To read this content please select one of the options below:

Intelligent Settings Using Artificial Intelligence at Auto-leveling Drawing Frame

Farooq Assad (Institute of Textile and Clothing Technology, Technishe Universität Dresden, Germany, )
C. Cherif (Institute of Textile and Clothing Technology, Technishe Universität Dresden, Germany, )

Research Journal of Textile and Apparel

ISSN: 1560-6074

Article publication date: 1 August 2011

175

Abstract

The optimization of a process requires exact knowledge of the process, which is knowledge of correlations and inter-dependence between the process-determining variables and the knowledge over the actual condition of the process. In a data rich knowledge poor process like spinning, where the exact relationships between machine, material, climate and quality are yet to be concluded objectively, this research focuses on the use of artificial neural networks as a tool to find out the correlations between decisive variables and to determine the optimum settings. Drawing frame is considered to be the last fault correction point in spinning preparation chain, therefore, its settings has a vital role to play towards yarn quality. Leveling action point is one of the important auto-leveling settings involving an automatic search function at Rieter drawing frame RSB-D40 and requiring a large amount of sliver. In this study, attempts were made to optimize the leveling action point. Optimization of draft settings is also within the scope of this article. The ANNs were used to achieve such objectives and they were found to be very helpful in identifying the optimum settings and hence decreasing material loss and improving sliver quality.

Keywords

Citation

Assad, F. and Cherif, C. (2011), "Intelligent Settings Using Artificial Intelligence at Auto-leveling Drawing Frame", Research Journal of Textile and Apparel, Vol. 15 No. 3, pp. 86-93. https://doi.org/10.1108/RJTA-15-03-2011-B010

Publisher

:

Emerald Group Publishing Limited

Copyright © 2011 Emerald Group Publishing Limited

Related articles