Adaptive neuro-fuzzy inference systems (ANFIS) and artificial neural networks (ANNs) for optimizing electrospun PVA/TIO2 fiber diameter

Although electrospinning in nanotechnology is gaining popularity, the influence of electrospinning treatment parameters on fiber diameter is an issue and has not been further explored. Several methods have been used to overcome this problem, such as response surface methodology (RSM), adaptive neuro-fuzzy inference systems (ANFIS), and artificial neural networks (ANNs). This study aimed to investigate the effect of electrospinning treatment parameters on nanofiber diameters using ANNS and ANFIS and evaluate the ability of these methods to predict nanofiber diameters. In this research, electrospun nanofibers were modified under different electrospinning treatment conditions. We fabricated electrospun PVA/TiO2 nanofibers by varying parameters, such as applied voltage, solution concentration, and spinning distance. ANFIS and ANNs were applied to predict and investigate the effect of treatment parameters on the electrospun PVA/TiO2 fiber diameters. Based on this study, the development of ANFIS, artificial neural networks, and response surface methodology could predict the experimental data with the root-mean-square error (RMSE) values were 0.00059067, 7.904308882, and 35.10999, as well as the sum of squares error (SSE) values for the ANFIS, ANNs, and RSM, were obtained at 3.14x10(-6), 562.3028901, and 11094.4, respectively. The results showed that the developed ANNs and ANFIS could accurately predict the experimental data in detail. The novelty of this study is that we used ANNs and ANFIS for the first time to obtain electrospun PVA/TiO2 fiber diameter accurately. The use of artificial intelligence to calculate and simulate the effects of electrospinning treatment for improving nanofiber diameter is another novelty of this research. The scientific application of this research is that the investigation will be beneficial for practitioners, researchers, and engineers in fabricating nanofibers using electrospinning machines. In the future, electrospinning machine design with artificial intelligence will increase productivity and reduce the risk of failure in the production process.

Automated summary

This study investigated the influence of electrospinning treatment parameters on nanofiber diameters using ANNS and ANFIS methods, and evaluated their predictive abilities. The developed artificial neural networks and ANFIS accurately predicted the experimental data, providing important insights for electrospinning machines in fabricating nanofibers.