Quantum neural network-based modeling of radiative magneto-ternary nanofluid flow over a porous stretching surface with enhanced thermal transport analysis

The research studied how nonlinear fluid mechanics affects motion and heat transfer combined phase mix on porous surfaces, with A l 2 ⁢ O 3 − C u − T i O 2 / H 2 ⁡ O nanofluids moving at various rates to simulate the presence of a stretched porous surface. It will be important to include nonlinear radiation, viscous dissipation, and suction/injection effects in this investigation. To model transport processes in the examined material systems a novel framework based on quantum intelligent models (inspired by quantum computing and machine learning using Bayesian regularization) was developed and validated. The equations governing the momentum and energy equations were transformed from nonlinear PDEs into ordinary differential equations with similar transformations, then solved numerically using the bvp4c function of Matlab. The QNN-BRM approach was used for prediction models. The QNN-BRM architecture incorporates feature encoding, superposition states, rotation-gate operations, and provides significant accuracy through its utilization of Bayesian regularization. All of these findings support the conclusion that the magnetic field strength parameter, Eckert number, radiation strength parameter, and suction parameter greatly impacts the motion and temperature profiles of the fluid flow within the porous substrate. Increased suction parameter significantly increase local Nusselt number due to enhancing velocity boundary thickness while increasing thermal boundary thickness at higher magnetic fields. The proposed ternary A l 2 ⁢ O 3 − C u − T i O 2 / H 2 ⁡ O hybrid or mono/bi-nanofluid have exhibited superior heat transfer than either Mono or Hybrid Nanofluid under alike test conditions. Proposed QNN-BRM Predictor has produced excellent agreement with Numerical Solutions yielding RMSE 1 ⁢ 0 − 6 , MAE 1 ⁢ 0 − 6 and no bias (MBE 1 ⁢ 0 − 8 ) thus proving to be a reliable Non-linear Thermal Transport Model.