arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2305.02622physics.flu-dyncs.LG
收藏

基于条件生成对抗网络的临界热流密度诊断

Critical heat flux diagnosis using conditional generative adversarial networks

Pohang University of Science and Technology (POSTECH)(浦项科技大学(POSTECH));Seoul National University(首尔大学)

UngJin Na, Moonhee Choi, HangJin Jo

AI总结:

针对临界热流密度(CHF)识别难、高分辨率热数据获取成本高的问题,本研究提出基于条件生成对抗网络(cGANs)的图像转换方法,利用流动沸腾实验的配对图像重构CHF工况热数据,为CHF诊断提供高效方案。

摘要:

临界热流密度(CHF)是高热通量热工水力系统所采用的沸腾传热过程中的关键安全边界。识别CHF对于防止设备损坏、保障系统整体安全至关重要,但由于该现象的复杂性,这项工作颇具挑战性。为深入理解这一复杂现象,学界已设计出多种方法,但高分辨率数据的获取受限于所需的大量资源消耗。本研究提出了一种数据驱动的图像到图像转换方法,利用条件生成对抗网络(cGANs)重构CHF工况下沸腾系统的热数据。该监督学习过程依赖配对图像,其中包含从流动沸腾实验中获取的全反射可视化结果和红外测温测量数据。我们提出的方法不仅有望为相界面动力学与热分布之间的关联提供证据,还能简化红外热成像相关的繁琐耗时的实验搭建和数据缩减流程,从而为CHF诊断提供一种有效解决方案。

英文摘要:

The critical heat flux (CHF) is an essential safety boundary in boiling heat transfer processes employed in high heat flux thermal-hydraulic systems. Identifying CHF is vital for preventing equipment damage and ensuring overall system safety, yet it is challenging due to the complexity of the phenomena. For an in-depth understanding of the complicated phenomena, various methodologies have been devised, but the acquisition of high-resolution data is limited by the substantial resource consumption required. This study presents a data-driven, image-to-image translation method for reconstructing thermal data of a boiling system at CHF using conditional generative adversarial networks (cGANs). The supervised learning process relies on paired images, which include total reflection visualizations and infrared thermometry measurements obtained from flow boiling experiments. Our proposed approach has the potential to not only provide evidence connecting phase interface dynamics with thermal distribution but also to simplify the laborious and time-consuming experimental setup and data-reduction procedures associated with infrared thermal imaging, thereby providing an effective solution for CHF diagnosis.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑