A predictive model for electrospun based Polyvinyl alcohol (PVA) nanofibers diameter using an artificial neural network.
Journal:
Scientific reports
Published Date:
Jul 1, 2025
Abstract
The aim of this work is to develop a predictive model for electrospun based polyvinyl alcohol (PVA) nanofiber diameter. Artificial Neural Network is employed to analyze the key variables such as applied electric field, the polymer concentrations, the rate of injection and nozzle collector distance, involves in the process of electrospinning affecting the diameter of PVA nanofiber. The most suitable network architecture was determined by considering and examining different topologies in artificial neural networks (ANNs) that composed of single and double hidden layers with different numbers of nodes for each layer. Strong prediction capabilities of the developed model are observed in the analysis of the parameters influencing the diameter of spun fibers for ANN configuration of 5-9-1. The findings revealed that PVA fiber diameters' predicted in our work and the already existing experimental data are significantly correlated with a regression that is around 0.973. Also, a low value of average absolute error i.e., 0.06 is obtained after the evaluation of the developed model.
Authors
Keywords
No keywords available for this article.
