Heat source field inversion and detection based on physics-informed deep learning

被引：0
作者：
Chi, Yimeng [1 ]
Li, Mingliang [1 ]
Long, Rui [1 ]
Liu, Zhichun [1 ]
Liu, Wei [1 ]
机构：
[1] Huazhong Univ Sci & Technol, Sch Energy & Power Engn, Wuhan 430074, Peoples R China
来源：
INTERNATIONAL COMMUNICATIONS IN HEAT AND MASS TRANSFER | 2025年 / 164卷
关键词：
Physics-informed neural network; Heat source field inversion and detection; Multi-heat sources;
D O I：
10.1016/j.icheatmasstransfer.2025.108824
中图分类号：
O414.1 [热力学];
学科分类号：
摘要：
Heat source field inversion and detection (HSFID) has drawn increasing attention as the exponentially growing application for integrated circuits, which offers promising way for determining the system's unnormal operation condition. In the HSFID, embodying the physical constraints in the neural networks could significantly reduce the data demand for training and offer higher reconstruction accuracy. In present study, the physics-informed neural network (PINN) is employed to achieve the goal of HSFID. The problem of reconstructing the heat source field is transformed into the challenge of temperature field reconstruction. The PINN is employed to conduct the HSFID with various locations, shapes, sizes and power densities under multi-heat source configurations. For the twosource configuration, the heat source shape and position similarity (HSSPS) for detecting triangular heat sources is 98.9 %, meanwhile for four heat source configurations, the HSSPS is 93.5 %. In complex heat source systems where the location, shape, size and power density change randomly and simultaneously, the maximum temperature mean absolute error (TMAE) value is around 0.003 K, the maximum value of the temperature absolute error (M-TAE) value fluctuates in the range of 0.02 K, and the HSSPS is not less than 92 %.
引用
收藏
页数：14
相关论文
共 35 条
  • [1] Chen X., Chen X., Zhou W., Zhang J., Yao W., The heat source layout optimization using deep learning surrogate modeling, Struct. Multidiscip. Optim., 62, 6, pp. 3127-3148, (2020)
  • [2] Emam M., Ookawara S., Ahmed M., Thermal management of electronic devices and concentrator photovoltaic systems using phase change material heat sinks: experimental investigations, Renew. Energy, 141, pp. 322-339, (2019)
  • [3] Wu B., Kim D.-S., Han B., Palczynska A., Gromala P.J., Thermal deformation analysis of automotive electronic control units subjected to passive and active thermal conditions, International Conference on Thermal, Mechanical and Multi-Physics Simulation and Experiments in Microelectronics and Microsystems, pp. 1-6, (2015)
  • [4] Le Niliot C., Lefevre F., A method for multiple steady line heat sources identification in a diffusive system: application to an experimental 2D problem, Int. J. Heat Mass Transf., 44, 7, pp. 1425-1438, (2001)
  • [5] Yang C.-Y., The determination of two heat sources in an inverse heat conduction problem, Int. J. Heat Mass Transf., 42, 2, pp. 345-356, (1999)
  • [6] Shuai Y., Zhang X., Qing H., Tan H.-P., Inversion research on temperature field with nonlinear multiple heat source using I-DEAS, Yuhang Xuebao, 32, 9, pp. 2088-2095, (2011)
  • [7] Morimoto M., Fukami K., Zhang K., Fukagata K., Generalization techniques of neural networks for fluid flow estimation, Neural Comput. & Applic., 34, 5, pp. 3647-3669, (2022)
  • [8] Zhou X., Dong C., Zhao C., Bai X., Temperature-field reconstruction algorithm based on reflected sigmoidal radial basis function and QR decomposition, Appl. Therm. Eng., 171, (2020)
  • [9] Chen X., Gong Z., Zhao X., Zhou W., Yao W., A machine learning surrogate modeling benchmark for temperature field reconstruction of heat source systems. SCIENCE CHINA, Inf. Sci., 66, 5, (2023)
  • [10] Yang S., Yao W., Zhu L.-F., Ke L.-L., Predicting the temperature field of composite materials under a heat source using deep learning, Compos. Struct., 321, pp. 0263-8223, (2023)
1234