[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-128834-105":59,"doc-detail-128834-en":134},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":127,"head_meta":129,"extra_data":131,"updated_unix":133},105,"en","machine-learning-aided-optimization-for-laser-based-metal-additive-manufacturing-doctoral-thesis","Machine Learning-Aided Optimization for Laser-Based Metal Additive Manufacturing - Doctoral Thesis","","Laser-based metal additive manufacturing (AM) such as laser powder bed fusion (LBPF) and laser direct energy deposition (LDED) relies on many interacting processing parameters, making it difficult to identify processing windows and achieve consistent component quality. This thesis addresses slow trial-and-error optimization for new materials by applying machine learning to accelerate optimization and clarify processing–structure–property relationships. The work covers powder flowability via computer vision, data-driven process-map parameter suggestions, deep learning for keyholes and pores in synchrotron imaging, coupling ML-predicted laser absorptance with CFD for keyhole depth, and high-speed IR monitoring plus quality metrics for LDED stainless steel thin-wall samples, improving efficiency and product quality.",{"@graph":69,"@context":126},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/machine-learning-aided-optimization-for-laser-based-metal-additive-manufacturing-doctoral-thesis/128834/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/machine-learning-aided-optimization-for-laser-based-metal-additive-manufacturing-doctoral-thesis/128834.png","ImageObject",300,407,{"name":92,"@type":93},"Maeve","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-09-21","2026-08-06",true,{"@type":102,"interactionType":103,"userInteractionCount":39},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118,122],{"name":109,"@type":110,"acceptedAnswer":111},"Why is optimizing laser-based metal additive manufacturing challenging?","Question",{"text":112,"@type":113},"AM involves many processing parameters—feedstock, laser power, spot size, scanning speed, layer thickness, and hatch spacing—creating a large parameter space. Identifying processing windows is difficult, and conventional optimization often uses slow trial-and-error.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"How does the thesis use machine learning to speed up optimization?",{"text":117,"@type":113},"Machine learning uncovers relationships from extensive data to accelerate process optimization and improve understanding of processing–structure–property links. The thesis integrates ML across multiple stages, from powder behavior to monitoring and modeling.",{"name":119,"@type":110,"acceptedAnswer":120},"What techniques are used for monitoring and image analysis?",{"text":121,"@type":113},"Deep learning models are trained to detect and analyze keyholes and generated pores from captured images, including data relevant to synchrotron X-ray monitoring. A high-speed IR camera-based system is also integrated into a customized LDED machine.",{"name":123,"@type":110,"acceptedAnswer":124},"How is laser absorptance incorporated into predictive modeling?",{"text":125,"@type":113},"ML-predicted laser absorptance is integrated into a computational fluid dynamics (CFD) model to accurately predict keyhole depth across different processing parameters.","https://schema.org",{"og:url":83,"og:type":128,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":130,"canonical":83},"index,follow",{"doc_id":132,"site_id":62},128834,1786003778,{"code":4,"msg":5,"data":135},{"doc_id":132,"user_id":136,"nickname":92,"user_avatar":137,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":138,"file_id":139,"file_url":140,"file_type":141,"file_size":142,"view_count":39,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":143,"language":144,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":145,"faqs":146,"seo_title":147,"seo_description":67,"update_tm":133,"read_time":148},2336474466712,"https://ap-avatar.wpscdn.com/davatar_a8503ba1806abce46bf441b54a3ca4cd","Machine Learning-Aided Optimization for Laser-Based Metal Additive Manufacturing  \nby  \nJiahui Zhang  \nA thesis submitted in conformity with the requirements  \nfor the degree of Doctor of Philosophy  \nDepartment of Materials Sciences and Engineering  \nUniversity of Toronto  \n© Copyright by Jiahui Zhang 2025  \nMachine Learning-Aided Optimization for Laser-Based Metal  \nAdditive Manufacturing  \nJiahui Zhang  \nDoctor of Philosophy  \nDepartment of Materials Science and Engineering  \nUniversity of Toronto  \n2025  \nAbstract  \nLaser-based metal additive manufacturing (AM) technologies, such as laser powder bed fusion (LBPF) and laser direct energy deposition (LDED), have been widely adopted in a wide range of  \nindustries, including the aerospace, automotive, biomedical and energy sectors. Compared with conventional manufacturing processes, the AM processes involve a wide range of processing  \nparameters, including feedstock characteristics, laser power, spot size, scanning speed, layer thickness and hatch spacing, which are essential to the quality, properties, and performance of  \nfinal products. The identification of processing windows from a vast process parameter space is a daunting task. Despite an increasing theoretical understanding and numerical simulations ofthe  \nmetal AM methods, the optimization of the AM processes is predominantly developed through a sequential and time-consuming trial-and-error approach, especially for new materials. To this  \nend, the recent advance of machine learning (ML), owing to its ability to uncover hidden  \nrelationships from extensive data, offers new opportunities to accelerate the optimization of metal AM processes and improve our understanding of their processing-structure-property relationships.  \nThis thesis explores the application of ML techniques to improve the final quality of components fabricated through metal AM across various stages ofthe process. This thesis covers the following optimization aspects: (1) The individual influence of particle size distribution (PSD) on the powder flowability has been investigated. To reduce the time and effort required to characterize powder flowability, a reliable computer vision approach is established to evaluate powder flowability based on scanning electron microscope images. (2) ML methods are applied for the parameter optimization by introducing a data-driven framework to establish process maps and suggest optimal processing parameters. (3) To facilitate efficient data analysis for synchrotron Xray monitoring, various deep learning models are trained to identify and analyze the keyholes and generated pores from captured images. (4) To delve into the laser-metal interaction process, the ML-predicted laser absorptance is integrated into a computational fluid dynamic model to accurately predict keyhole depth across various processing parameters. (5) A high-speed IR camera-based monitoring system is integrated into a customized LDED machine, and a comprehensive and reliable quality assessment metric is introduced for optimizing processing parameters for stainless steel thin-wall samples. This thesis demonstrates that ML significantly improve the process efficiency and product quality in laser-based metal AM processes, offering a powerful tool for addressing many of the most persistent challenges in the field of metal AM.  \nAcknowledgments  \nFirst and foremost, I would like to thank my supervisor, Professor Yu Zou, not only for his expertise, guidance, assistance, and support, but also for his encouragement, time and understanding throughout my Ph.D. program. I am also sincerely thankful to my co-supervisor, Professor Yiming Rong, for his trust and financial support. Your professionalism and passion for research have continually inspired me to push the boundaries of my scientific work.  \nI would also like to express my special thanks of gratitude to my committee members, Professor Jason Hattrick-Simpers, Professor Sanjeev Chandra, Professor Qiang","cbCaiocajn3wE5dy","https://ap.wps.com/l/cbCaiocajn3wE5dy","pdf",14503393,245,"English","# Abstract\n# Acknowledgments\n## Supervisors and Committee Members\n## Collaborators and Research Support","[{\"question\":\"Why is optimizing laser-based metal additive manufacturing challenging?\",\"answer\":\"AM involves many processing parameters—feedstock, laser power, spot size, scanning speed, layer thickness, and hatch spacing—creating a large parameter space. Identifying processing windows is difficult, and conventional optimization often uses slow trial-and-error.\"},{\"question\":\"How does the thesis use machine learning to speed up optimization?\",\"answer\":\"Machine learning uncovers relationships from extensive data to accelerate process optimization and improve understanding of processing–structure–property links. The thesis integrates ML across multiple stages, from powder behavior to monitoring and modeling.\"},{\"question\":\"What techniques are used for monitoring and image analysis?\",\"answer\":\"Deep learning models are trained to detect and analyze keyholes and generated pores from captured images, including data relevant to synchrotron X-ray monitoring. A high-speed IR camera-based system is also integrated into a customized LDED machine.\"},{\"question\":\"How is laser absorptance incorporated into predictive modeling?\",\"answer\":\"ML-predicted laser absorptance is integrated into a computational fluid dynamics (CFD) model to accurately predict keyhole depth across different processing parameters.\"}]","Machine Learning-Aided Optimization for Laser-Based Metal Additive Manufacturing - Doctoral Thesis | PDF",617]