Prediction of Fiber Diameter of Spunbonding Nonwovens by Using Neural Network and Multiple Regression Models

摘要

In this article, the multiple regression model and neural network model are designed and used to predicting the fiber diameter of spunbonding nonwovens from the process parameters. The neural network has good approximation capability and fast convergence rate, and it can provide quantitative predictions of fiber diameter. The results show the ANN model can yield more accurate and stable predictions than the multiple regression model. The predicted and experimental values agree well, indicating that the neural network is an excellent method for predictors.