A four-layer fuzzy neural network (FNN) model combining particle swarm optimization (PSO) algorithm and clustering method is proposed to predict the solubility of gases in polymers, hereafter called the CPSO-FNN, which combined fuzzy theory's better adaptive ability, neural network's capability of nonlinear and PSO algorithm's global search ability. In this article, the CPSO-FNN model has been employed to investigate solubility of CO 2 in polystyrene, N 2 in polystyrene, and CO 2 in polypropylene, respectively. Results obtained in this work indicate that the proposed CPSO-FNN is an effective method for the prediction of gases solubility in polymers. Meanwhile, compared with traditional FNN, this method shows a better performance on predicting gases solubility in polymers. The values of average relative deviation, squared correlation coefficient (R 2 ) and standard deviation are 0.135, 0.9936, and 0.0302, respectively. The statistical data demonstrate that the CPSO-FNN has an outstanding prediction accuracy and an excellent correlation between prediction values and experimental data.Recent years, the interdiscipline of information science and intelligent technology has a broad application perspective. 4,12,13 With the popularization of artificial neural networks (ANN), the determination of ANN structure, parameters and bias becomes the most crucial factors because the training process of ANN could be considered as a classical optimization problem. 12 Recently, researchers discovered that many intelligent algorithms such as genetic algorithm, 13 simulated annealing algorithm, 14 fuzzy logic theory, 15 gravitational search algorithm, 16 wavelet analysis, 17 ant colony optimization algorithm, 18 particle swarm optimization algorithm (PSO), 12,19-21 chaos theory, 22 and so on, can all be used for this determination. Therefore, ANN combined with intelligent optimization algorithms namely hybrid neural network has become one of the most active subject.So far as solubility of gases in polymers is concerned, it is affected by temperature, pressure, and sometimes it can also be affected by the interactions with the groups of the macromolecular chains. 23 As a result of the nonlinear relationship of these
In this study, the experiments of gas-assisted extrusion (GAE) for molten polypropylene were carried out under different gas pressures, the different extrudate deformations and sharkskin defects of melt were observed. To ascertain the effects of gas on melt extrusion, non-isothermal numerical simulation of GAE based on gas/melt two-phase fluid model was proposed and studied. In the simulations, the melt extruded profile, physical field distributions (velocities, pressure drop, and first normal stress difference) were obtained. Numerical results showed that the deformation degree of melt increased with increasing gas pressure, which was in good agreement with experimental results. It was demonstrated that the influence of gas pressure on the melt extrusion could be well reflected by GAE simulation based on gas/melt two-phase fluid model rather than simplified-GAE (SGAE) based on full-slip wall boundary condition used in the past time. Experimental and numerical results demonstrate that the gas pressure induced first normal stress difference is the main reason of triggering flow behavior changes, extrudate deformations, and sharkskin defects of melt. Therefore, the reasonable controlling of gas pressure is a key in practice of GAE, and the gas layer and its influence should be considered in GAE numerical simulation.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.