[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126791-en":3,"doc-seo-126791-105":30,"detail-sidebar-cat-0-en-105":83},{"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},126791,1099523882182,"Eliana","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Dreaming of Data - Examining Data Augmentation for Machine Learning in Additive Manufacturing","Additive manufacturing practice generates data that can train machine learning models to reduce defects, optimize mechanical properties, or improve efficiency. Research indicates that not only dataset size but also data characteristics affect whether additive manufacturing data fits machine-learning use. For cases where data is too small, too homogeneous, or otherwise inadequate, automated data augmentation can help. This study applies multiple augmentation techniques to synthetic design repositories to measure how they improve ML training performance across core additive-manufacturing ML tasks.","Dreaming of Data: Examining Data Augmentation for Machine Learning in Additive Manufacturing  \nGlen Williams, 1 Martha Baldwin,2 Timothy W. Simpson, 1 Nicholas A. Meisel, 1 Christopher McComb2  \n1 School of Engineering Design and Innovation, The Pennsylvania State University, University Park, PA 16802  \n2Department of Mechanical Engineering,  \nCarnegie Mellon University, Pittsburgh, PA 15213  \nAbstract  \nThe data generated during additive manufacturing (AM) practice can be used to train machine learning (ML) tools to reduce defects, optimize mechanical properties, or increase efficiency. In addition to the size of the repository, emerging research shows that other characteristics of the data also impact suitability of the data for AM-ML application. What should be done in cases for which the data in too small, too homogeneous, or otherwise insufficient? Data augmentation techniques present a solution, offering automated methods for increasing the quality of data. However, many of these techniques were developed for machine vision tasks, and hence their suitability for AM data has not been verified. In this study, several data augmentation techniques are applied to synthetic design repositories to characterize if and to what degree they enhance their performance as ML training sets. We discuss the comparative advantage of these data augmentation techniques across several canonical AM-ML tasks.  \n1. Introduction  \nStudying design repositories through metamodels can provide useful insight into whether or not an engineering design dataset will be successful in training a deep learning construct. However, what should be done if a dataset is estimated to be insufficient? Instead of simply giving up, researchers presented with incomplete, small, or otherwise low-quality datasets often turn to data augmentation to enhance their dataset prior to training a machine learning model. In this study, several data augmentation techniques are applied to artificial design repositories to characterize if and to what degree they enhance their performance as machine learning training sets. The intersection of additive manufacturing (AM) and machine learning (ML) presents numerous, complementary opportunities for design engineers. Manufacturing products using AM allows designers to take advantage of opportunistic AM attributes, such as part consolidation to reduce the number of parts in an assembly by increasing the complexity of individual parts [1] and hierarchical complexity to make parts that are lighter while remaining strong [2] . These beneficial attributes of AM can help designers focus more on problem solving than on limitations of traditional, tooling-driven manufacturing.  \nIn the same way that AM enables designers to manufacture increasingly complex and general shapes that might better solve a problem, ML could allow them to better predict how well those diverse solutions will perform in a multitude of ways. Some examples of researchers using ML to analyze AM parts include predicting AM build metrics [3], predicting thermal properties of AM designs during a build [4], classify parts as manufacturable or not [5], and prediction of product  \n1642  \ngeometric values to result in desired stress-strain performance [6]. However, both AM and ML are not perfect solutions, and many open questions regarding how to best utilize these technologies remain. ML approaches are generally most successful when developers have access to large training and validation datasets. Unfortunately, engineering data can be costly to create, obtain, and manage, resulting in datasets that are much smaller or more poorly labeled than those in some other fields. This problem is only compounded by the fact that AM technologies are relatively new and heuristics that might be useful for labeling datasets are the topic of contemporary research [7,8] and therefore in flux.  \nData augmentation can be a powerful tool to enhance the performance of ML constructs while reducing ","cbCairID75k5B4J0","https://ap.wps.com/l/cbCairID75k5B4J0","pdf",1385321,1,14,"English","en",105,"# Introduction\n## Data augmentation for insufficient engineering datasets\n## AM and ML opportunities (DfAM-ML)\n## Architecture-focused vs augmented-dataset nested iterative development","[{\"question\":\"What are some examples of machine learning tasks applied to additive manufacturing?\",\"answer\":\"Researchers use ML to predict build metrics, thermal properties during a build, whether parts are manufacturable, and geometric values that lead to desired stress-strain performance.\"}]","Dreaming of Data - Examining Data Augmentation for Machine Learning in Additive Manufacturing | PDF",1785934800,35,{"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":78,"head_meta":80,"extra_data":82,"updated_unix":28},"dreaming-of-data-examining-data-augmentation-for-machine-learning-in-additive-manufacturing","",{"@graph":36,"@context":77},[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/dreaming-of-data-examining-data-augmentation-for-machine-learning-in-additive-manufacturing/126791/",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],{"name":72,"@type":73,"acceptedAnswer":74},"What are some examples of machine learning tasks applied to additive manufacturing?","Question",{"text":75,"@type":76},"Researchers use ML to predict build metrics, thermal properties during a build, whether parts are manufacturable, and geometric values that lead to desired stress-strain performance.","Answer","https://schema.org",{"og:url":52,"og:type":79,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":81,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":46,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":46,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":46,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":46,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]