Modeling rotor spun yarn strength using polynomial neural networks.

Abstract

This report shows details of the steps which were taken, for execution, findings, and recommendations the project "modeling rotor spun yarn strength using polynomial neural networks". Polynomial Neural Networks (PPN) basically group method of data handling (GMDH) that was presented here as an intelligent algorithm to predict breaking strength of rotor spurn yarns based on rotor parameters and opening roller parameters as one of the most' important parameters in spinning line. Twenty-nine samples were produced on the Autocoro 312 open end rotor spinning machine in NYTIL and different models (PNN and Linear regression) were evaluated. Prediction performance of the PPN was compared with that. of linear regression using correlation coefficient (R2 Value) parameters on test data. The results showed a better capability of the PNN model in comparison to the linear regression model. The R2 values of PNN model and linear regression was 97.33% and 26.63 respectively; which means desirable predictive power of PNN algorithm.