The Prediction of Yarn Tensile Properties by Using Artificial Neural Networks

This paper presents an artificial-neural-net model for predicting yarn tensile properties. A single hidden-layer neural network trained by using the back-propagation algorithm performs a functional mapping between material properties, process variables, and the resulting yarn tensile properties. The material and process variables, namely, yarn count, blend, and front- and back-nozzle pressures on an air-jet spinning machine, arc correlated with...