Predicting the fiber diameter of spunbonding nonwovens fabrics by means of physical model, statistical method and artifical neural network theory

Abstract

Purpose

The purpose of this paper is to establish three modeling methods (physical model, statistical model, and artificial neural network (ANN) model) and use it to predict the fiber diameter of spunbonding nonwovens from the process parameters.

Design/methodology/approach

The results show the physical model is based on the inherent physical principles, it can yield reasonably good prediction results and provide insight into the relationship between process parameters and fiber diameter.

Findings

By analyzing the results of the physical model, the effects of process parameters on fiber diameter can be predicted. The ANN model has good approximation capability and fast convergence rate, it can provide quantitative predictions of fiber diameter and yield more accurate and stable predictions than the statistical model.

Originality/value

The effects of process parameters on fiber diameter are also determined by the ANN model. Excellent agreement is obtained between these two modeling methods.

Citation

Zhao, B. (2015), "Predicting the fiber diameter of spunbonding nonwovens fabrics by means of physical model, statistical method and artifical neural network theory", International Journal of Clothing Science and Technology, Vol. 27 No. 2, pp. 262-271. https://doi.org/10.1108/IJCST-01-2014-0015