[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126638-en":3,"doc-seo-126638-105":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},126638,549768064622,"Anda","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Machine learning approach to model the microstructure and strength of nickel superalloys - Doctor of Philosophy thesis","Nickel superalloys are essential in jet and gas turbine technologies, yet accelerated development requires reliable prediction of microstructure and mechanical strength. This PhD thesis develops machine learning models to improve these predictions, focusing on Gaussian process regression for microstructure and domain-knowledge-informed extrapolation. Results show microstructure models match CALPHAD interpolation while offering faster training, retrainability, inclusion of non-equilibrium effects, and use of computational data. When heat treatments are applied, the models predict microstructure evolution accurately, and related domain-informed models meaningfully expose physical mechanisms governing creep deformation.","Machine learning approach to model the microstructure and strength of  \nnickel superalloys  \nPatrick Louis Taylor  \nSupervisor: Dr Gareth Conduit Department of Physics University of Cambridge  \nThis thesis is submitted for the degree of Doctor of Philosophy  \nClare College  \nDecember 2022  \nDeclaration  \nThis thesis is the result of my own work and includes nothing which is the outcome of work done in collaboration except as declared in the preface and specified in the text. It is not substantially the same as any work that has already been submitted before for any degree or other qualification except as declared in the preface and specified in the text. The thesis does not exceed the prescribed word limit of 60,000 words as specified by the Degree Committee for the Faculty of Physics and Chemistry.  \nPublications  \nThe following chapters have been published in peer reviewed scientific journals:  \n• Chapter 4 has been published as: Taylor, P. L. & Conduit, G. Machine learning predictions of superalloy microstructure. Computational Materials Science 201, 110916 (Jan. 2022) [1] .  \nContribution: the DUQ was originally developed by Dr Gareth Conduit and expanded on by myself. The rest of the machine learning methodology described in the paper, along with all the results, are my own original work. Reviewing and editing was carried out by Dr Gareth Conduit.  \n• Chapter 5 has been published as: Taylor, P. L. & Conduit, G. Machine learning superalloy microchemistry and creep strength from physical descriptors. Computational Materials Science 227, 112265 (Aug. 2023) [2] .  \nContribution: the machine learning methodology and results in this paper are wholly my own work. Reviewing and editing was carried out by Dr Gareth Conduit.  \nii  \nMachine learning approach to model the microstructure and strength of nickel superalloys  \nPatrick Louis Taylor  \nNickel superalloys are a class of materials that find crucial applications in technologies such as jet and gas turbine engines. In order to accelerate the further development of these alloys, this thesis develops machine learning models that can better predict their microstructure and strength. The Gaussian process regression (GPR) models of microstructure are shown to be just as good at interpolation as traditional CALPHAD models, with advantages in speed, retrainability, incorporation of non-equilibrium effects, and the effective inclusion of computational data. By incorporating domain knowledge, it is shown that such GPR models can extrapolate into regions of composition space which include elements unseen during the training process. They can also make accurate predictions for the evolution of microstructure when heat treatments are applied. By making use of domain knowledge, similar extrapolations are possible for models of creep strength. Incorporating the results of the microstructure models leads to models of creep strength that meaningfully reveal underlying physical mechanisms of creep deformation.  \niv  \nAcknowledgements  \nFirst and foremost, I want to thank my supervisor, Dr Gareth Conduit, for all of the valuable guidance he has provided throughout this PhD project. He has been greatly invested in this project from the start and throughout, and has always been eager to lend his advice to me. I would also like to thank Dr Victor Milman and Dr Alexander Perlov at Dassault Syst`emes UK for the help and feedback they have provided.  \nFunding for this PhD was provided by the UK Engineering and Physical Sciences Research Council (EPSRC) and by Dassault Syst`emes via an EPSRC Industrial Cooperative Award in Science and Technology (ICASE) .  \nI would also like to extend my thanks to the friends and colleagues who have supported me in different ways during the course of this degree: my Centre for Doctoral Training cohort, especially Tim Wallis, Ben Seddon, Philip Kloza, Alwin B¨ucher, and James Wills; my colleagues in the Cavendish, including my office-mate Gunnar Lange, and Jack Whaley-B","cbCaihwWuGFXpHBq","https://ap.wps.com/l/cbCaihwWuGFXpHBq","pdf",17293698,1,143,"English","en",105,"# Abstract\n# Publications and Contributions\n## Chapter 4 journal publication\n## Chapter 5 journal publication\n# Introduction and Thesis Motivation\n## Gaussian process regression for microstructure\n## Domain-knowledge extrapolation\n## Microstructure-to-creep strength modeling\n# Acknowledgements","[{\"question\":\"What is the main goal of this thesis?\",\"answer\":\"To develop machine learning models that better predict the microstructure and strength of nickel superalloys, supporting faster alloy development for demanding engineering applications.\"},{\"question\":\"How are microstructure predictions modeled?\",\"answer\":\"Gaussian process regression (GPR) models are used, and their performance is compared to traditional CALPHAD approaches for interpolation and prediction.\"},{\"question\":\"What role does domain knowledge play?\",\"answer\":\"By incorporating domain knowledge, the models can extrapolate into composition regions containing elements unseen during training and can predict microstructure evolution under heat treatments; it also supports extrapolation for creep strength and reveals physical creep mechanisms.\"}]","Machine learning approach to model the microstructure and strength of nickel superalloys - Doctor of Philosophy thesis | PDF",1785933979,360,{"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-approach-to-model-the-microstructure-and-strength-of-nickel-superalloys-doctor-of-philosophy-thesis","",{"@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-approach-to-model-the-microstructure-and-strength-of-nickel-superalloys-doctor-of-philosophy-thesis/126638/",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","2026-08-05",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 is the main goal of this thesis?","Question",{"text":75,"@type":76},"To develop machine learning models that better predict the microstructure and strength of nickel superalloys, supporting faster alloy development for demanding engineering applications.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are microstructure predictions modeled?",{"text":80,"@type":76},"Gaussian process regression (GPR) models are used, and their performance is compared to traditional CALPHAD approaches for interpolation and prediction.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does domain knowledge play?",{"text":84,"@type":76},"By incorporating domain knowledge, the models can extrapolate into composition regions containing elements unseen during training and can predict microstructure evolution under heat treatments; it also supports extrapolation for creep strength and reveals physical creep mechanisms.","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"]