• The Journal of Korea Robotics Society
• /
• v.18 no.2
• /
• pp.225-232
• /
• 2023

With the recent increase of multiple robots cooperating in smart manufacturing logistics environments, it has become very important how to predict the safety and efficiency of the individual tasks and dynamically assign them to the best one of available robots. In this paper, we propose a novel task policy learner based on deep relational reinforcement learning for predicting the safety and efficiency of tasks in a multi-robot manufacturing logistics environment. To reduce learning complexity, the proposed system divides the entire safety/efficiency prediction process into two distinct steps: the policy parameter estimation and the rule-based policy inference. It also makes full use of domain-specific knowledge for policy rule learning. Through experiments conducted with virtual dynamic manufacturing logistics environments using NVIDIA's Isaac simulator, we show the effectiveness and superiority of the proposed system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.4
• /
• pp.157-163
• /
• 2022

Recently, with the development of automation in the industrial field, research on anomaly detection is being actively conducted. An application for anomaly detection used in factory automation is camera-based defect inspection. Vision camera inspection shows high performance and efficiency in factory automation, but it is difficult to overcome the instability of lighting and environmental conditions. Although camera inspection using deep learning can solve the problem of vision camera inspection with much higher performance, it is difficult to apply to actual industrial fields because it requires a huge amount of normal and abnormal data for learning. Therefore, in this study, we propose a network that overcomes the problem of collecting abnormal data with 72 geometric transformation deep learning methods using only normal data and adds an outlier exposure method for performance improvement. By applying and verifying this to the MVTec data set, which is a database for auto-mobile parts data and outlier detection, it is shown that it can be applied in actual industrial sites.

• IE interfaces
• /
• v.16 no.spc
• /
• 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.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.2
• /
• pp.73-85
• /
• 2020

While Korea became one of manufacturing powers in the world through a fast-follower strategy as well as implementing the approach of advancing manufacturing business focused on quantitative input, The advent of the fourth industrial revolution and demand becoming more complicated than ever both require a system that quickly detects the change of markets in advance and reflects it in the manufacturing strategy. Accordingly, the introduction of a smart factory is not optional but mandatory in order to strengthen the competitiveness of manufacturing business using ICT. This paper aims to investigate key factors having influence on the intention to continuously use a smart factory, the innovative IT device, on the basis of the technology acceptance model. This paper analyzed the influence of the leadership of CEO, organizational learning and perceived switching costs on the intention to continuously use a smart factory by the parameters of perceived ease of use and usefulness, the major belief valuables of the IT acceptance model.

• Journal of Korean Society for Quality Management
• /
• v.49 no.4
• /
• 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
• /
• v.8 no.2
• /
• 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.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• 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
• /
• v.56 no.1
• /
• 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.

• Journal of Engineering Education Research
• /
• v.15 no.5
• /
• 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.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2022.11a
• /
• 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.