Detailed study on fusion characteristics of rigid poly(vinyl chloride) nanocomposites: The comparison of using multiple regression analysis and artificial neural network

Abstract

Fusion behavior of poly(vinyl chloride) (PVC) compounds plays an important role in the development of physical properties of processed material. The fusion characteristics in PVC processing are governed by material variables that affect the fusion with some interactions. In this research, the aim was to characterize the effects of formulation ingredients on fusion characteristics of PVC. Four material parameters, including the contents of nanoclay (NC), azodicarbonamide, calcium stearate, and processing aid, are proposed as affecting variables. The fusion time (FT) as well as fusion factor (FF) are considered fusion indicators and are experimentally determined in some different levels of affecting parameters. The multivariable regression analysis (MRA) and the Artificial Neural Network (ANN) modeling are considered as two analytical methods. The regression analysis result for the FT denotes, in part, significant linear and quadratic effects of NC and also its significant interactions with azodicarbonamide and calcium stearate, whereas that of FF indicates only a linear effect of NC. ANN modeling is performed with a three‐layer (input, hidden, and output) neural network. The results of the comparison of the MRA and ANN predictions with experimental values are reported as the correlation coefficient (R2), mean‐square error, and mean absolute percentage error for both FF and FT parameters. The obtained values clearly denote that the ANN results are more precise and especially more general than those of MRA. However, in the case of FT, improvement of the ANN modeling is much greater than that of FF. J. VINYL ADDIT. TECHNOL., 21:147–155, 2015. © 2014 Society of Plastics Engineers

Fuzzy logic model for prediction of fusion characteristics in rigid polyvinyl chloride nanocomposite

“…It is a fast decision tree learner that builds a decision tree using information gain and prunes it using reduced error pruning (with back fitting). 20 In this research, experimental data that are previously used by the authors in a relevant study 9 are considered again. These data are presented as three predictors and a single response variable in Table 1.…”

“…In this research, experimental data that are previously used by the authors in a relevant study 9 are considered again. These data are presented as three predictors and a single response variable in Table 1.…”

“…6 To the best of the authors’ knowledge, the lack of data in fusion process of PVC nanocomposites as well as no effort orientated toward evaluating the interaction of effects of different ingredients has been seen in the literature. So, in previous works, 9 the authors reported the experimental research on evaluating the effects of processing parameters 5 and nanoclay (NC) and calcium stearate (CaSt) lubricant 6 on fusion parameters of rigid PVC formulations. In another article, 7 the effects of NC and some additives on fusion characteristics and thermal stability of rigid nanocomposites are reported.…”

“…In another research, 8 the effects of four key formulation parameters, that is, NC, blowing agent azodicarbonamide (ADCA), processing aid (PA), and internal lubricant CaSt content on the fusion parameters of melt-blended rigid PVC/NC nanocomposite foams are evaluated through experimental study. In a modeling attempt, Moghri et al 9 presented a nonlinear regression and an artificial neural network (ANN) model for prediction of FT and fusion factor of PVC nanocomposites as a function of content of NC, ADCA, and PA. They found that a simple linear regression model may predict fusion factor for only NC content, while a quadratic equation including all four predictors and interaction terms is necessary to predict FT.…”

Optimization of fusion behavior of the nanocomposites based on poly(vinyl chloride)/poly(epichlorohydrin‐co‐ethylene oxide)/organoclay

“…Therefore, it is necessary to study interactive effects of the parameters on fusion of the PVC and obtain optimized levels of the parameters. Our recent reports have been focused on this subject and several statistical approaches including fuzzy logic‐based model , multivariable regression analysis (MRA) and artificial neural network , and response surface methodology (RSM) have been employed to achieve desired fusion characteristics of the PVC/NC nanocomposites. Saeb et al studied effect of the NC modifier on FT and FF of the PVC nanocomposites using RSM.…”