Neural Networks: An Alternative Solution for Statistically Based Parameter Prediction

摘要

Over the past years, research has attempted to relate fiber properties with yarn properties, and many regression equations have been developed to accomplish this. The complexities of multiple regression equations put limits on their universal acceptance. Neural networks with better nonlinear mapping have also been used to develop such relationships. Our statistical data analysis of a few yarn properties will determine the suitability of neural networks for such textile applications.