Numerical simulation and optimization with artificial neural network of two-phase nanofluid flow in a circular heatsink with cylindrical pin-fins

This paper designs and simulates a circular heatsink (HSK) with a novel geometry. A number of cylindrical pin-fins (PIFs) are placed on the HSK. The flow of alumina/water nanofluid (NF) enters from the middle of the HSK, passes through the PIFs, goes toward the outer curvature, and exits from the HSK. Constant thermal flux is applied at the bottom of the HSK. The variables include the length of PIFs changing from 5 to 20 mm, the distance between PIFs varying from 10 to 15 mm, and the diameter of PIFs changing from 1 to 4 mm. The effect of these variables on the maximum of the HSK, the average temperature (T-AV) of the HSK is examined. Finally, numerical optimization is done on the results using machine learning and artificial intelligence in terms of the minimum HSK temperature. The flow of NF is simulated using a two-phase model and the finite element method (FEM). An increment in the length of the PIFs from 5 to 20 reduces the T-AV by 11.42 K. An increment in the diameter of the PIFs from 1 to 4 reduces the T-AV of the HSK by 5.98 K.

Automated summary

This paper presents the design and simulation of a novel circular heatsink with cylindrical pin-fins. The effects of variables such as pin-fins length, distance between pin-fins, and pin-fins diameter on the maximum and average temperature of the heatsink are investigated. The results are further optimized using machine learning and artificial intelligence to achieve the minimum heatsink temperature. The flow of nanofluid is simulated using a two-phase model and the finite element method. Increasing the length of pin-fins from 5 to 20 mm decreases the average temperature by 11.42 K. Increasing the diameter of pin-fins from 1 to 4 mm reduces the average temperature of the heatsink by 5.98 K.