Over the past several years, numerous relationships between fiber properties and yarn performance have been developed. The classical method for predicting yam performance is statistical analysis such as linear multiple regression. Neural networks are now a subject of interest in many fields and a tool for many areas of problem solving. This study investigates the application of neural networks to yarn strength prediction. HVI test results of the 1989 crop are used to train the neural nets and performance is discussed.
Get full access to this article
View all access options for this article.
References
1.
Aarts, E., and van Larhoven, P. , "Simulated Annealing: Theory and Practice ," John Wiley and Sons, NY, 1987.
2.
Avitzur, Ron , Your Own Handprinting Recognition Engine, Dr. Dobb's J. (4), 32-37 (1992).
3.
Baba, N., and Kozaki, M., An Intelligent Forecasting System of Stock Price Using Neural Networks, International Joint Conference on Neural Networks, Baltimore, MD, 1992.
4.
Blum, Adam, "Neural Networks in C++," John Wiley & Sons , NY, 1992.
5.
Ethridge, M.D. , Towery, J.D., and Hembree, J.F., Estimating Functional Relationships Between Fiber Properties and the Strength of Open-End Spun Yams, Textile Res. J.52, 35-45 ( 1982).
6.
Homik, K., Stinchcombe, M., and White, H., Multilayer Feedforward Networks Are Universal Approximators, Neural Networks2, 359-366 ( 1989).
7.
Lieberman, M.A. , and Patil, R.B., Clustering andNeural Networks to Categorize Cotton Trash , Opt. Eng.33 (5), 1642-1653 (1994).
Ramey, H.H., Lawson, R., and Worley, S., Relationship of Cotton Fiber Properties to Yam Tenacity, Textile Res. J.47, 685-691 (1977).
10.
Rumelhart, D.E. , Hinton, G., Williams , R.J., LearningInternal Representations by Error Propagation , in "Parallel Distributed Processing," vol. 1, MIT Press, Cam-bridge, MA, 1986, pp. 318-362.
11.
Troudet, T., and Werrill, W., A Real Time Neural Net Estimator of Fatigue Life, in "Proc. International Joint Conference on Neural Networks," MI: IEEE Neural Networks Council, June, 1990.
