Electrospun nanofiber membrane diameter prediction using a combined response surface methodology and machine learning approach

Despite the widespread interest in electrospinning technology, very few simulation studies have been conducted. Thus, the current research produced a system for providing a sustainable and effective electrospinning process by combining the design of experiments with machine learning prediction models. Specifically, in order to estimate the diameter of the electrospun nanofiber membrane, we developed a locally weighted kernel partial least squares regression (LW-KPLSR) model based on a response surface methodology (RSM). The accuracy of the model's predictions was evaluated based on its root mean square error (RMSE), its mean absolute error (MAE), and its coefficient of determination (R²). In addition to principal component regression (PCR), locally weighted partial least squares regression (LW-PLSR), partial least square regression (PLSR), and least square support vector regression model (LSSVR), some of the other types of regression models used to verify and compare the results were fuzzy modelling and least square support vector regression model (LSSVR). According to the results of our research, the LW-KPLSR model performed far better than other competing models when attempting to forecast the membrane's diameter. This is made clear by the much lower RMSE and MAE values of the LW-KPLSR model. In addition, it offered the highest R² values that could be achieved, reaching 0.9989.

Application of response surface methodology to tailor the surface chemistry of electrospun chitosan-poly(ethylene oxide) fibers

Chitosan is a promising biocompatible polymer for regenerative engineering applications, but its processing remains challenging due to limited solubility and rigid crystalline structure. This work represents the development of electrospun chitosan/poly(ethylene oxide) blend nanofibrous membranes by means of a numerical analysis in order to identify and tailor the main influencing parameters with respect to accessible surface nitrogen functionalities which are of importance for the biological activity as well as for further functionalization. Depending on the solution composition, both gradient fibers and homogenous blended fiber structures could be obtained with surface nitrogen concentrations varying between 0 and 6.4%. Response surface methodology (RSM) revealed chitosan/poly(ethylene oxide) ratio and chitosan molecular weight as the main influencing factors with respect to accessible nitrogen surface atoms and respective concentrations. The model showed good adequacy hence providing a tool to tailor the surface properties of chitosan/poly(ethylene oxide) blends by addressing the amount of accessible chitosan.