Electrospinning predictions using artificial neural networks

With regard to the fact that currently there is no comprehensive method to predict diameter of polyurethane/solvent fiber from electrospinning, in this study, diameter prediction of polyurethane/solvent fiber was conducted using neural networks and an error of 166 nm was observed. This error shows that artificial neural networks (ANNs) can predict diameter of electrospinning polyurethane fibers well. Then, considering weak repeatability nature of electrospinning in fabricating fibers with desired diameter, least mean square is used to improve stability of neural network model that shows an error of 113 nm, which represented better results compared to common ANN. To investigate the effect of each one of parameters affecting fiber diameter, sensitivity analysis was conducted. Along with this predicting model, sensitivity analysis can be used to reduce parameters space before conducting future studies. © 2017 Wiley Periodicals, Inc. J. Appl. Polym. Sci. 2017, 134, 45116.

(\frac{normalT normalH normalF}{normalT normalH normalF + normalD normalM normalF})

, polyurethane concentration, voltage and distance. Two types of cost functions of MSE [eq. ]…”

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Fabricating and robust artificial neural network modeling nanoscale polyurethane fiber using electrospinning method

Hosaini‐Alvand

Mirshekar

Khorasani

et al. 2017

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

Premasudha

Reddy

Lee

et al. 2020

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.

Physics‐based deep neural network model to guide electrospinning polyurethane fibers

Rahman

Tafreshi

Pourdeyhimi

2022

Electrospinning is an inexpensive room-temperature method of producing nanofibers from polymer granules. While it is quite easy to produce electrospun nanofibers, it is very difficult to control properties of the resulting fibers without conducting laborious trial-and-error experiments. In this work, a mass-spring-damper (MSD) model was used to simulate formation of electrospun fibers for different combinations of electrospinning conditions such as voltage, needle-to-collector distance, and polymer concentration. The sparse data from the CPU-intensive MSD model were then used in developing a deep neural network (DNN) model that could guide the electrospinning experiment toward producing fibers with a desired diameter. The accuracy of the MSD-DNN hybrid model was examined via comparison with experimental data obtained by electrospinning polyurethane fibers.