Heat transfer analysis in the engine‐based oil‐based hybrid nanofluid flow between two spinning disks: Probed by artificial neural network

Abstract A time‐dependent mixed convective hybrid nanofluid (HNF) ( /Engine oil) flow between two spinning disks is considered. The physical problem is modeled and transformed into a non‐dimensional ordianary differential equation system to reduce the complexity. A modified Devi and Devi's model is utilized for the nanofluid properties. The cylindrical shape nanoparticles are considered for the analysis of the various pertinent parameters. The base fluid is considered as the engine oil to briefly explain its thermal behavior. One of the famous optimization algorithms Levenberg–Marquardt is used to train the artificial neural network with the data achieved from the numerical results to analyze the various states of the HNF. The results for the state variables as well as nanoparticle shapes are displayed through graphs and tables. The enhancement of the expansion parameter () causes to augment, then drop and augment again the velocity gradient with the increasing distance between the disks. The temperature of the fluid initially drop and then enhances with the rising strength of (). The rising concentration of the nanomaterial associated with the higher values of volume fraction parameter () enhances the temperature distribution of the HNF. The results obtained show that the smaller nanoparticles concentration will keep the engine at a lower state of temperature. The results are validated through graphs in each case by providing the validation and absolute error graphs.