Cyber Physical Energy System for Saving Energy of the Dyeing Process with Industrial Internet of Things and Manufacturing Big Data

• Published in: International journal of precision engineering and manufacturing-green technology 2020-01, Vol.7 (1), p.219-238
• Main Authors: Park, Kyu Tae, Kang, Yong Tae, Yang, Suk Gon, Zhao, Wen Bin, Kang, Yong-Shin, Im, Sung Ju, Kim, Dong Hyun, Choi, Su Young, Do Noh, Sang
• Format: Article
• Language: English
• Subjects: Big Data; Data analysis; Data collection; Data management; Decision making; Defective products; Dyes; Emissions; Emissions control; Energy conservation; Energy consumption; Energy efficiency; Energy technology; Finishing; Greenhouse effect; Greenhouse gases; Industrial applications; Industrial plants; Industry 4.0; Internet of Things; Investment; Machine learning; Machine shops; Manufacturing; Manufacturing industry; Neural networks; Power efficiency; Process planning; Sampling techniques; Textile industry
• ISSN: 2288-6206; 2198-0810
• DOI: 10.1007/s40684-019-00084-7

The manufacturing industry has recently been focusing on improving energy efficiency to reduce greenhouse gas emissions and achieve sustainable growth. The focus is on combining existing energy technologies with new information and communication technologies as the Fourth Industrial Revolution approaches. Dyeing and finishing shops use the most energy in the textile industry and have below-average energy efficiency because of low technology and facility investment. Research into increasing the energy efficiency of dyeing and finishing shops has concentrated on developing equipment; however, it is difficult for small- and medium-sized factories to benefit from these advances. Thus, research into means of improving energy efficiency by improving the process and system efficiency of dyeing and finishing companies, who have difficulties with facility investment and operation, is necessary. In this study, a cyber physical energy system that improves the energy efficiency of the dyeing process by collecting and analyzing manufacturing big data was developed. Further, the implemented system was applied to actual dyeing and finishing shops, and its effects were verified. This research contributes to improving the situation of the dyeing process using machine learning techniques and manufacturing big data by adjusting cyber physical energy systems without utilizing expensive equipment. Inaccurate process instruction from the laboratory are also replaced by the cyber physical energy system, and the invalid and inefficient steps in the traditional process scenario derived from operator’s experience are replaced with more valid and usable actions.