https://doi.org/10.1140/epjp/s13360-023-04579-w
Regular Article
Backpropagation of Levenberg–Marquardt artificial neural networks for reverse roll coating process in the bath of Sisko fluid
1
College of Mathematics and System Sciences, Xinjiang University, 830046, Ürümqi, China
2
School of Mathematics and Statistics, Xi’an Jiaotong University, 710049, Xi’an, Shaanxi, China
Received:
11
July
2023
Accepted:
10
October
2023
Published online:
24
October
2023
A novel approach to the modeling of the nonlinear parameters of a coating system based on neural networks and artificial neural network neurons has been presented in this paper. The term “artificial neural network” refers to a novel type of information processing system based on modeling the neural system of the human brain. This study aims to utilize supervised neural networks based on Levenberg–Marquardt backpropagation (SNNs-LMB) to analyze the Sisko fluid model in the reverse roll coating process (SFM-RRCP). The mathematical model of SFM-RRCP based on partial differential equations is transformed into a set of nonlinear ordinary differential equations (NL-ODEs). To manipulate non-Newtonian fluid parameters for various scenarios, the perturbation method (PM) generates a reference dataset used by the (SNNs-LMB) technique. The velocity profile, pressure gradient, and pressure profile of the fluidic flow can be constructed by adjusting physical quantities such as velocities ratio and non-Newtonian parameters. The (SNNs-LMB) algorithm undergoes validation, training, and testing procedures on the reference PM data to obtain the numerical solution of SFM-RRCP for different scenarios. Comparing these results with the approximate outcomes confirms the precision and reasonable accuracy of the (SNNs-LMB) approach. The suggested solver (SNNs-LMB) is effective, as evidenced by comparison analyses and performance studies that make use of outputs like regression drawings, absolute error, and error histograms. Further, it has been observed that as the velocities ratio increases, the fluid velocity decreases.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
