Prediction of fiber diameter of Polylactic Acid (PLA) Spunbonding Nonwoven fabrics Using Artificial Neural Network and Statistical Methods

In this work, the artificial neural network model and statistical model are established and used for predicting the fiber diameter of polylactic acid (PLA) spunbonding nonwovens from the process parameters. The artificial neural network model has good approximation capability and fast convergence rate, and is utilized in this research. The results show the artificial neural network model can provide quantitative predictions of fiber diameter and yield more accurate and stable predictions than the statistical model, which reveals that the artificial neural network model is based on the inherent principles, it can yield reasonably good prediction results and provide insight into the relationship between process parameters and polylactic acid(PLA)fiber diameter. By analyzing the results of the artificial neural network model, the effects of process parameters on polylactic acid (PLA)fiber diameter can be predicted, at the same time, which also indicates that the artificial neural network technology is really an effective and viable modeling method when the required number of experimental data sets is available.