AI-powered computational analysis of dynamic responses in a vibrating Riga sensor within a reactive platinum -cerium oxide-water mixture

In this study, dynamic responses within a vertically extended vibrating Riga channel sensor immersed in a reactive hybrid nanofluid (HNF)-a mixture containing radioactive platinum, cerium oxide, and water-are analyzed through advanced artificial intelligence (AI)-based computational analysis using artificial neural networks (ANNs). The physical setup includes a static right wall and a left wall subjected to momentum and thermal vibrations (impulsive, cosinusoidal, and sinusoidal). The flow scenario is mathematically represented by time-dependent partial differential equations. A closed-form solution for the flow-regulating equations is derived using the Laplace transform (LT) method. The study thoroughly examines the influence of various critical parameters on the model’s functions and quantities, presenting the results in graphical and tabular forms. Our findings indicate that an intensification in the modified Hartmann number significantly reduces flow velocity within the Riga channel. An extended width of magnets and electrodes reduces flow velocity across the channel for both fluid types. The flow velocity is higher for cosinusoidal wall motion (CWM) than for impulsive wall motion (IWM) and sinusoidal wall motion (SWM). HNF maintains a lower temperature than nanofluid (NF), with the rate of heat transfer (RHT) at the vibrating wall consistently higher for HNF. The study uses an advanced AI approach, specifically an ANN, for accurate shear stress (SS) and RHT assessments. The proposed algorithm achieves 100 % accuracy for SS prediction in testing and 99.94 % in cross-validation, and 100 % for RHT in testing with 98.64 % in cross-validation. These insights have potential applications in chemical processing, environmental monitoring, and advanced manufacturing. [Display omitted] •This study examines the dynamics of an EM-reactive water-based hybrid nanofluid with Pt-CeO₂ in a vibrating Riga channel.•The study explores how the hybrid nanofluid responds to sudden pressure gradients and the impact of electromagnetic forces.•The model incorporates the integrated effects of magnetization and electromagnetic radiation.•We utilize the Laplace transform (LT) technique to obtain analytical expressions for the flow variables in our model.•We employ advanced AI-driven analysis with ANNs to accurately predict critical flow characteristics and metrics.