Prediction and analysis of flow behavior of a polymer melt through nanochannels using artificial neural network and statistical methods

Abstract

A new methodology, namely, artificial neural network (ANN) approach was proposed for modeling and predicting flow behavior of the polyethylene melt through nanochannels of nanoporous alumina templates. Wetting length of the nanochannels was determined to be a function of time, temperature, diameter of nanochannels, and surface properties of the inner wall of the nanochannels. An ANN was designed to forecast the relationship between the length of wetting as output parameter and other aforementioned parameters as input variables. It was demonstrated that the ANN method is capable of modeling this phenomenon with high accuracy. The designed ANN was then employed to obtain the wetting length of the nanochannels for those cases, which were not reported by the wetting experiments. The results were then analyzed statistically to identify the effect of each independent variable, namely, time, temperature, diameter of nanochannels, and surface properties of the inner wall of nanochannels as well as their combinations on the wetting length of the nanochannels. Interesting results were attained and discussed.

On the kinetics of the capillary imbibition of a simple fluid through a designed nanochannel using the molecular dynamics simulation approach

“…This phenomenon is of great importance in practical applications [53]. An extensive review of the fabrication methods of the nanochannels can be found in the literature [54].…”

Effects of hydration level, temperature, side chain and backbone flexibility of the polymer on the proton transfer in short-side-chain perfluorosulfonic acid membranes at low humidity conditions

“…energy gap calculated by the DFT method as a function of water content, temperature, side chain flexibility of the SSC PFSA membrane, and backbone flexibility of the SSC PFSA membrane. In addition, the use of the ANN method has some advantages as detailed below [28][29][30]. It is able to learn and therefore generalize.…”

“…An introduction to the ANN method has been given in our previous works [28][29][30]. In summary, an ANN is a computational tool inspired by the performance of the brain and nervous systems in biological organisms.…”

A comparison of neural networks and adaptive neuro-fuzzy inference systems for the prediction of water diffusion through carbon nanotubes

“…On the other hand, ANFIS owns both abilities of self-organizing network structure and dealing with ambiguous information. A few numbers of studies have been devoted to application of artificial intelligence tools in nanofluidic problems (Ahadian et al , 2010(Ahadian et al , 2011.…”