Artificial neural network investigation on Cattaneo-Christov flux and thermal-radiation effects on Sutterby Hybrid-Nanoliquid: Application of hybrid nanoparticles in heat transfer

This work investigates the significance of thermal radiation on a dusty Sutterby hybrid nanofluid with heat generation using the Levenberg-Marquardt technique with AI integration. A data-driven methodology is used to calibrate the Levenberg–Marquardt algorithm in each phase. This algorithm is closely related to artificial neural network machine learning technology. Heat transport properties are inspected using the Cattaneo-Christov heat flow model. In complex thermal management systems, the Cattaneo-Christov model has significant applications when applied to the two-phase flow of a dusty Sutterby hybrid nanofluid with heat radiation. Enhancing heat transmission in energy systems, industrial cooling systems, biomedical devices, and aeronautical engineering is made possible by this approach. Improved knowledge of non-Fourier heat conduction in complicated fluids is useful for oil recovery, nuclear reactor safety, and microelectronic cooling. Furthermore, for next-generation engineering applications like the creation of smart materials, nanofluid-based heat exchangers, and efficient thermal insulation, artificial neural networks can be utilized to accurately predict thermal and flow parameters. Regression presentation, fitness outline, state transition, and histogram error further support the robustness and reliability of the solver LMB-NN. The effectiveness of the recommended approach is demonstrated by the high convergence between the generated solutions and reference solutions using an integrated solver LMB-NN, where the accuracy level is realized in the regions of 10 − 7 to 10 − 9 .

Перевод пока недоступен