• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.2
• /
• pp.199-206
• /
• 2022

A malfunction or breakdown of a manufacturing facility leads to product defects and the suspension of production lines, resulting in huge financial losses for manufacturers. Due to the spread of smart factory services, a large amount of data is being collected in factories, and AI-based research is being conducted to predict and diagnose manufacturing facility breakdowns or manufacturing site efficiency. However, because of the characteristics of manufacturing data, such as a severe class imbalance about abnormalities and ambiguous label information that distinguishes abnormalities, developing classification or anomaly detection models is highly difficult. In this paper, we present an deep learning algorithm for anomaly detection of a manufacturing facility using reconstruction loss of CNN-based model and ananlyze its performance. The algorithm detects anomalies by relying solely on normal data from the facility's manufacturing data in the exclusion of abnormal data.

• Journal of Korean Society for Quality Management
• /
• v.30 no.2
• /
• pp.72-85
• /
• 2002

Advances in computer and sensor technology have made it possible to obtain superlarge manufacturing process data in real time, letting us extract meaningful information from these superlarge data sets. We propose a systematic data analysis procedure which field engineers can apply easily to manufacture quality products. The procedure consists of data cleaning and data analysis stages. Data cleaning stage is to construct a database suitable for statistical analysis from the original superlarge manufacturing process data. In the data analysis stage, we suggest a graphical easy-to-implement approach to extract practical information from the cleaned database. This study will help manufacturing companies to achieve six sigma quality.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.17 no.2
• /
• pp.25-33
• /
• 1992

Manufacturing cell formation is one of the most important problems faced in designing cellular manufacturing systems. The purpose of this study is to design effective manufacturing cell systems by developing a method which forms machines/parts into optimal machine cells/part families. The 0-1 data matrix structure is used to form a basis for manufacturing cell formation. In this paper, we propose a CE method to reorder the 0-1 data matrix for manufacturing cell formation. The resulting solutions are shown to demonstrate the effectiveness of the CE method.

• Proceedings of the KSME Conference
• /
• 2001.06a
• /
• pp.740-745
• /
• 2001

The plastic deformation behavior of formed CICC fur the superconducting Tokamac fusion device was examined and appropriate manufacturing information was provided. A relation between travel of the bending roller and spring back displacement was obtained via virtual manufacturing. The radius of CICC after forming was expressed as a function of the bend-roll travel. The maximum von Mises stress after spring back was also monitored fur the SAGBO prediction. Next, the variation of the CICC cross-sectional area was examined during the first turn and during conduit bending with the largest curvature. Finally, the coil radius was measured and compared with the data generated from the virtual manufacturing. The measured data showed similar pattern as predicted one. Using the mapping function found to match with the real data, the data from the virtual manufacturing may facilitate accurate manufacturing.

• Journal of Digital Convergence
• /
• v.12 no.1
• /
• pp.305-311
• /
• 2014

The manufacturing industry early have been introducing automation and information systems of the engineering and production process for getting competitive advantage. one of the typical information systems is MES(Manufacturing Execution System) and it keeps evolving. As Big Data showed up nowadays, application method of Big Data to MES is also being sought. First, this study will do preceding research and cases study on the application of Big Data in the manufacturing industry. Then, it will suggest application Plan of Big Data to MES.

• Biomaterials and Biomechanics in Bioengineering
• /
• v.3 no.1
• /
• pp.1-14
• /
• 2016

Well-ordered porous materials are very promising in orthopedics since they allow tailoring the mechanical properties. Finite element (FE) analysis is commonly used to evaluate the mechanical behavior of well-ordered porous materials. However, FE results generally differ importantly from experimental data. In the present article, three types of manufacturing irregularities were characterized on an additive manufactured porous titanium sample having a simple cubic unit-cell: strut diameter variation, strut inclination and fractured struts. These were included in a beam FE model. Results were compared with experimental data in terms of the apparent elastic modulus (Eap) and apparent yield strength (SY,ap). The combination of manufacturing irregularities that yielded the closest results to experimental data was determined. The idealized FE model resulted in an Eap one order of magnitude larger than experimental data and a SY,ap almost twice the experimental values. The strut inclination and fractured struts showed the strongest effects on Eap and SY,ap, respectively. Combining the three manufacturing irregularities produced the closest results to experimental data. The model also performed well when applied to samples having different structural dimensions. We recommend including the three proposed manufacturing irregularities in the FE models to predict the mechanical behavior of such porous structures.

• Korean Journal of Computational Design and Engineering
• /
• v.21 no.3
• /
• pp.215-223
• /
• 2016

The low price around 1000 USD makes consumer 3D printers as a new additive manufacturing platform for the personal manufacturing where consumers can make and sell their own products. To allow the consumers to design and manufacture their products, not only economic 3D printers but also supporting information systems for their design and manufacturing are essential. This study suggests an extended product data management (PDM) system that can support both the design and manufacturing of personal products with consumer 3D printing services. This extended PDM system helps consumer designers use advanced PDM technologies for their design and connected 3D printing services with Internet of Things (IoT) technology for realization of their products. As a result, the proposed system supports the consumer designers a seamless integrated product development and manufacturing environment supported by PDM and consumer 3D printing services.

• International Journal of Reliability and Applications
• /
• v.3 no.4
• /
• pp.155-164
• /
• 2002

This paper focuses on how modem data mining can be integrated with real-time relational databases and commercial data warehouses to improve reliability in real-time. An important Issue for many manufacturers is the development of relational databases that link key product attributes with real-time process parameters. Helpful data for key product attributes in manufacturing may be derived from destructive reliability testing. Destructive samples are taken at periodic time intervals during manufacturing, which might create a long time-gap between key product attributes and real-time process data. A case study is briefly summarized for the medium density fiberboard (MDF) industry. MDF is a wood composite that is used extensively by the home building and furniture manufacturing industries around the world. The cost of unacceptable MDF was as large as 5% to 10% of total manufacturing costs. Prevention can result In millions of US dollars saved by using better Information systems.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2001.10a
• /
• pp.411-415
• /
• 2001

Advances in computer and sensor technology have made it possible to obtain superlarge manufacturing process data in real time, letting us to extract meaningful information from these superlarge data sets. We propose a systematic data analysis procedure which field engineers can apply easily to manufacture quality products. The procedure consists of data cleaning and data analysis stages. Data cleaning stage is to construct a database suitable for statistical analysis from the original superlarge manufacturing process data. In the data analysis stage, we suggest a graphical easy-to-implement approach to extract practical information from the cleaned database. This study will help manufacturing companies to achieve six sigma quality.

• Journal of the Korean Data and Information Science Society
• /
• v.26 no.5
• /
• pp.1117-1128
• /
• 2015

In order to secure an important competitive advantage in manufacturing business, an automation and information system from manufacturing process has been introduced; however, small and medium enterprises have not met the power of information in the manufacturing fields. They have been managing the manufacturing process that is depending on the operator's experience and data written by hand, which has limits to reveal cause of defective goods clearly, in the case of happening of low-grade goods. In this study, we analyze critical factors which affect the quality of some manufacturing process in terms of 4M. We also studied the automobile parts processing of the small and medium manufacturing enterprises controlled with data written by hand so as to collect the data written by hand and to utilize sensor data in the future. Analysis results show that there is no deference in defective quantity in machines, while raw materials, production quality and task tracking have significant deference.