Modeling and optimization of electrospun PAN nanofiber diameter using response surface methodology and artificial neural networks

Abstract

Response surface methodology (RSM) based on a three-level, three-variable Box-Benkhen design (BBD), and artificial neural network (ANN) techniques were compared for modeling the average diameter of electrospun polyacrylonitrile (PAN) nanofibers. The multilayer perceptron (MLP) neural networks were trained by the sets of input-output patterns using a scaled conjugate gradient backpropagation algorithm. The three important electrospinning factors were studied including polymer concentration (w/v%), applied voltage (kV) and the nozzle-collector distance (cm). The predicted fiber diameters were in agreement with the experimental results in both ANN and RSM techniques. High-regression coefficient between the variables and the response (R 2 ¼ 0.998) indicates excellent evaluation of experimental data by second-order polynomial regression model. The R 2 value was 0.990, which indicates that the ANN model was shows good fitting with experimental data.Moreover, the RSM model shows much lower absolute percentage error than the ANN model. Therefore, the obtained results indicate that the performance of RSM was better than ANN. The RSM model predicted the 118 nm value of the finest nanofiber diameter at conditions of 10 w/v% polymer concentration, 12 cm of nozzle-collector distance, and 12 kV of the applied voltage. The predicted value (118 nm) showed only 2.5%, difference with experimental results in which 121 nm at the same setting were observed.

Experimental design as a tool for the manufacturing of filtering media based on electrospun polyacrylonitrile/ $$\upbeta $$ β -cyclodextrin fibers

“…In this case, the p value of this factor is very small and its standardized effect on the pareto chart (t value) is very high with respect to the other factors and interactions. The diameter increasing effect of concentration is coherent with the results from reference works ( [11,12]) and it can be explained taking into account that the droplets of more concentrated solutions contain a higher amount of polymer and the electrospun fibers originated from the Taylor cone at the droplet are thicker.…”

“…The experimental design has been used as a tool for the manufacturing of PAN [11,12] and polyvinyl alcohol (PVA) fibers [13]. The aforementioned works present the statistical analysis of the information and the response surfaces or contours for the average diameter of fibers depending on different factors.…”

“…The aforementioned works present the statistical analysis of the information and the response surfaces or contours for the average diameter of fibers depending on different factors. Regarding PAN fibers, solutions of PAN in dimethylformamide (DMF) are used for the electrostatic spinning process and the effects of polymer concentration, applied voltage and tip to collector distance on the average fiber diameter are evaluated (flow rate is fixed) [11,12]. The results of both works are very similar, and while one of them presents that PAN electrospun fibers with diameters under 100 nm may be produced with low concentration polymer solutions (8-10 % w/v), applied voltages between 10 and 20 kV ant tip to collector distances between 10 and 12 cm [11], the other one shows that PAN fibers with diameters around 120 nm may be produced with 10 % w/v polymer solutions, 12 kV of applied voltage and tip to collector distance of 12 cm [12].…”

Predicting the physical properties of drawn Nylon-6 fibers using an artificial-neural-network model

“…The advantage of ANNs is the ability of representing complex relationships directly from the data being modeled, while their representation (modeling) is always nonlinear [12][13][14] . Many researches were done in the textile industry to predict the properties of yarns, woven and nonwoven fabrics and many other characteristics of textile materials 10,[13][14][15][16][17][18][19][20][21][22][23][24][25] . Among these, just few studies are devoted to melt spinning and drawing of synthetic fibers.…”

Evaluation of effective electrospinning parameters controlling polyvinylpyrrolidone nanofibers surface morphology via response surface methodology

“…The surface morphology and the diameter of electrospun nanofibers depend on several variables. These variables are classified as polymer properties (molecular weight [9,10] and solubility [11]), polymer solution characteristics (polymer concentration [12], solution viscosity [10], conductivity [13], and surface tension [13]), processing conditions (applied voltage [14], nozzle-collector distance [14], feed rate [15], and needle diameter [16]), and ambient variables (temperature [17], and relative humidity [18]). As described in the literature [12,14,15], the properties of the polymer solution and processing conditions such as polymer concentration, applied voltage, and nozzle-collector distance have the most significant variables influence in the electrospinning process and the resultant nanofiber morphology, when compared with other variables.…”