Global Journal of Technology and Optimization

Modeling and Prediction of Electrospun Fiber Morphology using Artificial Intelligence Techniques

Abstract

Deogratias Nurwaha and Xinhou Wang

This study presents the application of Artificial Intelligence (AI) techniques to predict the morphology of nanofibers
produced by needless electrospinning method. Two straight and parallel copper wire electrodes electrospinning
method was used to produce nanofibers. Using digital image processing software Image Journal, Mean Nanofiber
Diameter (MFD) and Nanofiber Diameter Standard Deviation (NFSD) have been measured and recorded. Adaptive
Neuro-Fuzzy Inference Systems (ANFIS), Support Vector Machines (SVMs) and Gene Expression Programming
(GEP) methods were used for prediction of electrospun nanofiber morphology. Prediction results and experimental
were compared. It was found that SVMs model has better predictive power in comparison with both ANFIS and Gene
Expression Programming models. However, results provided by both GEP and ANFIS are also acceptable. The
relative importance of process parameters as contributor to the nanofiber morphology was also investigated. It was
found that nanofiber morphology was strongly or weakly dependent on processing parameters.