Modeling electrospun PLGA nanofibers’ diameter using response surface methodology and artificial neural networks

Abstract

The present work is an attempt to model the diameter of Poly Lactic-co-Glycolic Acid (PLGA) nanofibers by utilizing response surface methodology (RSM) and artificial neural networks (ANNs). Hence, determining the optimal electrospinning process conditions to produce a minimum fiber diameter. For modelling the average diameter of nanofibers, RSM approach based on four parameters (polymer concentration, high voltage and needle tip to collector distance and spinning angle) with five-level was compared to ANN technique. In the RSM approach, central composite design (CCD) was used to determine the individual and interaction impacts of the parameters on the average diameter of nanofibers. Several ANNs of single and double hidden layers with different number of cells for each were tried to obtain the best network structure. The experimental and predicted PLGA fiber diameters using an ANN showed a strong correlation, indicating that the network topology of 4-14-1 has good predictability for analyzing factors impacting PLGA fiber diameter. The average absolute relative error for predicting PLGA nanofibers’ diameter using ANN (2.24%) is slightly less than that obtained from RSM (2.59%). The high regression coefficient between the variables and the response (R2 = 0.9636) shows a good second-order polynomial regression model for evaluating experimental data. The R2 value was 0.945, indicating that the ANN model was good fitting with the experimental results. The optimum combinations (PLGA concentration of 26 wt.%, high voltage 22 kV, needle tip to collector distance 20 cm, and spinning angle 60o) were developed by RSM model for electrospinning PLGA nanofiber that can produce fine, consistent, and high-quality nanofibers.

Analysis and Prediction of Electrospun Nanofiber Diameter Based on Artificial Neural Network

“…The artificial neural network algorithm hierarchy mainly includes the input layer, hidden layer, and output layer. As shown in Figure 1, the spinning solution concentration, spinning voltage, receiving distance, and injection rate are set as the input layer, the weight allocation and integration of the relationship between spinning parameters are reflected in the hidden layer, and the nanofiber diameter is the output layer [22]. The number of hidden layers is generally more than one, and the specific number of layers is determined by the specific requirements of the problem and the number of nodes.…”

“…Compared to traditional optimization methods such as trial-and-error experimentation and statistical modeling, ANNs can handle large amounts of data and identify nonlinear relationships between process parameters and fiber properties that may not be captured by other methods. Additionally, ANNs can continuously learn and improve over time, making them well-suited for dynamic and complex systems like electrospinning [21][22][23][24]. Overall, the use of ANNs in electrospinning optimization has the potential to accelerate the development of new PAN nanofiber materials with tailored properties for various applications.…”

Optimization of electrospun chitosan/polyethylene oxide hybrid nanofibril composite via response surface methodology

“…p -values <.05 show that the variable significantly affects the diameter of the nanofiber. 37,38 Additionally, to confirm the validity and suitability of the adequate model R 2 coefficient of determination and adjusted-R 2 were investigated. R 2 represents the percentage of total variability that the regression model has shown.…”

Fabrication of in situ polymerized polyaniline‐based functional nanofibrous structures for flexible electromechanical devices

“…The electrospun membranes went through an exhaustive characterization encompassing morphological, mechanical, thermal, thermomechanical, and electrical analyses. Morphological features were examined using scanning electron microscopy (SEM) (JEOL JSM‐6510 IV, Japan), with Image‐J software facilitating the measurement of about 100 fiber diameters for each membrane 27 . X‐ray diffraction spectrometry (XRD) (X'Pert3 Powder, Malvern PANalytical, UK) was utilized to analyze the structure and composition of the membranes in the 4°–70° spectrum, using a time interval of 0.6 s.…”