Comparative Analysis of Regression and Artificial Neural Network Models for the Prediction of Yarn Hairiness

Abstract

Hairiness is a very important yarn quality parameter for high speed weaving. This paper presents a comparative analysis of two modeling methodologies for the prediction of ring and rotor yarn hairiness. Cotton fibre properties measured by a high volume instrument (HVI) and yarn count have been used as inputs for artificial neural network (ANN) and linear regression models. The prediction accuracy for both of the models is found to be good as the correlation coefficient is higher than 0.92 and mean absolute error is less than 4%. However, ANN models have an edge over the regression model particularly for ring yarn hairiness prediction. The importance of the cotton fibre properties on yarn hairiness has also been analysed by the developed ANN and regression models. For ring spun yarns, the ranking of cotton fibre properties given by the ANN and regression models are generally in agreement although some disparities exist in the ranking of length properties. Both models yield almost identical ranking of cotton fibre properties for rotor yarn hairiness.

Citation

Majumdar, A. (2010), "Comparative Analysis of Regression and Artificial Neural Network Models for the Prediction of Yarn Hairiness", Research Journal of Textile and Apparel, Vol. 14 No. 3, pp. 85-93. https://doi.org/10.1108/RJTA-14-03-2010-B009