Off-centred stagnation controlled strategy mechanism on heat transfer aspects of chemically reactive non-Newtonian nanofluid

Heat transfer is an essential component of engineering systems, impacting production, cooling, and energy efficiency. An effective method for forecasting intricate nonlinear heat transport behaviours without the need for explicit mathematical models is the artificial neural network. Artificial neural networks can precisely predict thermal conductivity, heat flow, and temperature distribution by training on simulated or experimental data. In view of this, the current study employs an artificial neural network to investigate the effects of an off-centred stagnation-controlled strategy mechanism on a non-Newtonian chemically reactive nanofluid. When evaluating the mass and heat transport of fluid flow, the importance of both active and passive control of nanoparticles is considered. It is designed to monitor the numerical approximation of the heat transfer rate for different parameters in both control scenarios through testing, training, and validation. The results indicate a substantial correlation between the testing and training data sets, yielding mean square error values of 1.7708e-11 and 7.6175e-15 for the heat sink/source and Brownian motion parameters, respectively, in the active control scenario. Mean square error values for the heat source/sink and Brownian motion parameters in the passive control scenario were 5.4465e-14 and 6.7659e-11, indicating a strong match between the testing and training data sets.