Pablo Salgado Sánchez, Fernando Varas, Jeff Porter, Dan Gligor
{"title":"Optical Processing of Melting PCM Bridges in Microgravity Using SVD and ANNs","authors":"Pablo Salgado Sánchez, Fernando Varas, Jeff Porter, Dan Gligor","doi":"10.1007/s12217-025-10166-8","DOIUrl":null,"url":null,"abstract":"<div><p>Both Singular Value Decomposition (SVD) and Artificial Neural Networks (ANNs) can be powerful tools for image processing. Here they are applied in the context of the “Effect of Marangoni Convection on Heat Transfer in Phase Change Materials” (MarPCM) microgravity experiment [Porter et al. (Acta Astronautica 210, 212–223, 2023)], which investigates the use of thermocapillary (Marangoni) convection to expedite melting of organic Phase Change Materials (PCMs) in cuboidal and cylindrical domains. The processing of the cylindrical “melting bridge” experimental images is particularly challenging due to the converging lens effect caused by the curved interface and the refractive index of the liquid PCM. A combination of SVD and ANNs is used to propose an algorithm to process these images. The network is trained on a set of synthetic images of the melting bridge, generated via ray-tracing [Martinez et al. (Advances in Space Research 72, 1915–1928, 2023)] then projected onto the eigenmodes associated with the largest singular values of the image database, which includes snapshots of the melting process in all representative cases. Two optimal algorithm architectures are described, characterized by the number of SVD modes considered in the projection and the hyperparameters of the ANN. The performance of the algorithm is analyzed in terms of its ability to associate images with the correct liquid fraction. The processing strategy is tested by applying it to images obtained from ground experiments using the scientific prototype of the MarPCM cuboidal cell.</p></div>","PeriodicalId":707,"journal":{"name":"Microgravity Science and Technology","volume":"37 1","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s12217-025-10166-8.pdf","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Microgravity Science and Technology","FirstCategoryId":"5","ListUrlMain":"https://link.springer.com/article/10.1007/s12217-025-10166-8","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, AEROSPACE","Score":null,"Total":0}
引用次数: 0
Abstract
Both Singular Value Decomposition (SVD) and Artificial Neural Networks (ANNs) can be powerful tools for image processing. Here they are applied in the context of the “Effect of Marangoni Convection on Heat Transfer in Phase Change Materials” (MarPCM) microgravity experiment [Porter et al. (Acta Astronautica 210, 212–223, 2023)], which investigates the use of thermocapillary (Marangoni) convection to expedite melting of organic Phase Change Materials (PCMs) in cuboidal and cylindrical domains. The processing of the cylindrical “melting bridge” experimental images is particularly challenging due to the converging lens effect caused by the curved interface and the refractive index of the liquid PCM. A combination of SVD and ANNs is used to propose an algorithm to process these images. The network is trained on a set of synthetic images of the melting bridge, generated via ray-tracing [Martinez et al. (Advances in Space Research 72, 1915–1928, 2023)] then projected onto the eigenmodes associated with the largest singular values of the image database, which includes snapshots of the melting process in all representative cases. Two optimal algorithm architectures are described, characterized by the number of SVD modes considered in the projection and the hyperparameters of the ANN. The performance of the algorithm is analyzed in terms of its ability to associate images with the correct liquid fraction. The processing strategy is tested by applying it to images obtained from ground experiments using the scientific prototype of the MarPCM cuboidal cell.
奇异值分解(SVD)和人工神经网络(ann)都是图像处理的有力工具。在这里,它们被应用于“Marangoni对流对相变材料传热的影响”(MarPCM)微重力实验[Porter等人[Acta Astronautica 210, 212-223, 2023]]的背景下,该实验研究了使用热毛细(Marangoni)对流加速有机相变材料(pcm)在立方体和圆柱形区域的熔化。由于液态PCM的弯曲界面和折射率引起的会聚透镜效应,使得圆柱形“熔化桥”实验图像的处理尤其具有挑战性。将奇异值分解与人工神经网络相结合,提出了一种图像处理算法。该网络在一组通过光线追踪生成的熔化桥的合成图像上进行训练[Martinez等人[Advances in Space Research 72, 1915-1928, 2023]],然后将其投影到与图像数据库的最大奇异值相关的特征模式上,其中包括所有代表性案例中熔化过程的快照。描述了两种最优算法架构,其特征是投影中考虑的奇异值分解模式的数量和人工神经网络的超参数。根据将图像与正确的液体分数相关联的能力,分析了该算法的性能。将该处理策略应用于利用MarPCM立方单元科学样机的地面实验图像,对其进行了验证。
期刊介绍:
Microgravity Science and Technology – An International Journal for Microgravity and Space Exploration Related Research is a is a peer-reviewed scientific journal concerned with all topics, experimental as well as theoretical, related to research carried out under conditions of altered gravity.
Microgravity Science and Technology publishes papers dealing with studies performed on and prepared for platforms that provide real microgravity conditions (such as drop towers, parabolic flights, sounding rockets, reentry capsules and orbiting platforms), and on ground-based facilities aiming to simulate microgravity conditions on earth (such as levitrons, clinostats, random positioning machines, bed rest facilities, and micro-scale or neutral buoyancy facilities) or providing artificial gravity conditions (such as centrifuges).
Data from preparatory tests, hardware and instrumentation developments, lessons learnt as well as theoretical gravity-related considerations are welcome. Included science disciplines with gravity-related topics are:
− materials science
− fluid mechanics
− process engineering
− physics
− chemistry
− heat and mass transfer
− gravitational biology
− radiation biology
− exobiology and astrobiology
− human physiology