Analyzing slip factor impacts on bio-convective micro-rotating nanofluids over a stretchable plate: An artificial neural network approach

The present research aims to develop the Levenberg-Marquardt learning algorithm with backpropagation neural networks (LMLA-BPNN) to investigate impact of thermal radiation and various slip effects on the magnetohydrodynamic (MHD) bio-convection flow of micro-rotating based nanofluid over a porous stretchable plate. To incorporate the effects of nanofluid, an external mechanism of inducing Brownian and thermophoresis motion is integrated. The mathematical model for the present study is formulated with relevant assumptions and then transformed into ordinary differential equations using appropriate similarity transformations. Utilizing the bvp4c technique, data is gathered for the LMLA-BPNN to controls temperature, linear and angular velocities, and nanofluid concentration profiles. These parameters are associated with the bio-convection micro-rotating fluid flow model. The proposed algorithm LMLA-BPNN is employed to evaluate the acquired current physical model performance in multiple scenarios and a correlation of the findings with a reference data set is performed to check the validity and efficiency of the proposed algorithm. Statistical tools such as state transition dynamics, mean square error, regression analysis, and error dynamic histogram investigations all successfully validate the suggested LMLA-BPNN for solving the current physical model. The practical applications of this study include real-time integration in smart HVAC systems, thermal energy storage solutions, the design of efficient thermal systems for microelectronics and biomedical devices, thermal regulation in bioreactors, enhancing the effectiveness of thermal therapies, separation and purification processes in chemical engineering, drug delivery systems, chemical sensors, and advanced material synthesis.