DIGITALISED NONWOVEN MANUFACTURING FOR REDUCED ENERGY CONSUMPTION AND EFFICIENT PRODUCTION RATES

Year 2023, , 226 - 230, 30.09.2023

M Murat Peksen Fatma Banu Nergis , Cevza Candan , Bilge Koyuncu

https://doi.org/10.7216/teksmuh.1365862

Abstract

The requirements placed on the textile industry are changing drastically. Zero-emission targets for 2030 and beyond require cross-sectoral changes. This also challenges the textile industry to find viable all-in solutions that satisfy social, economic, and sustainable requirements. Currently, the use of textiles in transdisciplinary sectors demands a high level of tailor-made solutions. This requires a broad understanding of the processed materials, complex multiphysics as well as machine settings. Hence, to consolidate high production rates with optimal energy consumption and the use of sustainable resources, systematic research and product development need to be pursued. The digitalisation of research and production in the textile industry aids to close the gap between the complex production processes and the quality measure of the end products. For this purpose, a systematic approach comprising experimental measurements and emerging digital technologies is used. nonwoven manufacturing machine park results have been used for the benchmark study.

Keywords

AI, Nonwoven, Multiphysics, Digitalisation, Digital twin, Machine-Learning

Thanks

The authors gratefully acknowledge the R&D team of Low&Bonar (former COLBOND bv) for their technical support in experimental measurements that have been used as data in the research.

References

• 1. Peksen, M. (2022). Artificial Intelligence-Based Machine Learning toward the Solution of Climate-Friendly Hydrogen Fuel Cell Electric Vehicles. Vehicles 4, 663–680.
• All references were included within the file of manuscript.