Using Artificial Neural Network Model on Studying Fiber Diameter of Spunbonding Nonwovens: Comparison with Mathematical Empirical Statistical Method Model

In this article, the mathematical statistical model and artificial neural network model are established and used to predict the fiber diameter of spunbonding nonwovens. The artificial neural network model has good approximation capability and fast convergence rate, and is employed in this research. The results show it can provide quantitative predictions of fiber diameter and yield more accurate and stable predictions than the mathematical statistical model, which shows that the artificial neural network technique is really an effective and viable modeling method when the required number of experimental data sets is available. The effects of process parameters on fiber diameter are also determined by the ANN model. By analyzing the results of the mathematical statistical model, the effects of process parameters on fiber diameter can be predicted.