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 is used for nonlinear wire coating analysis by soaking the wires in Oldroyd 8-constant fluid under a constant pressure gradient with the help of feed forward artificial neural networks (ANNs). The system of partial differential equations generated for the process of wire coating is transformed into a nonlinear dimensionless ordinary differential equation. One of the salient features of ANNs is the mathematical modeling of transformed equations by exploring the unsupervised error. A new scheme based on inverse multiquadric neural networks (IMQNNs) is used with a hybridization process of well-known genetic algorithms (GAs) and sequential quadratic programming (SQP) to obtain expeditious convergence, i.e., IMQNNs-GA-SQP. The applicability of the problem is investigated by altering the values of the dilatant constant, pressure gradient, shear stress, and pseudo-plastic constant, the outcome of which is in the form of varying polymer coating thickness. Comparison of highly accurate results in the shape of error analysis based on absolute errors of obtained results with those of the reference solution, calculated using the Adams numerical technique using MATHEMATICA software, statistical analysis such as root-mean-square error, Theil’s coefficient for inequality, E-R2 (error function based on the coefficient of determination), E-VAF (variance accounted for), E-NSE (Nash–Sutcliffe efficiency), mean absolute error, box plot analyses, and the cumulative distributive function through histogram analyses, is also carried out in this research, which guarantees the effectiveness of the used scheme.