[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119001-en":3,"doc-seo-119001-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},119001,549758252649,"Ivy","https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819",8,"Research & Report","An Exploration of Flow Control Using Machine Learning and Computational Fluid Dynamics - read online","This exploratory study addresses the limits of workflows that apply machine learning to computational fluid dynamics mainly at early stages with fixed 3D models or at final testing. It proposes performing computational fluid dynamics and machine learning concurrently so aerodynamic design can adapt as models are continuously revised. The method develops, implements, and compares machine learning models that generate optimised three-dimensional geometries to guide airflow for pressure generation and for active or passive flow control applications. Results show decision tree regression and LSTM autoencoders can optimise aerodynamic efficiency, with LSTM performing better overall, while optimisation reduces overall shape size.","[https://doi.org/10.59200/ICARTI.2023.017](https://doi.org/10.59200/ICARTI.2023.017)  \nAn Exploration of Flow Control Using Machine Learning and Computational Fluid Dynamics  \nMatthew Cornfield and Karen Bradshaw  \nDepartment of Computer Science  \nRhodes University  \nGrahamstown, South Africa  \nmatcornfield@gmail.com, k.bradshaw@ru.ac.za  \nAbstract—Although numerous studies relating to computational fluid dynamics and machine learning have been conducted in relation to automotive development, the majority focus on either early development using completed 3D models, or the final testing stages of development, or machine learning accelerated computational fluid dynamic simulations.  \nWhile this approach is helpful in software development and simulation, it is not easily adaptable to automotive design where the final model is constantly changing and being modified. Consequently, the aim of this study is to propose a method for conducting computational fluid dynamics and machine learning concurrently to accelerate the development process. The proposed method is used to design and improve the aerodynamic efficiency of an object. The approach focuses on developing, implementing, and comparing machine learning models capable of generating optimised three-dimensional objects with the required geometry to direct airflow paths required in applications such as pressure generation, as needed for both active and passive flow control.  \nThe study concludes that both decision tree regression and long short-term memory (LSTM) autoencoder models could be used to optimise the aerodynamic efficiency of solid bodies, but that the LSTM autoencoder performs better overall. An undesirable effect of the shape optimisation is an overall reduction in shape size as optimization increases.  \nKeywords—computational fluid dynamics, machine learning, long short-term memory autoencoder, decision tree, optimisation  \nI. INTRODUCTION  \nAutomotive development is a highly competitive, high-stress environment, especially in the context of smaller automakersor race teams.  \nIn the first stages of development, teams are under enormous pressure to get early, functional prototypes designed and implemented. Design and development time is a time-consuming and computationally expensive task due to the complexity and non-linearity inherent in fluid dynamics. Computational fluid dynamic (CFD) environments are often used for testing designs in the early phases of development [1], while machine learning (ML) aided CFD environments are used to reduce the computational power required to compute the complex equations needed for CFD prototyping [2] .  \nThe design process for a race car is an iterative one, where engineers constantly test and refine the vehicle in an effort to leverage every aspect of performance available. The goal is to  \nThis work was undertaken in the Distributed Multimedia Centre of Excellence at Rhodes University.  \ndesign a vehicle that is both fast and safe, giving the driver the best possible chance of success.  \nThe design of a racing car is heavily influenced by the specific racing series in which the vehicle will compete. The regulations for a given series will dictate many of the vehicle’s design decisions, such as engine displacement, weight, tyre size, and aerodynamic configuration. Similarly, the track on which the vehicle will race also has a significant impact on the vehicle’s design. A vehicle designed to compete on a road course, for example, will need to be able to negotiate tight turns and maintain high speeds through long straights, while a vehicle designed for an oval track will need to be able to generate a high amount of grip and maintain stability at high speeds.  \nEnsuring that the design is the most optimal is a complex process, with heavy reliance on IT tools and techniques.  \nThis exploratory study aims to develop machine learning decision tree (DT) and long short-term memory (LSTM) autoencoder models that can run in CFD environmen","cbCail8BnvMp1XEZ","https://ap.wps.com/l/cbCail8BnvMp1XEZ","pdf",459808,1,"English","en",105,"# Introduction\n## Background concepts and literature\n### Aerodynamic fundamentals","[{\"question\":\"Why does the paper propose concurrent CFD and machine learning instead of stage-based workflows?\",\"answer\":\"Stage-based workflows are not easily adaptable when automotive models are constantly changing. Concurrent execution supports faster development while handling iterative design updates.\"},{\"question\":\"What machine learning models are evaluated for aerodynamic optimisation?\",\"answer\":\"The study evaluates decision tree regression and an LSTM (long short-term memory) autoencoder for optimising aerodynamic efficiency of solid bodies.\"},{\"question\":\"What trade-off does the paper observe when increasing the optimisation process?\",\"answer\":\"An undesirable effect is an overall reduction in shape size as optimisation increases.\"}]","An Exploration of Flow Control Using Machine Learning and Computational Fluid Dynamics - read online | PDF",1785721639,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"an-exploration-of-flow-control-using-machine-learning-and-computational-fluid-dynamics-read-online","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/an-exploration-of-flow-control-using-machine-learning-and-computational-fluid-dynamics-read-online/119001/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-03",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"Why does the paper propose concurrent CFD and machine learning instead of stage-based workflows?","Question",{"text":74,"@type":75},"Stage-based workflows are not easily adaptable when automotive models are constantly changing. Concurrent execution supports faster development while handling iterative design updates.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"What machine learning models are evaluated for aerodynamic optimisation?",{"text":79,"@type":75},"The study evaluates decision tree regression and an LSTM (long short-term memory) autoencoder for optimising aerodynamic efficiency of solid bodies.",{"name":81,"@type":72,"acceptedAnswer":82},"What trade-off does the paper observe when increasing the optimisation process?",{"text":83,"@type":75},"An undesirable effect is an overall reduction in shape size as optimisation increases.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]