[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122068-en":3,"doc-seo-122068-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},122068,8796095461564,"Liam","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","PLIC-Net - A Machine Learning Approach for 3D Interface Reconstruction in Volume of Fluid Methods","Accurate reconstruction of immiscible fluid-fluid interfaces from the volume fraction field is essential for geometric Volume of Fluid methods. A key challenge lies in selecting planes or higher-order shapes for interface reconstruction, where standard Piecewise Linear Interface Calculation may require costly optimization and tailored heuristics for richer geometries. This work evaluates a machine-learning alternative: a feed-forward deep neural network predicts the PLIC plane normal from volume fraction and phasic barycenter data on a 3×3×3 stencil, then translates the plane to enforce exact volume conservation. The proposed PLICNet is tested against LVIRA and ELVIRA in multiphase-flow simulations, showing cleaner breakup, fewer spurious planes, and lower computational cost.","arXiv :2408 .01383v1 [physics .comp-ph] 2 Aug 2024  \nPLIC-Net: A Machine Learning Approach for 3D Interface Reconstruction in Volume  \nof Fluid Methods  \nAndrew Cahalya,∗, Fabien Evrardb , Olivier Desjardinsa  \na Sibley School of Mechanical and Aerospace Engineering, Cornell University, Ithaca, 14853, NY, USA b Department of Aerospace Engineering, University of Illinois Urbana-Champaign, Urbana, 61801, Il, USA  \nAbstract  \nThe accurate reconstruction of immiscible fluid-fluid interfaces from the volume fraction field is a critical component of geometric Volume of Fluid methods. A common strategy is the Piecewise Linear Interface Calculation (PLIC), which fitsa plane in each mixed-phase computational cell. However, recent work goes beyond PLIC by using two planes or even a paraboloid. To select such planes or paraboloids, complex optimization algorithms as well as carefully crafted heuristics are necessary. Yet, the potential exists for a well-trained machine learning model to efficiently provide broadly applicable solutions to the interface reconstruction problem at lower costs. In this work, the viability of a machine learning approach is demonstrated in the context of a single plane reconstruction. A feed-forward deep neural network is used to predict the normal vector of a PLIC plane given volume fraction and phasic barycenter data in a 3 × 3 × 3 stencil. The PLIC plane is then translated in its cell to ensure exact volume conservation. Our proposed neural network PLIC reconstruction (PLICNet) is equivariant to reflections about the Cartesian planes. Training data is analytically generated with O(106 ) randomized paraboloid surfaces, which allows for the sampling a broad range of interface shapes. PLIC-Net is tested in multiphase flow simulations where it is compared to standard LVIRA and ELVIRA reconstruction algorithms, and the impact of training data statistics on PLIC-Net’s performance is also explored. It is found that PLIC-Net greatly limits the formation of spurious planes and generates cleaner numerical break-up of the interface. Additionally, the computational cost of PLIC-Net is lower than that of LVIRA and ELVIRA. These results establish that machine learning is a viable approach to Volume of Fluid interface reconstruction and is superior to current reconstruction algorithms for some cases.  \n© 2024. This manuscript version is made available under the CC-BY-NC-ND 4.0 license.  \n[http://creativecommons.org/licenses/by-nc-nd/4.0](http://creativecommons.org/licenses/by-nc-nd/4.0)  \nKeywords: Volume of Fluid, PLIC, Interface Reconstruction, Machine Learning  \n1. Introduction  \nThe accurate representation of the interface that separatesimmiscible fluids is a key challenge in the simulation of multiphase flows. The difficulty arises from needing to capture detailed interface features and handle topology changes robustly while also conserving volume. Out of the major approaches to this problem, interface capturing methods have shown a great ability to handle complex topology changes, such as in liquid atomization, by using an implicit interface representation. The Volume of Fluid (VOF) method (Hirtand Nichols, 1981) is a popular choice among interface capturing methods since it can be designed to be exactly volume conservative.  \nVOF starts by representing the phasic distribution using a binary indicator function, which assigns one of the fluid regions (e.g., the gas) a value of 0 and the other region (e.g., the liquid) a value of 1 . When discretized in a finite volume method, the normalized zeroth order spatial moment of  \n∗ Corresponding Author.  \nEmail address: [ajc428@cornell.edu](ajc428@cornell.edu) (Andrew Cahaly)  \nthe indicator function becomes the liquid volume fraction α, which represents in each cell the ratio of liquid volume to the volume of the cell. While each Eulerian grid cell possesses a volume fraction such that 0 ≤ α ≤ 1, cells with 0 \u003C α \u003C 1 have both phases present and must therefore contain the i","cbCaiiI8PmC0rOnw","https://ap.wps.com/l/cbCaiiI8PmC0rOnw","pdf",7842217,1,15,"English","en",105,"# Introduction\n## Volume of Fluid (VOF) and interface capturing\n## Piecewise Linear Interface Calculation (PLIC)\n## Existing reconstruction algorithms: LVIRA and ELVIRA","[{\"question\":\"What problem does PLICNet address in Volume of Fluid methods?\",\"answer\":\"PLICNet targets the reconstruction of immiscible fluid-fluid interfaces from the volume fraction field, specifically the selection of PLIC plane orientation needed for accurate geometric VOF simulations.\"},{\"question\":\"How does PLICNet generate the PLIC plane in a cell?\",\"answer\":\"It uses a feed-forward deep neural network to predict the PLIC plane normal from volume fraction and phasic barycenter data using a 3×3×3 stencil, then translates the plane to achieve exact volume conservation.\"},{\"question\":\"How does PLICNet compare with LVIRA and ELVIRA?\",\"answer\":\"In multiphase-flow simulations, PLICNet greatly reduces spurious planes, produces cleaner interface breakup, and lowers computational cost relative to LVIRA and ELVIRA, with performance also influenced by training data statistics.\"}]","PLIC-Net - A Machine Learning Approach for 3D Interface Reconstruction in Volume of Fluid Methods | PDF",1785808671,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"plic-net-a-machine-learning-approach-for-3d-interface-reconstruction-in-volume-of-fluid-methods","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/plic-net-a-machine-learning-approach-for-3d-interface-reconstruction-in-volume-of-fluid-methods/122068/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does PLICNet address in Volume of Fluid methods?","Question",{"text":75,"@type":76},"PLICNet targets the reconstruction of immiscible fluid-fluid interfaces from the volume fraction field, specifically the selection of PLIC plane orientation needed for accurate geometric VOF simulations.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does PLICNet generate the PLIC plane in a cell?",{"text":80,"@type":76},"It uses a feed-forward deep neural network to predict the PLIC plane normal from volume fraction and phasic barycenter data using a 3×3×3 stencil, then translates the plane to achieve exact volume conservation.",{"name":82,"@type":73,"acceptedAnswer":83},"How does PLICNet compare with LVIRA and ELVIRA?",{"text":84,"@type":76},"In multiphase-flow simulations, PLICNet greatly reduces spurious planes, produces cleaner interface breakup, and lowers computational cost relative to LVIRA and ELVIRA, with performance also influenced by training data statistics.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]