The heat source layout optimization using deep learning surrogate modeling
- PDF / 6,212,810 Bytes
- 22 Pages / 595.224 x 790.955 pts Page_size
- 100 Downloads / 275 Views
RESEARCH PAPER
The heat source layout optimization using deep learning surrogate modeling Xiaoqian Chen1 · Xianqi Chen2 · Weien Zhou1 · Jun Zhang1 · Wen Yao1 Received: 6 February 2020 / Revised: 20 May 2020 / Accepted: 11 June 2020 © Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract In practical engineering, the layout optimization technique driven by the thermal performance is faced with a severe computational burden when directly integrating the numerical analysis tool of temperature simulation into the optimization loop. To alleviate this difficulty, this paper presents a novel deep learning surrogate-assisted heat source layout optimization method. First, two sampling strategies, namely the random sampling strategy and the evolving sampling strategy, are proposed to produce diversified training data. Then, regarding mapping between the layout and the corresponding temperature field as an image-to-image regression task, the feature pyramid network (FPN), a kind of deep neural network, is trained to learn the inherent laws, which plays as a surrogate model to evaluate the thermal performance of the domain with respect to different input layouts accurately and efficiently. Finally, the neighborhood search-based layout optimization (NSLO) algorithm is proposed and combined with the FPN surrogate to solve discrete heat source layout optimization problems. A typical two-dimensional heat conduction optimization problem is investigated to demonstrate the feasibility and effectiveness of the proposed deep learning surrogate-assisted layout optimization framework. Keywords Heat source layout optimization · Deep learning surrogate · Feature pyramid network · Neighborhood search
1 Introduction With the increasingly smaller size but higher power density of electronic devices, the problem of thermal management inside the overall system is becoming more and more Responsible Editor: Nestor V Queipo Wen Yao
[email protected] Xiaoqian Chen [email protected] Xianqi Chen [email protected] Weien Zhou [email protected] Jun Zhang [email protected] 1
National Innovation Institute of Defense Technology, Chinese Academy of Military Science, Beijing, 100000, China
2
College of Aerospace Science and Engineering, National University of Defense Technology, Changsha, 410073, China
serious. The objective of thermal management is to reduce the maximum temperature and improve the uniformity of heat distribution of the domain, so as to provide a good thermal environment and keep the operation consistency of components (Chen et al. 2016a). One effective approach to improve the thermal performance through passive cooling is to optimize the positions of the heat-generating components as implemented in Chen et al. (2016a, b, 2017) and Aslan et al. (2018). It can be regarded as a kind of component layout optimization problem driven by the thermal performance of the concerned system and generally defined as heat source layout optimization that treats the heat-generating components as heat so
Data Loading...
