Hyeonbok Cho
Pohang University of Science and Technology · 工学
研究室紹介
Professor Hyeonbok Cho's research lab specializes in intelligent manufacturing systems, with a focus on enhancing shop-floor control, supply chain integration, and decision-making through advanced information modeling and semantic technologies. The lab develops innovative solutions for real-time data management, supplier discovery, and nonconformance prediction using ontologies and machine learning. Key research directions include semantic interoperability in manufacturing, agile smart manufacturing systems, and the integration of hierarchical control architectures for make-to-order environments. The lab emphasizes the use of standardized modeling techniques and semantic web technologies to improve system agility and operational performance.
Research Overview
Research Output Trend
Figures are computed from collected data and may differ slightly.
Selected Papers
15The information architecture for a shop floor controller provides the accurate and relevant data in an appropriate format. The information architecture is built by specifying the information requirements and by defining the information handling mechanism. The objective of the paper is to capture and specify the information requirements of workstation and machine controllers for hierarchical shop floor control in a discrete part manufacturing system. The information contents managed by the workst
Smart Manufacturing Systems (SMS) need to be agile to adapt to new situations by using detailed, precise, and appropriate data for intelligent decision-making. The intricacy of the relationship of strategic goals to operational performance across the many levels of a manufacturing system inhibits the realization of SMS. This paper proposes a method for identifying what aspects of a manufacturing system should be addressed to respond to changing strategic goals. The method uses standard modeling
Nonconformities are the major sources of waste in manufacturing process. Nonconformities cannot be fully eliminated but their occurrence rate can be predicted. This paper proposes a hybrid approach based on ontological modelling and machine learning for predicting the non-conformance rates of a manufacturing process and minimising its associated costs. Based on the proposed approach, the work orders, that are represented semantically using a formal ontology, are first clustered according to thei
As companies move forward to source globally, supply chain management has gained attention more than ever before. In particular, the discovery and selection of capable suppliers has become a prerequisite for a global supply chain operation. Manufacturing e-marketplaces have helped companies quickly and effectively discover new suppliers and/or buyers for their products and services. However, as the requirements and capabilities in isolation, their true meanings may not be uniformly interpreted b
In today's increasingly competitive global market, most enterprises place great stress on reducing order fulfillment costs, minimizing time-to-market and maximizing product quality. The desire of businesses to achieve these goals has seen a shift from a make-to-stock paradigm to a make-to-order paradigm. The success of the make-to-order paradigm requires robust and efficient supply chain integration and implementation in the business-to-business (B2B) environment. Recent Internet-based
This paper presents an experimental design developed to determine a combination of robust planning and scheduling rules for an intelligent workstation controller (MTC). The IWC is used as part of the control system for an automated flexible manufacturing system. A three-level hierarchical control structure (shop, workstation and equipment) is adopted in order effectively to control a shop-floor. At the top level is a shop controller which receives orders and their associated manufacturing inform
Data-driven fault diagnosis has received significant attention in the era of big data. Most data-driven methods have been developed under the assumption that both training and test data come from identical data distributions. However, in real-world industrial scenarios, data distribution often changes due to varying operating conditions, leading to a degradation of diagnostic performance. Although several domain adaptation methods have shown their feasibility, existing methods have overlooked me