Host: The Japan Society of Mechanical Engineers
Name : [in Japanese]
Date : October 12, 2019 - October 13, 2019
A Loop Heat Pipe (LHP) is a two-phase heat transfer device driven by capillary force. Many design parameters such as the shape and the working fluid affect the performance of the LHP, but it is difficult to select the best shape due to the complexity of the correlation and the time cost for analysis. In this study, in order to maximize the heat transport of the LHP, Bayesian optimization, which is one of the machine learning methods, is used to improve the efficiency of the work for optimizing the shape parameters of the LHP.
