Neural Network for Prediction of Hairiness of Ring Spun Cotton Yarn

In this research, the multi-layer perception (MLP) artificial neural network (ANN) model trained by data from the mill was used to predict the hairiness of ring spun cotton yarn. Fourteen kinds of ring spun parameters were grouped into two units: one group was used to train the artificial neural network model, while the other group was used to validate the accuracy of the model. The input parameters of the model are as follows: aperture of guide wire, nip gauge, spindle speed and back draw time. And the output parameter is hairiness of ring spun cotton yarn. Predicting results match the testing data well. The result shows that the hairiness of ring spun cotton yarn can be predicted well by ring spun processing parameters.