Swarm-based multi-objective optimization of double-layered microchannel heat sink with hybrid solid-porous ribs

The current article focuses on the thermal and hydraulic optimization of a double-layered microchannel with hybrid solid-porous ribs. Therefore, for both upper and lower layers, solid-porous ribs, having different thickness ratios of porous and solid, are considered. The ratio of solid-porous thickness in the upper and lower layers and Reynolds number variations are taken into account as design variables. The present study is conducted to find an optimum design by which not only thermal performance improves, but also power consumption reduces. At the initial step, the double-layer microchannel is simulated using artificial neural network. The second step involves the application of the optimum network and the microchannel inputs for minimizing the thermal resistance and the power consumption single-objective and multi-objective type's optimization problems are solved. The two mentioned optimization problems in the proposed strategy are targeted using four swarm-based algorithms. Results indicated that the designed neural network has a maximum error of 4% for producing the desired outputs. Moreover, the single-objective optimization of the second stage showed that by the porous ratios of 0.19 and 1 for the upper and lower layers, respectively, and Reynolds number of 578.7, the minimum values of pressure drop and overall thermal resistance are achieved.