[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127079-en":3,"doc-seo-127079-105":30,"detail-sidebar-cat-0-en-105":92},{"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":20,"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},127079,5909887256941,"Levi","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Machine-Learning Enhanced Predictors for Accelerated Convergence of Partitioned Fluid-Structure Interaction Simulations","Stable partitioned techniques for simulating unsteady fluid-structure interaction (FSI) become computationally expensive when high added-mass effects are present. Existing acceleration strategies often rely on simple finite-difference extrapolation predictors, limiting robustness and efficiency. This study introduces a non-intrusive, data-driven predictor that couples reduced-order models for both solid and fluid subproblems to provide the initial guess for the next nonlinear time-step solve. Encoder-regressor-decoder architectures with adaptive updates improve extrapolation, yielding faster fixed-point convergence and overall speedups up to 3.2 versus classical predictor-based coupling.","Graphical Abstract  \nMachine-Learning Enhanced Predictors for Accelerated Convergence of Partitioned FluidStructure Interaction Simulations  \nTIBA Azzeddine, DAIRAY Thibault, DE VUYST Florian, MORTAZAVI Iraj, BERRO RAMIREZ Juan-Pedro  \narXiv :2405 .099  \nHighlights  \nMachine-Learning Enhanced Predictors for Accelerated Convergence of Partitioned FluidStructure Interaction Simulations  \nTIBA Azzeddine, DAIRAY Thibault, DE VUYST Florian, MORTAZAVI Iraj, BERRO RAMIREZ Juan-Pedro  \n• Novel predictor to accelerate convergence of fluid-structure interactions problems.  \n• Coupled solution of solid and fluid reduced models is used as the next initial guess.  \n• Reduced models take the form of encoder-regressor-decoder data-driven models.  \n• Online adaptation of the reduced models is used for more robust extrapolation.  \n• Faster convergence and speedups up to 3.2 versus classical-predictor based coupling.  \nMachine-Learning Enhanced Predictors for Accelerated Convergence of Partitioned Fluid-Structure Interaction Simulations  \nTIBA Azzeddinea , DAIRAY Thibaultb,c , DE VUYST Floriand , MORTAZAVI Iraja , BERRO  \nRAMIREZ Juan-Pedroe  \naM2N, CNAM, 2, Rue Conté, Paris, 75003, France  \nbManufacture Française des Pneumatiques Michelin, Place des Carmes-Dechaux, Clermont-Ferrand, 63000, France  \nc Centre Borelli, CNRS, Université Paris Saclay, ENS Paris Saclay, 4, Avenue des  \nSciences, Gif-sur-Yvette, 91190, France  \nd Université de Technologie de Compiègne, CNRS, Laboratory of Biomechanics and Bioengineering, Rue du docteur  \nSchweitzer, Compiègne, 60203, France  \ne Altair Engineering France, 5, Rue de la Renaissance, Antony, 92160, France  \nAbstract  \nStable partitioned techniques for simulating unsteady fluid-structure interaction (FSI) are known to be computationally expensive when high added-mass is involved. Multiple coupling strategies have been developed to accelerate these simulations, but often use predictors in the form of simple finite-difference extrapolations. In this work, we propose a non-intrusive data-driven predictor that couples reducedorder models of both the solid and fluid subproblems, providing an initial guess for the nonlinear problem of the next time step calculation. Each reduced order model is composed of a nonlinear encoder-regressor-decoder architecture and is equipped with an adaptive update strategy that adds robustness for extrapolation. In doing so, the proposed methodology leverages physics-based insights from high-fidelity solvers, thus establishing a physics-aware machine learning predictor. Using three strongly coupled FSI examples, this study demonstrates the improved convergence obtained with the new predictor and the overall computational speedup realized compared to classical approaches.  \nKeywords: Physically relevant reduced order model, Fluid-structure interaction, Partitioned approach, ROM-FOM coupling, Data-driven model, Fixed-point acceleration.  \n1. Introduction  \nEngineering applications involving Fluid-Structure Interaction (FSI) phenomena are numerous, and are present in various fields. This includes aeroelasticity, biomechanics, microfluidics, hydrodynamics and many more. Modeling these FSI problems is a challenging task due to the usually high complexity of the coupling between the solid system and the fluid system.  \nPhysics-based numerical simulations are considered as one of the leading options of modeling FSI problems, benefiting from years of advances in computational mechanics and from the increase of accessible computing power. These computations often have the goal of modeling the complicated coupling between the kinematics of a solid body and a fluid flow along with the mechanical loads associated with it. This results in very complicated problems, with nonlinearities present in both the fluid and the solid systems, in addition to the nonlinearities of the coupling itself. Furthermore, highly complex dynamics can be present due for example to the turbulent nature of the flow a","cbCaifxR0qsPv8FJ","https://ap.wps.com/l/cbCaifxR0qsPv8FJ","pdf",8971145,1,44,"English","en",105,"# Highlights\n# Abstract\n# 1. Introduction\n## FSI applications and modeling challenges\n## Numerical simulation approaches: monolithic vs partitioned\n## Partitioned coupling advantages","[{\"question\":\"Why are partitioned unsteady fluid-structure interaction simulations computationally expensive?\",\"answer\":\"They become costly when high added-mass effects are involved, which makes stable partitioned coupling require more expensive iterations and computations.\"},{\"question\":\"What predictor approach is proposed to accelerate convergence?\",\"answer\":\"A non-intrusive, data-driven predictor that couples reduced-order models of both the solid and fluid subproblems to generate the initial guess for the next time step.\"},{\"question\":\"How are the reduced-order models structured and made more robust?\",\"answer\":\"Each reduced-order model uses a nonlinear encoder-regressor-decoder data-driven architecture with an adaptive online update strategy to enhance robustness during extrapolation.\"}]","Machine-Learning Enhanced Predictors for Accelerated Convergence of Partitioned Fluid-Structure Interaction Simulations | PDF",1785936727,111,{"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":87,"head_meta":89,"extra_data":91,"updated_unix":28},"machine-learning-enhanced-predictors-for-accelerated-convergence-of-partitioned-fluid-structure-interaction-simulations","",{"@graph":36,"@context":86},[37,54,69],{"@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/machine-learning-enhanced-predictors-for-accelerated-convergence-of-partitioned-fluid-structure-interaction-simulations/127079/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"Why are partitioned unsteady fluid-structure interaction simulations computationally expensive?","Question",{"text":76,"@type":77},"They become costly when high added-mass effects are involved, which makes stable partitioned coupling require more expensive iterations and computations.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"What predictor approach is proposed to accelerate convergence?",{"text":81,"@type":77},"A non-intrusive, data-driven predictor that couples reduced-order models of both the solid and fluid subproblems to generate the initial guess for the next time step.",{"name":83,"@type":74,"acceptedAnswer":84},"How are the reduced-order models structured and made more robust?",{"text":85,"@type":77},"Each reduced-order model uses a nonlinear encoder-regressor-decoder data-driven architecture with an adaptive online update strategy to enhance robustness during extrapolation.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":46,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":46,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":46,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":46,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":46,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":46,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]