用视觉图像分析气泡变化，快速判断沸腾状态转换。
A novel visual data-based diagnostic approach for estimation of regime transition in pool boiling
- 通过图像特征匹配和气泡区域分割，构建视觉相似性指标。
- 指标与实测传热系数高度相关，能准确识别核态沸腾起始和临界热流密度前兆。
- 无需复杂测量，适合实时监测沸腾过程，适用于多表面场景。
本研究提出一种新型视觉指标——视觉相似性指数（IVS），仅基于视觉数据定性表征沸腾传热状态。IVS结合SIFT特征匹配的形态相似性与基于Mask R-CNN的气泡区域估计的物理相似性，捕捉气泡形状、大小及分布的关键变化，反映传热机制转变。利用高帧率图像对抛光铜和多孔铜泡沫表面的池沸腾过程进行测试，验证了该方法的普适性。IVS与由实测传热系数导出的等效指标Φ表现出强相关性，可靠检测核态沸腾起始及接近临界热流密度（CHF）的状态。针对实测传热系数变化精度受限的问题，进一步分析了IVS对表面过热度的敏感性，强化其可信度。该指标具备快速、非侵入式优势，适用于相变传热中的实时图像诊断，具有广泛应用前景。
原文摘要 · Abstract (English)
This study introduces a novel metric, the Index of Visual Similarity (IVS), to qualitatively characterize boiling heat transfer regimes using only visual data. The IVS is constructed by combining morphological similarity, through SIFT-based feature matching, with physical similarity, via vapor area estimation using Mask R-CNN. High-speed images of pool boiling on two distinct surfaces, polished copper and porous copper foam, are employed to demonstrate the generalizability of the approach. IVS captures critical changes in bubble shape, size, and distribution that correspond to transitions in heat transfer mechanisms. The metric is validated against an equivalent metric, $Φ$, derived from measured heat transfer coefficients (HTC), showing strong correlation and reliability in detecting boiling regime transitions, including the onset of nucleate boiling and proximity to critical heat flux (CHF). Given experimental limitations in precisely measuring changes in HTC, the sensitivity of IVS to surface superheat is also examined to reinforce the credibility of IVS. IVS thus emerges as a powerful, rapid, and non-intrusive tool for real-time, image-based boiling diagnostics, with promising applications in phase change heat transfer.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。