Intelligent computing Levenberg Marquardt paradigm for the analysis of Hall current on thermal radiative hybrid nanofluid flow over a spinning surface

The aim of this work is to construct a supervised learning neural network algorithm termed as LM-SLNNAs (Levenberg Marquardt) for the influence of Hall current on Radiation Nanofluidic flow on a spinning Disk (IHC-RNF-OSD). The effects of a magnetic field and heat radiation have also been considered in order to better understand of the flow and energy details. Hybrid nanofluid, comprising Copper (Cu) and Titanium Dioxide (TiO2) in water, is utilized. The intended IHC-RNF-OSD is originally represented as a system of PDEs, which may be transformed into a system of non-linear ODEs using the appropriate transformation. To construct a dataset of the proposed model for six scenarios, the bvp4c numerical technique is used. These scenarios may produce by adjusting the physical variations of the model such as hall parameter, thermal radiation parameter, Prandtl number, etc. LM-SLNNAs executed operations on training, testing, and certification to data-samples of IHC-RNF-OSD model. Comparing the conventional result and the outputs of the suggested solver for the proposed model, the statistical analysis such as M.S.E (mean squared error), histograms plots, regression and absolute error analysis has used which confirmed the efficiency of the LM-SLNNAs. Furthermore, the result demonstrates that the radial skin frictional factor is increased for the Hall parameter; however, the transverse frictional component displays the inverse situation of this. The major goal of this research is to use artificial intelligence to model and predict the properties of nanofluid/hybrid nanofluid, choose the optimal ANN structure from a group of predicted structures, and control time and cost by predicting the ANN with the least error.