[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119005-en":3,"doc-seo-119005-105":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},119005,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","Aerodynamic shape optimisation using a machine learning-augmented turbulence model","Aerodynamic shape optimisation relies on CFD analyses but turbulence-model inaccuracies can severely limit reliability in complex flows with flow separation, especially under off-design conditions. This work presents a steady-state RANS-based optimisation strategy that augments turbulence modelling with machine learning. The FIML framework infers turbulence-model discrepancies from high-fidelity inverse problems across multiple shapes and flow conditions, then generalises the discrepancy fields to unseen cases using ML (e.g., neural networks). Proof-of-concept uses DNS on parameterised periodic hills to augment the SST model, compared with the Wilcox model, with validation via hybrid RANS-LES IDDES against DNS. Results show strong optimisation sensitivity to turbulence-model choice and substantially higher drag reduction with improved agreement to IDDES predictions.","This is a repository copy of Aerodynamic shape optimisation using a machine learningaugmented turbulence model.  \nWhite Rose Research Online URL for this paper:  \n[https://eprints.whiterose.ac.uk/214493/](https://eprints.whiterose.ac.uk/214493/)  \n[Version: Accepted Version](Version: Accepted Version)  \nProceedings Paper:  \nBidar, O., He, P., Anderson, [S. orcid.org/0000-0002-7452-5681](S. orcid.org/0000-0002-7452-5681) et al. (1 more author)(2024) Aerodynamic shape optimisation using a machine learning-augmented turbulence model. In: AIAA SCITECH 2024 Forum. AIAA SCITECH 2024 Forum, 08-12 Jan 2024, Orlando, FL, USA. American Institute of Aeronautics and Astronautics . ISBN 9781624107115  \n[https://doi.org/10.2514/6.2024-1231](https://doi.org/10.2514/6.2024-1231)  \n© 2024 The Authors. Except as otherwise noted, this author-accepted version of a paper published in AIAA SCITECH 2024 Forum is made available via the University of Sheffield Research Publications and Copyright Policy under the terms of the Creative Commons Attribution 4.0 International License (CC-BY 4.0), which permits unrestricted use, distribution and reproduction in any medium, provided the original work is properly cited. To view a copy of this licence, visit [http://creativecommons.org/l](http://creativecommons.org/l)icenses/by/4.0/  \nReuse  \nThis article is distributed under the terms of the Creative Commons Attribution-NonCommercial (CC BY-NC) licence. This licence allows you to remix, tweak, and build upon this work non-commercially, and any new works must also acknowledge the authors and be non-commercial. You don’t have to license any derivative works on the same terms. More information and the full terms of the licence here: [https://creativecommons.org/licenses/](https://creativecommons.org/licenses/)  \nTakedown  \nIf you consider content in White Rose Research Online to be in breach of UK law, please notify us by  \nemailing [eprints@whiterose.ac.uk](eprints@whiterose.ac.uk) including the URL of the record and the reason for the withdrawal request.  \n[eprints@whiterose.ac.uk](eprints@whiterose.ac.uk)[ ](eprints@whiterose.ac.uk)[https://eprints.whiterose.ac.uk/](https://eprints.whiterose.ac.uk/)  \nAerodynamic Shape Optimisation Using a Machine Learning-augmented Turbulence Model  \nOmid Bidar ∗1, Ping He†2, Sean Anderson‡1, and Ning Qinğ1  \n1 The University of She􀀞eld, Western Bank, She􀀞eld, S10 2TN, UK  \n2 Iowa State University, Ames, Iowa, 50011, USA  \nThis paper presents an aerodynamic shape optimisation approach that utilises machine learning techniques to augment the turbulence model for the steady-state Reynolds-averaged Navier-Stokes (RANS) simulations􀀖which are prone to inaccuracies for complex 􀀝ows involving phenomena such as separation. We employ the 􀀜eld inversion and machine learning (FIML) approach which infers model discrepancies by solving a number of inverse problems (fordi􀀛erent shapes and/or 􀀝ow conditions) given some high-􀀜delity data, and uses machine learning (such as neural networks) to generalise the discrepancy 􀀜elds for unseen cases. As a proof-of-concept we use direct numerical simulation (DNS) data for a set of parameterised periodic hills to augment the two-equations 􀀺 − 􀁬 SST model using FIML, then incorporating it in the CFD solver for aerodynamic shape optimisation where the cost function is the drag minimisation. To illustrate the inherent optimisation sensitivity to the choice of turbulence model, we also use the Wilcox  \n􀀺 − 􀁬 model for comparison. Once the optimal shapes are achieved for the di􀀛erent turbulence models, we propose using the hybrid RANS-LES improved delayed detached eddy simulations (IDDES) to validate the 􀀝ow predictions, which in turn is validated against the available DNS data. Results highlight the sensitivity of optimisation to the turbulence model in the presence of  \n􀀝ow separation, and the FIML-augmented 􀀺 −􀁬 SST model is able to achieve much higher drag reduction (20 .8 − 25 . 3%) with fair agreeme","cbCaisIyWrDekNSP","https://ap.wps.com/l/cbCaisIyWrDekNSP","pdf",2357249,1,18,"English","en",105,"# Introduction\n## Problem background: turbulence modelling limits in shape optimisation\n## CFD optimisation with RANS vs LES/DNS\n## Proposed approach: ML-augmented RANS via FIML","[{\"question\":\"Why are standard RANS-based aerodynamic shape optimisation methods limited for complex flows?\",\"answer\":\"RANS turbulence models have documented deficiencies for complex flow phenomena such as separation, making them unreliable in those scenarios, particularly at off-design conditions.\"},{\"question\":\"What is the role of FIML in the proposed ML-augmented turbulence model?\",\"answer\":\"FIML infers turbulence-model discrepancy fields by solving inverse problems using high-fidelity data across different shapes and/or flow conditions, then uses machine learning to generalise those discrepancies to unseen cases.\"},{\"question\":\"How are the optimised flow predictions validated in this study?\",\"answer\":\"After obtaining optimal shapes for different turbulence models, the work proposes validating flow predictions using hybrid RANS-LES IDDES and then compares against available DNS data.\"}]","Aerodynamic shape optimisation using a machine learning-augmented turbulence model | PDF",1785721720,45,{"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},"aerodynamic-shape-optimisation-using-a-machine-learning-augmented-turbulence-model","",{"@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/aerodynamic-shape-optimisation-using-a-machine-learning-augmented-turbulence-model/119005/",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","2026-08-03",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},"Why are standard RANS-based aerodynamic shape optimisation methods limited for complex flows?","Question",{"text":75,"@type":76},"RANS turbulence models have documented deficiencies for complex flow phenomena such as separation, making them unreliable in those scenarios, particularly at off-design conditions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the role of FIML in the proposed ML-augmented turbulence model?",{"text":80,"@type":76},"FIML infers turbulence-model discrepancy fields by solving inverse problems using high-fidelity data across different shapes and/or flow conditions, then uses machine learning to generalise those discrepancies to unseen cases.",{"name":82,"@type":73,"acceptedAnswer":83},"How are the optimised flow predictions validated in this study?",{"text":84,"@type":76},"After obtaining optimal shapes for different turbulence models, the work proposes validating flow predictions using hybrid RANS-LES IDDES and then compares against available DNS data.","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"]