[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-124319-en":3,"doc-seo-124319-105":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},124319,1374391974468,"Eden","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Machine Learning Driven Optimization of Complex Turbulent Flows - Thesis overview","Optimizing complex turbulent flows is challenging because turbulence is non-linear and chaotic, making traditional design optimization computationally intensive. This thesis develops a continuously learning, machine-learning driven optimization framework that couples with CFD to accelerate engineering design studies. Case studies include turbulence-field optimization for a gas turbine combustor, airflow optimization in a dental office to reduce infection spread, and tutorial demonstrations for MILO on heat exchanger tuning and multi-objective fire suppression design. Results show substantial performance gains and large CPU-hour savings under engineering constraints.","Machine Learning Driven Optimization of Complex  \nTurbulent Flows  \nby  \nJennifer A. Miklaszewski  \nB.A., Purdue University, 2012  \nM.S., Purdue University, 2013  \nA thesis submitted to the  \nFaculty of the Graduate School of the  \nUniversity of Colorado in partial fulfillment  \nof the requirements for the degree of  \nDoctor of Philosophy  \nDepartment of Mechanical Engineering  \n2025  \nCommittee Members: Peter Hamlington, Chair Masha Folk  \nDaven Henze  \nDebanjan Mukherjee Shelly Miller  \nJohn Evans  \nii  \nMiklaszewski, Jennifer A. (Ph.D., Mechanical Engineering)  \nMachine Learning Driven Optimization of Complex Turbulent Flows  \nThesis directed by Prof. Peter Hamlington  \nOptimizing complex turbulent flows presents a difficult challenge due to the non-linear, chaotic nature of turbulence. Most fluid flows found in nature or in engineering applications are turbulent, prompting the need for a design optimization method that can quickly and efficiently handle this complexity. Incorporating machine learning and artificial intelligence can greatly accelerate traditionally computationally-intensive methods of optimizing these flows. The aim of this thesis is to showcase the development of a continuously-learning, machine-learning driven optimization method. This is coupled with computational fluid dynamics (CFD) and is applied to various engineering design problems to demonstrate its potential as a powerful engineering design tool.  \nThe first case study presented is the optimization of the exit turbulence field in a gas turbine combustor simulator. Combustor turbulence in a gas turbine engine greatly influences the efficiency of the downstream high pressure turbine stage. Studies have shown that combustor turbulence can result in a 1 .3% reduction in stage efficiency of the turbine. This is a staggering number when considering the impact on engine fuel efficiency, with improvements of 0.1% generally garnering substantial research funding. With an optimized design, I am able to achieve substantial improvements in stage efficiency, as well as identify the specific aspects of combustor geometry that contribute to this finding. The second case study presented is the optimization of airflow patterns in a dental office to minimize infection spread. The placement of the air supply and return vents is analyzed to produce optimal circulation within the building and decrease infection potential for dental personnel and patients.  \nTwo more cases are presented as tutorial cases for the packaged optimizer and to expand functionality of the optimization scheme, named the Multi-fidelity Integrated Learning Optimization, or MILO. The third case is a simplified heat exchanger, where the cooling air temperature,  \niii  \nvelocity, and fan speed is adjusted to target a desired outlet water temperature. Uncertainty in the inlet conditions and fan speed is propagated throughout the optimization, showing the potential success of this tool when used in real-world industrial applications where operating conditions may vary. The fourth case introduces multi-objective optimization of a fire suppression system where both the mass flow rate of the water and the amount of solid burned are minimized. This demonstration of a multi-objective problem radically expands the number of engineering design problems that MILO can be applied to. In all cases presented in this thesis, there is a substantial improvement in design performance despite the numerous design constraints applied, as well as an average 88% savings in the number of CPU hours needed to reach an optimized solution.  \nDedication  \nTo my husband and best friend, Eric, for all of the sacrifices you made to get me here.  \nv  \nAcknowledgements  \nI would like to thank my advisor, Peter Hamlington, for his guidance and support throughout this work, both personal and professional.  \nI would like to thank Masha Folk for her keen insight, guidance, and excellent mentoring. She has inspired the kind of engineer","cbCaigZV5Dyzxpm6","https://ap.wps.com/l/cbCaigZV5Dyzxpm6","pdf",20037904,1,180,"English","en",105,"# Introduction\n# Literature Review\n## Gradient-based vs. Gradient-free Methods\n## Surrogate Modeling\n# Case Study: Multi-Fidelity Optimization of Turbulence Characteristics in a Gas Turbine Combustor Simulator\n## Introduction\n## Numerical Simulations\n## Sensitivity Analysis","[{\"question\":\"Why is optimization of turbulent flows difficult in engineering design?\",\"answer\":\"Turbulent flows are non-linear and chaotic, which makes the behavior hard to predict and the optimization process computationally intensive.\"},{\"question\":\"What is the core goal of this thesis?\",\"answer\":\"To develop a continuously learning, machine-learning driven optimization method that works with CFD and demonstrates strong potential as an engineering design tool.\"},{\"question\":\"Which engineering problems are used to evaluate the method?\",\"answer\":\"The thesis evaluates optimization of combustor exit turbulence, airflow patterns in a dental office to minimize infection spread, and tutorial cases using MILO such as heat exchanger targeting and multi-objective fire suppression.\"}]","Machine Learning Driven Optimization of Complex Turbulent Flows - Thesis overview | PDF",1785821583,454,{"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},"machine-learning-driven-optimization-of-complex-turbulent-flows-thesis-overview","",{"@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/machine-learning-driven-optimization-of-complex-turbulent-flows-thesis-overview/124319/",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},"Why is optimization of turbulent flows difficult in engineering design?","Question",{"text":75,"@type":76},"Turbulent flows are non-linear and chaotic, which makes the behavior hard to predict and the optimization process computationally intensive.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the core goal of this thesis?",{"text":80,"@type":76},"To develop a continuously learning, machine-learning driven optimization method that works with CFD and demonstrates strong potential as an engineering design tool.",{"name":82,"@type":73,"acceptedAnswer":83},"Which engineering problems are used to evaluate the method?",{"text":84,"@type":76},"The thesis evaluates optimization of combustor exit turbulence, airflow patterns in a dental office to minimize infection spread, and tutorial cases using MILO such as heat exchanger targeting and multi-objective fire suppression.","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"]