[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-123380-en":3,"doc-seo-123380-105":29,"detail-sidebar-cat-0-en-105":90},{"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":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":26,"seo_description":14,"update_tm":27,"read_time":28},123380,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Interpretable Machine Learning for Predicting the Fatigue Strength of Steel - Influence of Composition and Processing - Abstract","Fatigue strength prediction in steel is essential for structural design and failure assessment because fatigue tests are costly and time-consuming, while fatigue failures can be highly consequential. The study applies the CatBoost machine learning algorithm to predict fatigue strength using chemical composition, processing parameters, and mechanical properties. Model trust is increased by integrating Shapley additive explanations (SHAP), identifying feature contributions such as tempering temperature, chromium content, and molybdenum content. The framework delivers strong predictive performance (R²=0.952), supporting safety-critical applications and interpretable feature-importance analysis.","Interpretable Machine Learning for Predicting the Fatigue Strength of Steel: Influence of Composition and Processing  \nParameters  \nSoheila Kookalani1, Gozde Basak Ozturk2, Hamidreza Alavi1, Erika Parn1, and Ioannis Brilakis1  \n1Department of Engineering, University of Cambridge, Cambridge, UK 2Department of Civil Engineering, Aydin Adnan Menderes University, Aydin, Turkey  \n[sk2268@cam.ac.uk](sk2268@cam.ac.uk), [gbozturk@edu.edu.tr](gbozturk@edu.edu.tr), [sa2194@cam.ac.uk](sa2194@cam.ac.uk), [eap47@cam.ac.uk](eap47@cam.ac.uk), [ib340@cam.ac.uk](ib340@cam.ac.uk)  \nAbstract –  \nThe prediction of fatigue strength in steel is critical for the design and analysis of structural components, given the high costs and time associated with fatigue testing and the severe consequences of fatigue failures. This study explores the application of the CatBoost machine learning algorithm to predict the fatigue strength of steel based on chemical composition, processing parameters, and mechanical properties. The model's interpretability is enhanced by integrating Shapley additive explanations, providing insights into the contributions of key features such as tempering temperature (TT), chromium content (Cr), and molybdenum content (Mo). The proposed framework achieves high predictive accuracy, with an R² of 0.952 and anRMSE of 31.625. This study fosters trust and utility in safetycritical applications by addressing the limitations of black-box models. The results underscore the potential of interpretable machine learning in advancing fatigue strength prediction methodologies and informing structural and construction engineering practices, while Enhancing the SHAPbased feature importance analysis to refine the selection of key predictors, potentially simplifying the model while maintaining accuracy.  \nKeywords –  \nFatigue strength; Steel; Construction; Machine learning; Shapely additive explanations; CatBoost; Predictive modeling; Regression; Data interpretability.  \n1 Introduction  \nAccurate prediction of the fatigue strength of steels is of particular significance due to the extremely high costs and time requirements of fatigue testing, as well as the often-debilitating consequences of fatigue failures [1],[2] . Fatigue strength is the most fundamental data  \nrequired for the design and failure analysis of structural components [3], [4], [5] . It is reported that fatigue accounts for over 90% of all mechanical failures in structural components [6], underscoring the critical need for reliable fatigue life prediction methods.  \nFatigue failure is a complex phenomenon influenced by a multitude of variables, including material composition, microstructure, processing parameters, and operational conditions [7] . The intricate interactions among these variables pose significant challenges for conventional modeling and analytical approaches, which often fail to capture the non-linear relationships and hidden dependencies inherent in fatigue behavior. Consequently, a robust and reliable predictive framework is essential for advancing understanding and improving the safety and performance of steel components.  \nIn recent years, machine learning (ML) algorithms have demonstrated significant potential in solving complex predictive tasks in structural engineering [8], [9],[10], [11] . Wang et al. [12] provided a review of fatigue life prediction methods, highlighting the limitations of purely data-driven approaches. Zhan et al. [13] presented a ML-based approach for predicting the fatigue life of additively manufactured stainless steel 316L. However, the application of these algorithms to fatigue strength prediction has been limited, particularly in terms of interpretability. Most ML models function as \"black boxes,\" providing accurate predictions but little insight into the decision-making processes or the influence of individual variables. This lack of transparency hampers the adoption of ML techniques in safety-critical domains like fatigue prediction. ","cbCaivvUOPq8w3pO","https://ap.wps.com/l/cbCaivvUOPq8w3pO","pdf",751365,1,"English","en",105,"# Introduction\n# Shapley additive explanations","[{\"question\":\"What is the main goal of the study on steel fatigue strength?\",\"answer\":\"To predict the fatigue strength of steel using machine learning while also providing interpretable, actionable insights into how individual features influence predictions.\"},{\"question\":\"Which machine learning model is used for fatigue strength prediction?\",\"answer\":\"The study leverages the CatBoost machine learning algorithm.\"},{\"question\":\"How does the study improve interpretability compared with black-box models?\",\"answer\":\"It integrates Shapley additive explanations (SHAP) to quantify and explain the contributions and relative importance of key input features.\"}]","Interpretable Machine Learning for Predicting the Fatigue Strength of Steel - Influence of Composition and Processing - Abstract | PDF",1785816200,20,{"code":4,"msg":30,"data":31},"ok",{"site_id":23,"language":22,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":85,"head_meta":87,"extra_data":89,"updated_unix":27},"interpretable-machine-learning-for-predicting-the-fatigue-strength-of-steel-influence-of-composition-and-processing-abstract","",{"@graph":35,"@context":84},[36,53,67],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/interpretable-machine-learning-for-predicting-the-fatigue-strength-of-steel-influence-of-composition-and-processing-abstract/123380/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":22,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-08-04",true,{"@type":64,"interactionType":65,"userInteractionCount":20},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What is the main goal of the study on steel fatigue strength?","Question",{"text":74,"@type":75},"To predict the fatigue strength of steel using machine learning while also providing interpretable, actionable insights into how individual features influence predictions.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which machine learning model is used for fatigue strength prediction?",{"text":79,"@type":75},"The study leverages the CatBoost machine learning algorithm.",{"name":81,"@type":72,"acceptedAnswer":82},"How does the study improve interpretability compared with black-box models?",{"text":83,"@type":75},"It integrates Shapley additive explanations (SHAP) to quantify and explain the contributions and relative importance of key input features.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":91},[92,96,100,104,109,114,119,122,126,129,133],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":112,"slug":113},6,"Technology",50,"technology",{"id":115,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":28,"slug":125},9,"Religion & Spirituality","religion-spirituality",{"id":28,"doc_module":4,"doc_module_name":45,"category_name":127,"show_sort_weight":28,"slug":128},"World Cup","world-cup",{"id":130,"doc_module":4,"doc_module_name":45,"category_name":131,"show_sort_weight":130,"slug":132},10,"Lifestyle","lifestyle",{"id":134,"doc_module":4,"doc_module_name":45,"category_name":135,"show_sort_weight":105,"slug":136},19,"General","general"]