[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122585-en":3,"doc-seo-122585-105":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":20,"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},122585,7971461741311,"Ophelia","https://ap-avatar.wpscdn.com/avatar/74000253aff267980c6?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779345379180704826",8,"Research & Report","Interpretable machine learning for predicting the bearing capacity of double shear-bolted connections - a data-driven evaluation","Accurate prediction of the bearing capacity of double shear-bolted connections is essential for safe and efficient structural steel design. The study applies ten machine learning algorithms to improve prediction accuracy while addressing common interpretability limitations. Models are tuned using 10-fold cross-validation and evaluated with RMSE, R2 and a20 accuracy index. A sensitivity analysis and interpretability methods—including partial dependence plots, accumulated local effects, and Shapley additive explanations—identify critical variables at local and global scales, supporting trustworthy, data-driven design.","TYPE Original Research PUBLISHED 17 February 2026 DOI 10.3389/fbuil.2026.1753382  \nOPEN ACCESS  \nEDITED BY  \nVagelis Plevris,  \nQatar University, Qatar  \nREVIEWED BY  \nCarlos Couto,  \nUniversity of Aveiro, Portugal Yanping Zhu,  \nMontana Technological University, United States  \n*CORRESPONDENCE  \nSoheila Kookalani,  [sk2268@cam.ac.uk](sk2268@cam.ac.uk)  \nRECEIVED 24 November 2025  \nREVISED 09 January 2026  \nACCEPTED 14 January 2026  \nPUBLISHED 17 February 2026  \nCITATION  \nKookalani S, Liu H, Dash T, Mathew A and Brilakis I (2026) Interpretable machine learning for predicting the bearing capacity of double  \nshear-bolted connections: a datadriven evaluation.  \nFront. Built Environ. 12:1753382 .  \ndoi: 10.3389/fbuil.2026.1753382  \nCOPYRIGHT  \n© 2026 Kookalani, Liu, Dash, Mathew and Brilakis. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY) . The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.  \nInterpretable machine learning for predicting the bearing capacity of double shear-bolted connections: a data-driven evaluation  \nSoheila Kookalani 1*, Hongchen Liu 1, Tirtharaj Dash 2, Alwyn Mathew 1 and Ioannis Brilakis 1  \n1Department of Engineering, University of Cambridge, Cambridge, United Kingdom, 2Department of Biochemistry, University of Cambridge, Cambridge, United Kingdom  \nIntroduction: Accurate prediction of the bearing capacity of double shear-bolted connections in structural steel is essential for ensuring safety and efficiency in structural design. This study explores the application of ten machine learning algorithms to enhance prediction accuracy while addressing the interpretability challenges often associated with such models.  \nMethods: Models were tuned with 10-fold crossvalidation and assessed using RMSE, R2 and a20 accuracy index. A comprehensive sensitivity analysis evaluates the influence of input parameters, while advanced interpretability techniques, such as partial dependence plots, accumulated local effects, and Shapley additive explanations, are employed alongside parametric studies to elucidate the decision-making processes of the models.  \nResults: These methods facilitate the identification of critical variables that influence bearing capacity predictions at both local and global scales. Discussion: The study demonstrates that machine learning can be a trustworthy and data-driven complement to conventional mechanics-based approaches, when coupled with rigorous interpretability, advancing both safety and efficiency in steelconnection design. The findings highlight the potential of interpretable machine learning approaches to not only improve predictive precision but also provide actionable insights into complex model behaviours, ultimately advancing structural engineering practices and promoting data-driven design methodologies.  \nKEYWORDS  \nbearing capacity prediction, double shear-bolted connections, interpretable AI, machine learning, sensitivity analysis, structural steel joints  \n1 Introduction  \nBolted and welded connections are widely regarded as the backbone of steel structures, ensuring load transfer and global stability across a broad spectrum of engineering applications. In comparison to welded joints, bolted connections offer several advantages, including expedited assembly and reduced cost by obviating specialized labour and on-site welding procedures, while still achieving reliable structural performance when bolt holes and net-section effects are properly accounted for in design (Zakir et al., 2022) . Within the family of bolted connections, bearing-type joints  \nFrontiers in Built Environment 01 [frontiersin.org](frontiersin.org)  \nhave garnered par","cbCaiq0ejKnEDXhW","https://ap.wps.com/l/cbCaiq0ejKnEDXhW","pdf",6845934,1,26,"English","en",105,"# Introduction\n## Bolted and welded connections and bearing-type behavior\n## Prior research and key influencing parameters\n## AI in civil engineering and related predictive studies\n# Methods\n## Model tuning and evaluation metrics\n## Sensitivity analysis\n## Interpretability techniques and parametric studies\n# Results and Discussion\n## Critical variable identification\n## Trustworthy ML complement to mechanics-based approaches","[{\"question\":\"What problem does the study address in steel connection design?\",\"answer\":\"It targets accurate prediction of the bearing capacity of double shear-bolted connections to support safe and efficient structural design.\"},{\"question\":\"Which machine learning evaluation metrics are used?\",\"answer\":\"Models are assessed using RMSE, R2, and the a20 accuracy index after tuning with 10-fold cross-validation.\"},{\"question\":\"How does the study improve interpretability of machine learning models?\",\"answer\":\"It combines sensitivity analysis with interpretability methods such as partial dependence plots, accumulated local effects, and Shapley additive explanations, supported by parametric studies.\"}]","Interpretable machine learning for predicting the bearing capacity of double shear-bolted connections - a data-driven evaluation | PDF",1785811496,66,{"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},"interpretable-machine-learning-for-predicting-the-bearing-capacity-of-double-shear-bolted-connections-a-data-driven-evaluation","",{"@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/interpretable-machine-learning-for-predicting-the-bearing-capacity-of-double-shear-bolted-connections-a-data-driven-evaluation/122585/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the study address in steel connection design?","Question",{"text":75,"@type":76},"It targets accurate prediction of the bearing capacity of double shear-bolted connections to support safe and efficient structural design.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which machine learning evaluation metrics are used?",{"text":80,"@type":76},"Models are assessed using RMSE, R2, and the a20 accuracy index after tuning with 10-fold cross-validation.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the study improve interpretability of machine learning models?",{"text":84,"@type":76},"It combines sensitivity analysis with interpretability methods such as partial dependence plots, accumulated local effects, and Shapley additive explanations, supported by parametric studies.","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"]