Prediction of micro-spun yarn lea CSP using artificial neural networks

Abstract

<span style="font-size: 14.0pt;mso-bidi-font-size:8.0pt;font-family:" times="" new="" roman","serif""="">A back-propagation artificial neural network has been used to develop a model relating to cotton fibre properties and micro-spun yarn lea CSP. Fibre properties such as span length , bundle strength, fineness, breaking elongation, uniformity ratio and percentage of mature fibres have been studied. <span style="font-size:14.5pt;mso-bidi-font-size:8.5pt;font-family:" arial","sans-serif""="">It <span style="font-size:14.0pt;mso-bidi-font-size:8.0pt;font-family:" times="" new="" roman","serif""="">is observed that a neural network architecture having five hidden neurons in one hidden layer and an epoch size of 12 gives better prediction. The predictions are more accurate than those obtained from regression models. The mean absolute error of neural network model is found to be 60% lower than those of the regression models.

</span></span></span>