Search

This article presents the significance of using different sizes and positions of IC (Integrated Circuit) chips that are mounted on substrates of different materials. 1631The ICs are cooled by forced convection in a horizontal wind tunnel. COMSOL Multiphysics 5.4 solve the IC chip cooling problem by selecting a conjugate heat transfer module with laminar flow. FR4, ba-kelite, single and multi-layer copper clad boards are used as substrate materials. Numerical simulations are performed for FR4, bakelite with a constant heat flux of 5000 W/m², at 2.5 m/s air velocity. In contrast, single and multi-layer copper clad boards are studied for 10000 W/m² with 1.5 m/s air velocity. The prime objective of this research is to use adequate size and placement of chips generating high heat fluxes for enhanced heat transfer. Results showed that larger chips placed at bottom rows and sequentially decreasing sizes in the subsequent rows for the same overall input for high substrate thermal conductivity give more heat dissipation. Among all configurations A0 - F considered in the study, case E provides minimum tempera-ture using single and multi-layer copper clad boards. In addition to modification of chip sizes, geometric spacing of X1/X2 = 1.8 results in lower maximum temperature. [ABSTRACT FROM AUTHOR]

This paper explores the use of machine learning algorithms, such as XGBoost, random forest regression, support vector machine regression, and artificial neural network (ANN), which are employed for predicting temperatures of rectangular silicon heaters with dummy elements. A combination of these machine learning algorithms can predict better results over individual algorithm. Silicon heaters are equipped on an FR4 substrate board for cooling under forced convection in a horizontal channel. COMSOL Multiphysics 5.4 software is used for all the three-dimensional numerical simulations. Heat transfer at the solid and fluid interface is studied using a module based on conjugate heat transfer and nonisothermal fluid flow. Dummy elements are coupled with heated sources to evaluate heat transfer and analyze the flow of fluid. The study is performed with 2.5 m/s velocity and a uniform heat flux of 5000 W/m2. The study is aimed at predicting and comparing results of support vector regression (SVR), ensemble learning with ANN to explore optimal configuration. Results indicate an agreement of less than 10% between the simulated and predicted temperatures. It is also found that SVR has given the best results compared with XG Boot and ANN when analyzed individually. The programming for these algorithms is performed using the Python programming language. [ABSTRACT FROM AUTHOR]