• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.85-88
• /
• 2021

There are many irregularly-sampled time series in the manufacturing data which are collected from manufacturing facilities by short intervals. Those time series often have large variance. In this paper, we propose irregularly-sampled time series correction method based on simple moving average. This method corrects time intervals between neighboring values in time series regularly and reduces the variance of the values at the same time. We examine that this method improves performance of anomaly detection in manufacturing facility.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.11
• /
• pp.2037-2042
• /
• 2017

The manufacturing facility is generally operated by a pre-set program under the existing factory automation system. On the other hand, the manufacturing facility must decide how to operate autonomously in Industry 4.0. Determining the operation mode of the production facility itself means, for example, that it detects the abnormality such as the deterioration of the facility at the shop-floor, prediction of the occurrence of the problem, detection of the defect of the product, In this paper, we propose a manufacturing process modeling using a queue for detection of manufacturing process abnormalities at the shop-floor, and detect abnormalities in the modeling using SVM, one of the machine learning techniques. The queue was used for M / D / 1 and the conveyor belt manufacturing system was modeled based on ${\mu}$, ${\lambda}$, and ${\rho}$. SVM was used to detect anomalous signs through changes in ${\rho}$.

• The Journal of Society for e-Business Studies
• /
• v.23 no.2
• /
• pp.97-110
• /
• 2018

With the advent of the 4-th industrial revolution, manufacturing companies have increasing interests in the realization of smart manufacturing by utilizing their accumulated facilities data. However, most previous research dealt with the structured data such as sensor signals, and only a little focused on the unstructured data such as text, which actually comprises a large portion of the accumulated data. Therefore, we propose an association rule mining based facility error pattern extraction framework, where text data written by operators are analyzed. Specifically, phrases were extracted and utilized as a unit for text data analysis since a word, which normally used as a unit for text data analysis, is unable to deliver the technical meanings of facility errors. Performances of the proposed framework were evaluated by addressing a real-world case, and it is expected that the productivity of manufacturing companies will be enhanced by adopting the proposed framework.

• Proceedings of the Safety Management and Science Conference
• /
• 2002.11a
• /
• pp.233-238
• /
• 2002

The product process is sequence of all the required activities that a company must perform to develop, and manufacture a product. These activities include marketing, research, engineering design, quality assurance, manufacturing, and a whole chain of suppliers and vendors. The process also comprises all strategic planning, capital investments, management decisions, and tasks necessary to create a new product. manufacturing processes must be created so that the product can be produced in the product facility Purchasing new equipment and training workers may be required if new technology is to be used. Tools, fixtures, and the sequence of steps in the manufacturing processes must all be developed to allow rapid, high-quality, cost effective production. Also, it may be needed to be rearrange the production facility to adapt to the new manufacturing processes. Therefore, this study tries to proposed that Scheduling by customer needs group for minimizing the problem and reducing inventory, product development time, cycle time, and order lead time.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.20 no.2
• /
• pp.227-234
• /
• 2020

This paper introduces the state definition and diagnostic algorithm for autonomic control of manufacturing facilities. Smart factory systems through cyber-physical systems and digital twin technology are increasing the productivity and stability of existing manufacturing plants, which has become an issue recently. A Smart factory system is one of the key technologies that make up a smart factory system, to improve productivity, enable workers to make better decisions, and to control abnormal process flows. However, performing an autonomic control process based on large number of integrated plat data requires significant advance work. Therefore, in this paper, we define an abstracted facility state for manufacturing facility autonomic control and propose an algorithm to diagnose the current state. This makes the autonomic control process simpler by autonomic control based on the facility status rather then integrated facility data.

• International Journal of Highway Engineering
• /
• v.12 no.2
• /
• pp.129-136
• /
• 2010

The present annexed parking lot standards for buildings in Parking Act are categorized in 9 groups in terms of recreation, culture and assembly, housing, factory, and so on, in which same grouped facilities have uniform parking standards. The local governments have authority to itemize groups and adjust parking standards within ${\pm}50%$ ranges. These days diversity in building types and functions need more fractionated parking standards; however, most local governments focusing merely on applying strengthened parking standards in general without systematic rules of consistency. The current problem of parking standards being used is lack of regarding facility characteristics; expecially, a large sized high-tech manufacturing facility located in industrial site is still applied by same parking standards as normal manufacturing facility, even though most part of manufacturing process is automated and hence less manpower is employed. This paper presents a systematic method of analyzing parking generation unit for factory facilities in industrial site in terms of facility use and scale characteristics.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2004.04a
• /
• pp.484-489
• /
• 2004

The purpose of this study is to examine the success factor of Quality Management (QM) in the manufacturing conditions aspect of medium and small-sized sanitary enterprise. The requisite for manufacturing factors are classified into manufacturing human factors (the number of production employee, training and teaching, discuss on quality, manufacture expertness, etc.), manufacturing facility factors (coating, hardening, and molding equipment), manufacturing core component factors (temperature and viscosity, line, surface). And the indicator of quality outcomes are measured by reorder and recommendation to others.

• The Journal of Korean Medicine
• /
• v.38 no.1
• /
• pp.81-92
• /
• 2017

Objectives: Herbal dispensaries can be installed separately from medical institutions. This study was done to suggest directions of regulation on management of externally installed herbal dispensaries. Methods: In this study, we visited and investrigated 7 representative herbal dispensaries to understand current status of herbal dispensaries. After comprehending current domestic regulations on herbal dispensaries, we referred "Management Practice on Dispensary Facility of Traditional Chinese Medicine in Medical Institution", "Enforcement Rule of Decree on Institution Standard of Manufacturing and Importation for Drugs, etc." and "Enforcement Rule of Food Sanitation Act" to suggest improved regulations for herbal dispensaries. Results: We suggested reasonable regulations for facility standards including location of building, dispensary room, water supply facility, lavatory and storage facility, etc.. Conclusions: We hope that results of this study could be baseline data for developing regulations on facility standards of herbal dispensaries.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2012.05a
• /
• pp.643-644
• /
• 2012

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.78-81
• /
• 2021

Through the smart factory construction project, sensors can be installed in manufacturing production facilities and various process data can be collected in real time. Through this, research on real-time facility anomaly detection is being actively conducted to reduce production interruption due to facility abnormality in the manufacturing process. In this paper, to detect abnormalities in production facilities, the manufacturing data was applied to deep learning models Autoencoder(AE), VAE(Variational Autoencoder), and AAE(Adversarial Autoencoder) to derive the results. Manufacturing data was used as input data through a simple moving average technique and preprocessing process, and performance analysis was conducted according to the window size of the simple movement average technique and the feature vector size of the AE model.