (2021); 5-Year Impact Factor: 4.089 (2021))에 게재됐다. https://www.mdpi.com/2071-1050/14/16/9864 / https://doi.org/10.3390/su14169864 논문요약 - As a software delivery model, Software as a Service (SaaS) has attracted considerable attention from software providers and users. Most traditional companies are shifting their businesses to an SaaS model. SaaS development is a very complicated process and its success depends on architectural design and development. A Manufacturing Execution System (MES) was used at the expense of licensing fees for features not used in the On-Premise environment, although the features used vary depending on the manufacturing environment. In an SaaS environment, MES is applied with a function-specific container approach through a Microservice Architecture (MSA) to select and employ only the necessary functions. Furthermore, as the number of customers of virtualized applications increases in SaaS-based services, complexity and operating costs increase; thus, Multi-tenancy Architecture (MTA) technology, which serves all customers through a single instance of the application is crucial. Thus, in this study, we investigate the MTA approach and propose a suitable MTA for the manufacturing execution system. Real-time response is crucial to achieving a cyber-physical system of digital manufacturing in SaaS-based MES. Furthermore, SaaS-based big data analytics and decision-making cannot meet the needs of numerous applications in real-time sensitive workplaces. In this study, we propose an SaaS-based MSA/MTA model for real-time control of Internet of Things (IoT) Edge in digital manufacturing (SaaMES), an architecture of SaaS-based MES with MSA and MTA to meet vulnerable workplaces and real-time responses in Cloud environments. The analysis is used by applying the Autoencoder and Generic Adversarial Networks analysis model to IoT Edge for the connection between the Cloud environment and work site to enable real-time response and decision-making through communication using OPC-UA and small-scale analysis.
-
- 작성일 2022-08-10
- 조회수 5977
-
- [교수동정] 박정수 교수의 현미경 '스마트팩토리' -[142]스마트 팩토리의 궁극적 목적
- 박정수 교수의 현미경 '스마트팩토리' -[142]스마트 팩토리의 궁극적 목적
-
- 작성일 2022-08-02
- 조회수 4798
-
- [연구] 석사과정 김진엽, SCI 논문지(MDPI applied sciences/Q2) 게재
- 석사과정 김진엽 학생(지도교수: 정종필)의 연구(Design and Implementation of an HCPS-Based PCB Smart Factory System for Next-Generation Intelligent Manufacturing)가 MDPI applied sciences(Impact Factor: 2.838 (2021); 5-Year Impact Factor: 2.921 (2021))에 게재됐다. https://www.mdpi.com/2076-3417/12/15/7645 / https://doi.org/10.3390/app12157645 논문요약 - The next-generation intelligent smart factory system that is proposed in this paper could improve product quality and realize flexible, efficient, and sustainable product manufacturing by comprehensively improving production and management innovation via its digital network and intelligent methods that reflect the characteristics of its printed circuit board (PCB) manufacturing design and on-site implementation. Intelligent manufacturing systems are complex systems that are composed of humans, cyber systems, and physical systems and aim to achieve specific manufacturing goals at an optimized level. Advanced manufacturing technology and next-generation artificial intelligence (AI) are deeply integrated into next-generation intelligent manufacturing (NGIM). Currently, the majority of PCB manufacturers are firms that specialize in processing orders from leading semiconductor and related product manufacturers, such as Samsung Electronics, TSMC, Samsung Electro-Mechanics, and LG Electronics. These top companies have been responsible for all product innovation, intelligent services, and system integration, with PCB manufacturers primarily playing a role in intelligent production and system integration. In this study, the main implementation areas were divided into manufacturing execution system (MES) implementation (which could operate the system using system integration), data gathering, the Industrial Internet of Things (IIoT) for production line connection, AI and real-time monitoring, and system implementation that could visualize the collected data. Finally, the prospects of the design and on-site implementation of the next-generation intelligent smart factory system that detects and controls the occurrence of quality and facility abnormalities are presented, based on the implementation system.
-
- 작성일 2022-07-29
- 조회수 5491
-
- [연구] 석사과정 구병진, SCI 논문지(MDPI Electronics/Q2) 게재
- 석사과정 구병진 학생(지도교수 : 정종필)의 연구(Real-Time ISR-YOLOv4 Based Small Object Detection for Safe Shop Floor in Smart Factories)가 MDPI Electronics(Impact Factor: 2.690 (2021); 5-Year Impact Factor: 2.657 (2021))에 게재됐다. https://www.mdpi.com/2079-9292/11/15/2348 / https://doi.org/10.3390/electronics11152348 논문요약 - Wearing a hard hat can effectively improve the safety of workers on a construction site. However, workers often take off their helmets because they have a weak sense of safety and are uncomfortable, and this action poses a large danger. Workers not wearing hard hats are more likely to be injured in accidents such as human falls and vertical falls. Therefore, the detection of wearing a helmet is an important step in the safety management of a construction site, and it is urgent to detect helmets quickly and accurately. However, the existing manual monitor is labor intensive, and it is difficult to popularize the method of mounting the sensor on the helmet. Thus, in this paper, we propose an AI method to detect the wearing of a helmet with satisfactory accuracy with a high detection rate. Our method selects based on YOLO v4 and adds an image super resolution (ISR) module at the end of the input. Afterward, the image resolution is increased, and the noise in the image is removed. Then, dense blocks are used to replace residual blocks in the backbone network using the CSPDarknet53 framework to reduce unnecessary computation and reduce the number of network structure parameters. The neck then uses a combination of SPPnet and PANnet to take full advantage of the small target’s capabilities in the image. We add foreground and background balance loss functions to the YOLOv4 loss function part to solve the image background and foreground imbalance problem. Experiments performed using self-constructed datasets show that the proposed method has more efficacy than the currently available small target detection methods. Finally, our model achieves an average precision of 93.3%, a 7.8% increase over the original algorithm, and it takes only 3.0 ms to detect an image at 416 × 416.
-
- 작성일 2022-07-28
- 조회수 5589
-
- [연구] 박사과정 김지형, SCI 논문지(MDPI applied sciences/Q2) 게재
- 박사과정 김지형 학생(지도교수: 정종필)의 연구(Design and Implementation of OPC UA-Based VR/AR Collaboration Model Using CPS Server for VR Engineering Process)가 MDPI applied sciences(Impact Factor: 2.838 (2021); 5-Year Impact Factor: 2.921 (2021))에 게재됐다. https://www.mdpi.com/2076-3417/12/15/7534 / https://doi.org/10.3390/app12157534 논문요약 - In order to cope with the changing era of the innovative management paradigm of the manufacturing industry, it is necessary to advance the construction of smart factories in the domestic manufacturing industry, and in particular, the 3D design and manufacturing content sector is highly growthable. In particular, the core technologies that enable digital transformation VR (Virtual Reality)/AR (Augmented Reality) technologies have developed rapidly in recent years, but have not yet achieved any particular results in industrial engineering. In the manufacturing industry, digital threads and collaboration systems are needed to reduce design costs that change over and over again due to the inability to respond to various problems and demands that should be considered when designing products. To this end, we propose a VR/AR collaboration model that increases efficiency of manufacturing environments such as inspection and maintenance as well as design simultaneously with participants through 3D rendering virtualization of facilities or robot 3D designs in VR/AR. We implemented converting programs and middleware CPS (Cyber Physical System) servers that convert to BOM (Bill of Material)-based 3D graphics models and CPS models to test the accuracy of data and optimization of 3D modeling and study their performance through robotic arms in real factories.
-
- 작성일 2022-07-27
- 조회수 5590
-
- [연구] 석사과정 박찬호, SCI 논문지(MDPI applied sciences/Q2) 게재
- 석사과정 박찬호 학생(지도교수: 정종필)의 연구(Fv-AD: F-AnoGAN Based Anomaly Detection in Chromate Process 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/2076-3417/12/15/7549 / https://doi.org/10.3390/app12157549 논문요약 - Anomaly detection for quality prediction has recently become important, as data collection has increased in various fields, such as smart factories and healthcare systems. Various attempts have been made in the existing manufacturing process to improve discrimination accuracy due to data imbalance in the anomaly detection model. Predicting the quality of a chromate process has a significant influence on the completeness of the process, and anomaly detection is important. Furthermore, obtaining image data, such as monitoring during the manufacturing process, is difficult, and prediction is challenging owing to data imbalance. Accordingly, the model employs an unsupervised learning-based Generative Adversarial Networks (GAN) model, performs learning with only normal data images, and augments the Fast Unsupervised Anomaly Detection with GAN (F-AnoGAN) base with a visualization component to provide a more intuitive judgment of defects with chromate process data. In addition, anomaly scores are calculated based on mapping in the latent space, and new data are applied to confirm anomaly detection and the corresponding location values. As a result, this paper presents a GAN architecture to detect anomalies through chromate facility data in a smart manufacturing environment. It proved meaningful performance and added visualization parts to provide explainable interpretation. Data experiments on the chromate process show that the loss value, anomaly score, and anomaly position are accurately distinguished from abnormal images.
-
- 작성일 2022-07-27
- 조회수 5409