Gaussian process optimization of phase change material heat sink design

Abstract

Thermal management strategies based on phase change materials (PCMs) offer promising alternatives to conventional approaches, owing to their ability to absorb transient heat flows by melting. However, the design of PCM heat sinks is challenging due to the nonlinear interactions between heat flow and phase change during melting and solidification. This paper presents the design optimization of PCM heat sinks using a Gaussian Process (GP) method. We show that the GP method offers a significant decrease in computational intensity compared to conventional approaches used for optimization. We apply our method to optimize the design of a PCM-integrated heat sink for a gallium nitride (GaN) device that operates under a pulse train heat profile. Field’s metal-infused copper foam is used as the PCM. We used a reduced order model (ROM) for the PCM-integrated device, which is validated through experimental measurements and finite element simulations. We coupled the ROM with the GP optimizer to determine PCM heat sink design parameters, including geometric dimensions and the composition of the composite PCM, which minimizes both the GaN maximum junction temperature and junction temperature swing. We tested the GP optimizer under various conditions, encompassing GaN device power levels ranging from 1 to 4 W, pulse widths spanning 1 to 10 s, and duty cycles ranging from 10 to 90%. The GP optimizer produced nearly identical results to particle swarm optimization, with a mean absolute error <0.2 °C for optimal thermal performance and a reduction in computational time of 39×. Overall, our design method offers a computationally efficient approach to optimizing PCM-integrated heat sinks for the transient thermal management of electronic devices.