Intelligent computing technique based supervised learning for squeezing flow model

Abstract In this study, the unsteady squeezing flow between circular parallel plates (USF-CPP) is investigated through intelligent computing paradigm of Levenberg–Marquard backpropagation neural networks (LMBNN). Similarity transformation introduces fluidic system governing partial differential equations into nonlinear ordinary equations. A dataset generated based on fluid USF-CPP for LMBNN Runge–Kutta method by suitable variations Reynolds number and volume rate. To attain approximation solutions to different scenarios cases LMBNN, operations training, testing, validation are prepared then outcomes compared with reference data set ensure suggested model’s accuracy. The output discussed mean square error, dynamics state transition, analysis error histograms, regression illustrations.