Um Jumyoung
Kyung Hee University · 工学
研究室紹介
Professor Um Jumyoung's research lab specializes in digital transformation and intelligent manufacturing systems, focusing on the integration of advanced technologies such as augmented reality (AR), cyber-physical systems, and standardized data models (e.g., STEP-NC) to enhance industrial efficiency and decision-making. The lab explores practical applications of AR in warehousing, construction site management, and flexible manufacturing, with an emphasis on low-cost, accessible solutions for small and medium enterprises. Research also extends to energy-efficient manufacturing processes, particularly in automotive production, where AR and simulation tools support sustainable and data-driven engineering decisions.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15In today’s business environment, the efficiency of warehouses can be critical for the efficiency of the overall supply chains they belong to. As a result, new technologies are being tested and adopted in industry to improve the performance of warehouse operations. An example technology that has recently gained interest by both academia and industry is augmented reality. In this paper, we investigate the opportunities arising from the usage of augmented reality in warehouses as well as the barrie
The Digital Age is becoming the de-facto of future direction in manufacturing domain. Its main driver is the pressure of shorter product life cycles and leads companies to faster engineering time of their production lines. To cope with the need, recent literature has successfully shown modular production and assembly line concepts by using standardized interfaces on electromechanical and communication level. This change entails new challenges. Given the fact that production life cycle decreases,
Informed decision-making is crucial for construction site operators. Cyber-physical systems, including various technologies such as augmented reality and building automation tools, are gathering popularity within the infrastructure management sector. However, they are expensive and inaccessible to adopt for most small organizations. This paper describes a prototype of low-cost mobile augmented reality service for BIM and demonstrated its usability for pipe maintenance by supporting inspection, w
The trend of mass customization requires highly flexible production systems, which pose a new challenge for workers. Numerous concepts using augmented reality technologies have been developed to offer support in manual assembly processes. Newer AR devices are equipped with more and more functions, such as microphones, speakers or multiple camera systems, which can be used to help workers. However, wearable devices offer only limited computational power and limited flexibility of their interface
The machine tool data model of STEP-NC (ISO 14649) was conceived as a necessary extension to the original STEP-NC set of standards to make efficient control possible. The intention of this paper is to describe the background to the data model as well as related research work building on a higher level of information than can currently be found in the control information. The development of STEP-NC controllers promises improved manufacturing and resource use. However, even with legacy controllers
The issues in the energy-efficiency process have much interest in the automotive industry. The energy criteria are also important in machine selection as well as productivity when new equipment is introduced on a shop floor. Remote laser welding having benefits for productivity and for energy saving is receiving attention in automotive assembly lines, but introducing this innovative equipment is a significant decision because of high initial cost in spite of the advantages. This paper specifical
Manufacturing systems need to be resilient and self-organizing to adapt to unexpected disruptions, such as product changes or rapid order, in supply chain changes while increasing the automation level of robotized logistics processes to cope with the lack of human experts. Deep Reinforcement Learning is a potential solution to solve more complex problems by introducing artificial neural networks in Reinforcement Learning. In this paper, a game engine was used for Deep Reinforcement Learning trai
Cloud computing sets to make a change in business between enterprises over the internet based on services providing dynamically reconfigurable and virtualized networks. It is difficult for an aircraft manufacturer to consider the performance and status of each factory (i.e., capacity, inventory, order, technology, etc.) because of the huge amount of suppliers. In legacy environments, the supplier consumed a long time to identify the machine and process required and the energy to be consumed in o
Recent market trends require extremely short product life cycles to cope with individual customer requirements. The key technology to deal with these requirements is plug-and-produce, which reduces engineering time to change the production lines rapidly. This challenge is solved by the concept of a modular factory which allows to reconfigure individual machine stations without the need of extensive engineering effort. Current solutions focus on hardware approaches such as modular frames, cables
As the global emphasis on sustainable resource management intensifies, the need for efficient recycling automation becomes critical. This paper addresses the integration of blockchain technology and federated learning to enhance the automation and efficiency of recycling processes. The authors propose a novel digital product passport system that utilizes blockchain for secure data sharing and federated learning for continuous improvement of recycling automation models. Manufacturers develop base