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

Abstract

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.

On the Robustness of Forward and Inverse Artificial Neural Networks for the Simulation of Ethylene/1‐Butene Copolymerization

“…The results show that the predicted chain microstructures deviated mostly well within the range of error introduced in the data set with only few outliers, possibly due to the error propagation. Similar behavior has also been reported . This indicates that the forward model is robust as most prediction errors do not propagate outside the range of errors introduced in the data.…”

“…Similar behavior has also been reported. [45] This indicates that the forward model is robust as most prediction errors do not propagate outside the range of errors introduced in the data. This also proves that, had we used experimental data instead of model data, our ANN would be able to correctly predict the values for M n , M w , CC, and Y within the experimental errors associated with these measurements.…”

Application of ANN modeling techniques in the prediction of the diameter of PCL/gelatin nanofibers in environmental and medical studies

“…The results show that artificial neural networks can predict the diameter of electrospun polyurethane nanofibers well. 56 In this research, PDNFM MLP provides a framework for accurate analyzing electrospinning parameters and the diameter of electrospun PCL/Gt nanofibers that will result in greater economy and save time. The results of the MLP approach, especially the greater accuracy ( R 2 = 0.96) obtained in comparison with the RBFNN ( R 2 = 0.821), and SVM ( R 2 = 0.829) results signify that PDNFM MLP can be used as a comparative impact assessment model for predicting the diameter of PCL/Gt nanofibers.…”

“…20 These results were reported in recent studies. [56][57][58] Fig. 10c shows the effect of applied voltage on the diameter of the nanobers.…”

Evaluation thermal degradation kinetics of ionic liquid assisted polyetheretherketone‐multiwalled carbon nanotubes composites

“…The ANN model was established with the help of MATLAB 2019a. The equations shown below [30][31][32] were used to evaluate the model by estimating MSE (mean square error), MAD (mean absolute deviation), and RMSE (root mean square error), respectively. ANN design provides better prediction when R 2 (coefficient of determination) is higher and RMSE and MSE have lower values.…”