Design of inverse multiquadric radial basis neural networks for the dynamical analysis of wire coating problem with Oldroyd 8-constant fluid

Wire coating is a commercial method to insulate wires for mechanical intensity and environmental protection. In this experimental study, the technique of computational intelligence used nonlinear wire analysis by soaking in Oldroyd 8-constant fluid under constant pressure gradient with help feed forward artificial neural networks (ANNs). The system partial differential equations generated process transformed into dimensionless ordinary equation. One salient features ANNs mathematical modeling exploring unsupervised error. A new scheme based on inverse multiquadric (IMQNNs) hybridization well-known genetic algorithms (GAs) sequential quadratic programming (SQP) obtain expeditious convergence, i.e., IMQNNs-GA-SQP. applicability problem investigated altering values dilatant constant, gradient, shear stress, pseudo-plastic outcome which form varying polymer thickness. Comparison highly accurate results shape error absolute errors obtained those reference solution, calculated using Adams numerical MATHEMATICA software, statistical such as root-mean-square error, Theil’s coefficient inequality, E-R 2 (error function determination), E-VAF (variance accounted for), E-NSE (Nash–Sutcliffe efficiency), mean box plot analyses, cumulative distributive through histogram also carried out research, guarantees effectiveness scheme.