[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291089-105":59,"doc-detail-291089-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","deconvoluting-thermomechanical-effects-in-x-ray-diffraction-data-using-machine-learning","Deconvoluting Thermomechanical Effects in X-ray Diffraction Data using Machine Learning","","X-ray diffraction probes sub-surface states in crystalline materials under rapid thermomechanical loading, but increasing diffraction volume size and convolution of lattice deformation mechanisms hinder disentangling thermal versus mechanical contributions. This work presents a physics-informed machine-learning framework combining heat/fluid simulations, elasto-plasticity, and X-ray diffraction modeling to generate training data. Temperature-dependent elastic and thermal properties come from density functional theory. Gaussian Process Regression maps intensity distributions to thermomechanical elastic strain fields, successfully separating thermal and mechanical effects even for irregular peak shapes, demonstrated on laser-melted Inconel 625 with residual stress.",{"@graph":69,"@context":123},[70,84,106],{"@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/deconvoluting-thermomechanical-effects-in-x-ray-diffraction-data-using-machine-learning/291089/",{"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/deconvoluting-thermomechanical-effects-in-x-ray-diffraction-data-using-machine-learning/291089.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-27","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",13,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"Why is deconvolution difficult in X-ray diffraction under combined thermal and mechanical loading?","Question",{"text":113,"@type":114},"Temperature and hydrostatic stress modify the lattice strain tensor in similar ways, and broad thermal/mechanical strain distributions across a diffraction volume further complicate separation.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"How does the proposed method generate training data for machine learning?",{"text":118,"@type":114},"It combines heat transfer and fluid flow simulations, elasto-plasticity modeling, and X-ray diffraction simulations to create a dictionary of diffraction patterns mapped to underlying thermomechanical strain fields.",{"name":120,"@type":111,"acceptedAnswer":121},"What is the role of Gaussian Process Regression (GPR) in the workflow?",{"text":122,"@type":114},"GPR models learn the relationship between measured diffraction intensity distributions and the underlying thermal and mechanical elastic strain fields, enabling deconvolution even for complex diffraction patterns.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291089,1789643423,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","arXiv :2408 .09447v3 [ cond-mat .mtrl-sci ] 8 Jan 2025  \nDeconvoluting Thermomechanical Effects in X-ray Diffraction Data using Machine Learning  \nRachel E. Lima,c , Shun-Li Shanga , Chihpin Chuangb , Thien Q. Phanc , Zi-Kui Liua ,  \nDarren C. Pagana,∗  \na Pennsylvania State University, University Park, PA 16802, USA b Argonne National Laboratory, Lemont, IL 60439, USAc Lawrence Livermore National Laboratory, Livermore, CA 14850, USA  \nAbstract  \nX-ray diffraction is ideal for probing sub-surface state during complex or rapid thermomechanical loading of crystalline materials. However, challenges arise as the size of diffraction volumes increases due to spatial broadening and inability to deconvolute the effects of different lattice deformation mechanisms. Here, we present a novel approach to use combinations of physics-based modeling and machine learning to deconvolve thermal and mechanical elastic strains for diffraction data analysis. The method builds on a previous effort to extract thermal strain distribution information from diffraction data. The new approach is applied to extract the evolution of thermomechanical state during laser melting of an Inconel 625 wall specimen which produces significant residual stress upon cooling. A combination of heat transfer and fluid flow, elasto-plasticity, and X-ray diffraction simulations are used to generate training data for machine-learning (Gaussian Process Regression, GPR) models that map diffracted intensity distributions to underlying thermomechanical strain fields. Firstprinciples density functional theory is used to determine accurate temperature-dependent thermal expansion and elastic stiffness used for elasto-plasticity modeling. The trained GPR models are found to be capable of deconvoluting the effects of thermal and mechanical strains, in addition to providing information about underlying strain distributions, even from complex diffraction patterns with irregularly shaped peaks.  \nKeywords: synchrotron X-ray diffraction, stress, superalloys, machine learning, physics-based modeling, first-principles calculations, Gaussian Process Regression  \n∗ Corresponding author  \nEmail address: [dcp5303@psu.edu](dcp5303@psu.edu) (Darren C. Pagan)  \nPreprint submitted to arXiv January 10, 2025  \n1. Introduction  \nUnderstanding and controlling the development of residual stress during traditional welding, and now additive manufacturing (AM), is an ongoing challenge. Rapid, localized heating then solidification leads to large thermal stresses which, in turn, lead to plastic flow and residual stress. These residual stresses can drive hot-cracking or cause such severe distortions that a part is unusable. Optical and thermography measurements provide a means to characterize the temperature gradients driving stress development [1, 2, 3, 4, 5, 6, 7, 8], but are limited to the surface. In addition, while there has been a significant focus placed on developing high-speed X-ray imaging at synchrotron sources to monitor melt pool characteristics and the development of porosity in support of AM processing, the use of scattering and the study of stress development has been limited in comparison. However, recent efforts are building upon imaging efforts to also use scattering to study complex rapid solidification processes [9, 10, 11, 12, 13, 14, 15, 16, 17, 18, 19] . More specifically, diffraction processes are capable of monitoring the development of texture, phases, and residual strains (and related stress) .  \nAn acute challenge in using diffraction to monitor stress development in combined thermal and mechanical loading is that both temperature and mechanical stress alter the state of the crystal lattice (which is what is probed during diffraction measurements) . Specifically in cubic crystal types, both temperature and hydrostatic stress will alter the volumetric portion of the lattice strain tensor in the same fashion, making deconvolution of the effects difficult. Assumptions can be made re","cbCaisjX5Zu9UzG6","https://ap.wps.com/l/cbCaisjX5Zu9UzG6","pdf",10960687,47,"English","# Introduction\n## Challenge in deconvolving thermal and mechanical effects\n## Proposed physics-informed ML approach with GPR\n## Role of DFT and training-data generation","[{\"question\":\"Why is deconvolution difficult in X-ray diffraction under combined thermal and mechanical loading?\",\"answer\":\"Temperature and hydrostatic stress modify the lattice strain tensor in similar ways, and broad thermal/mechanical strain distributions across a diffraction volume further complicate separation.\"},{\"question\":\"How does the proposed method generate training data for machine learning?\",\"answer\":\"It combines heat transfer and fluid flow simulations, elasto-plasticity modeling, and X-ray diffraction simulations to create a dictionary of diffraction patterns mapped to underlying thermomechanical strain fields.\"},{\"question\":\"What is the role of Gaussian Process Regression (GPR) in the workflow?\",\"answer\":\"GPR models learn the relationship between measured diffraction intensity distributions and the underlying thermal and mechanical elastic strain fields, enabling deconvolution even for complex diffraction patterns.\"}]","Deconvoluting Thermomechanical Effects in X-ray Diffraction Data using Machine Learning | PDF",118]