A machine learning surrogate modeling benchmark for temperature field reconstruction of heat source systems

Temperature field reconstruction of heat source systems (TFR-HSS) with limited monitoring sensors occurred in thermal management plays an important role real time health detection system electronic equipment engineering. However, prior methods common interpolations usually cannot provide accurate performance as required. In addition, there exists no public dataset for widely research to further boost the and engineering applications. To overcome this problem, work develops a machine learning modelling benchmark TFR-HSS task. First, task is mathematically modelled from real-world problem four types numerically modellings have been constructed transform into discrete mapping forms. Then, proposes set methods, including general deep advance state-of-the-art over temperature reconstruction. More importantly, novel dataset, namely Field Reconstruction Dataset (TFRD), evaluate these Finally, analysis typical given on TFRD, which can be served baseline results benchmark.