Use of Artificial Neural Networks for Determining the Leveling Action Point at the Auto-leveling Draw Frame

Abstract

Artificial neural networks with their ability of learning from data have been successfully applied in the textile industry. The leveling action point is one of the important auto-leveling parameters of the drawing frame and strongly influences the quality of the manufactured yarn. This paper reports a method of predicting the leveling action point using artificial neural networks. Various leveling action point affecting variables were selected as inputs for training the artificial neural networks with the aim to optimize the auto-leveling by limiting the leveling action point search range. The Levenberg—Marquardt algorithm is incorporated into the back-propagation to accelerate the training and Bayesian regularization is applied to improve the generalization of the networks. The results obtained are quite promising.

Keywords

artificial neural networks auto-leveling draw frame leveling action point

Get full access to this article

View all access options for this article.

References

Huang, C.C. , and Chang, K.T. , Fuzzy Self-organizing and Neural Network Control of Sliver Linear Density in Drawing Frame, Textile Res. J. 71(11), 987-992 (2001).

Dämmig, J. , Cherif, C. , and Karalar, I. , "Apparatus for the Optimizing of the Regulation Adjustment of a Spinning Machine as well as a Procedure Corresponding Thereto", U.S. Patent 6,874,204 B2, 2005.

Cherif, C. , and Wulfhorst, B. , "Method and Apparatus for Determining the Point of Regulation for a Drafting Unit in a Fiber Processing Machine", U.S. Patent 6,640,392 B2, 2003.

Vangheluwe, L. , Sette, S. , and Pynckels, F. , Assessment of Set Marks by Means of Neural Nets, Textile Res. J. 63(4), 244-246 (1993).

Shamey, R. , and Hussain, T. , Artificial Intelligence in the Colour and Textile Industry, Rev. Prog. Color. 33, 33-45 (2003).

Veit, D. , "Einstellung von Falschdraht-Texturiermaschinen mit Hilfe der Evolutionsstrategie und neuronaler Netze", Shaker Verlag, Aachen, 1999.

Ramesh, M.C. , Rajamanickam, R. , and Jayaraman, S. , The Prediction of Yarn Tensile Properties by Using Artificial Neural Networks, J. Textile Inst. 86, 459-469 (1995).

Cheng, L. , and Adams, D.L. , Yarn strength Prediction using Neural Networks, Textile Res. J. 65(9), 495-500 (1995).

Sette, S. , Boullart, L. , Langenhove, L.V. , and Kiekens, P. , Optimizing the Fiber-to-Yarn Production Process with a Combined Neural Network/Genetic Algorithm Approach, Textile Res. J. 67(2), 84-92 (1997).

10.

Beltran, R. , Wang, L. , and Wang, X. , Predicting Worsted Spinning Performance with an Artificial Neural Network Model, Textile Res. J. 74(9), 757-763 (2004).

11.

Majumdar, P.K. , and Majumdar A. , Predicting the Breaking Elongation of Ring Spun Cotton Yarns Using Mathematical, Statistical and Artificial Neural Models , Textile Res. J. 74(7), 652-655 (2004).

12.

Desai, J.V. , Kane, C.D. , and Bandyopadhayay , B. , Neural Networks : An alternative Solution for Statistically Based Parameter Prediction, Textile Res. J. 74(3), 227-230 (2004).

13.

Velasquez, G. , "A Distributed Approach to a Neural Network Simulation Program", Master's Thesis, The University of Texas at El Paso, El Paso, TX, 1998.

14.

Mackay, D.J.C. , Bayesian Interpolation, Neural Comput. 4, 415-447 (1992).

15.

Foresee, F.D. , and Hagan, M.T. , Gauss-Newton Approximation to Bayesian Regularization, in "Proceedings of the 1997 International Joint Conference on Neural Networks". International Conference on Neural Networks, TX, USA, 1997, pp. 1930-1935.

16.

Internet FAQ Archive [homepage on the Internet]. Warren, S. , Advameg, Inc., c 2004 [updated 26 June 2007; cited 15 January 2007]. Available from http://www.faqs.org/faqs/ai-faq/neural-nets/ .

17.

Andreas, B. , "Untersuchung des Regeleinsatzpunkts an der Strecke RSB-D40", Diploma Thesis, Fachhochschule Hof, Germany , 2006.