Temperature prediction of heat sources using machine learning techniques

Abstract

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.

LBM curved boundary treatments for pulsatile flow on convective heat transfer and friction factor in corrugated channels

“…Durgam et al used machine learning algorithms to predict temperatures of rectangular silicon heaters with dummy elements for cooling under forced convection. 35 The paper highlights the importance of accurate temperature prediction for designing efficient cooling systems and proposes the implementation of machine learning algorithms to improve the accuracy of these predictions. This research compares the findings of support vector regression, ensemble learning with artificial neural networks, and XG Boost, and concludes that a combination of these machine learning algorithms can predict temperatures more accurately than any one of them.…”

Computational cooling performance of electronic chips on printed circuit boards

“…They proposed artificial neural network as alternative tool to CFD. Durgam et al [13,14,15,16] have used machine learning algorithms viz. support vector regression, XG Boost, random forest regression, and artificial neural network as an alternative to simulation software for cooling of heaters with dummy components on PCB under forced convection.…”

Study of Substrate Conductance Effect on Cooling of Electronic Components

“…Experimental results and numerical predictions for validation of heater temperatures on different substrates for electronic components cooling are available in Durgam et al (2019Durgam et al ( , 2020b; Durgam (2021). The findings of simulation results of temperatures of heated blocks are compared with the temperature results of machine learning methods as a viable option for determining temperatures of heated modules Durgam et al (2022Durgam et al ( , 2020aDurgam et al ( , 2021. Jaluria et al (2020) have presented steady and transient heat transfer from data centers for its thermal management and reduced energy consumption by optimizing the cooling strategy.…”