Using artificial neural networks to model and interpret electrospun polysaccharide (Hylon VII starch) nanofiber diameter

Abstract

Present work was aimed to develop an artificial neural networks (ANN) model to predict the polysaccharide-based biopolymer (Hylon VII starch) nanofiber diameter and classification of its quality (good, fair, and poor) as a function of polymer concentration, spinning distance, feed rate, and applied voltage during the electrospinning process. The relationship between diameter and its quality with process parameters is complex and nonlinear. The backpropagation algorithm was used to train the ANN model and achieved the classification accuracy, precision, and recall of 93.9%, 95.2%, and 95.2%, respectively. The average errors of the predicted fiber diameter for training and unseen testing data were found to be 0.05% and 2.6%, respectively. A stand-alone ANN software was designed to extract information on the electrospinning system from a small experimental database. It was successful in establishing the relationship between electrospinning process parameters and fiber quality and diameter. The yield of smaller diameter with good quality was favored by lower feed rate, lower polymer solution concentration, and higher applied voltage.

Machine learning to empower electrohydrodynamic processing

“…(C(i)) High accuracies were obtained using ANN, (C(ii)) particularly when compared to multi-linear regression [131]. Study revealed that DoE performed poorly in predicting fibre diameter compared to (D(ii)) ANN [129]. (X -denotes the input feature; Ydenotes the target variable; T -target) [140]; and the fibre diameter for (B) polycaptolactone/gelatin blends [131]; (C) polyurethane [147]; (D) poly(vinyl pyrrolidone) [135];…”

“…ML on the other hand can overcome the aforementioned issues, and hence less effort is spent by researchers in preparing the data. A more pertinent advantage is that ML was reported to outperform a DoE quadratic model in predicting fibre diameter (Figure 5(D)) [129,130].…”

“…and poly vinyl alcohol composite [138]. (S -denotes Significance) Some of the studies using ANN applied sensitivity analysis to determine the relationship between electrospinning parameters and fibre diameter [129], whereas others used surface response plots to determine the relationship. Sensitivity analysis is used to identify how 'sensitive' a model is to change when the input is varied [148].…”

“…Sensitivity analysis is used to identify how 'sensitive' a model is to change when the input is varied [148]. For producing starch fibres, the ANN modelling elucidated an inverse relationship between fibre diameter and both spinning distance (5-8 cm) and voltage (6-10 kV), whereas a proportional relationship between starch concentration and fibre diameter was observed (10-15 w/v%) [129]. For PVP, increasing the polymer concentration (8-20 wt%) or voltage (13)(14)(15)(16)(17)(18)(19)(20)(21)(22)(23) was found to increase fibre diameter (10-20 cm), whereas increasing the spinning distance was found to decrease fibre diameter [135].…”

Correlating the 3D melt electrospun polycaprolactone fiber diameter and process parameters using neural networks

“…Electrospinning gained considerable attention due to its flexibility in fabricating micro/nanoscale polymer fibers for various applications 4,5 . The electrospun fibers are used mainly in infiltration, 5 scaffold fabrication, drug delivery, 6,7 and wound healing 8 . Based on the purpose of the application, the fabrication process can use either a polymer solution or melt phases of polymers.…”