[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-119311-en":3,"doc-seo-119311-105":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},119311,13056703019404,"Miles","https://ap-avatar.wpscdn.com/davatar_29158cc5080c5b710cf443261637dec0",8,"Research & Report","Modelling of automotive steel fatigue lifetime by machine learning method","Neural-network-based modelling of fatigue life was developed for QSTE340TM automotive steel under cyclic loading. A Multi-Layer Perceptron with a 3-75-1 architecture predicts crack length using the load cycles N, stress ratio R, and overload ratio Rol as inputs. Training and evaluation used an 80/20 split of loading-cycle data with separate training, validation, and test sets. The model captures nonlinear relations between parameters and yields high prediction accuracy, with mean absolute percentage error (MAPE) from 0.02% to 4.59% across different R and Rol values.","Modelling of automotive steel fatigue lifetime by machine learning method  \nOleh Yasniy 1,†, Dmytro Tymoshchuk 1,∗,†, Iryna Didych 1,†, Nataliya Zagorodna1,† and Olha Malyshevska 2,†  \n1 Ternopil Ivan Puluj National Technical University, Ruska str. 56, Ternopil, 46001, Ukraine  \n2 Ivano-Frankivsk National Medical University, Galytska Str. 2, Ivano-Frankivsk, 76018, Ukraine  \nAbstract  \nIn the current study, the fatigue life of QSTE340TM steel was modelled using a machine learning method, namely, a neural network. This problem was solved by a Multi-Layer Perceptron (MLP) neural network with a 3-75-1 architecture, which allows the prediction of the crack length based on the number of load cycles N, the stress ratio R, and the overload ratio Rol. The proposed model showed high accuracy, with mean absolute percentage error (MAPE) ranging from 0.02% to 4.59% for different R and Rol. The neural network effectively reveals the nonlinear relationships between input parameters and fatigue crack growth, providing reliable predictions for different loading conditions.  \nKeywords  \nmachine learning, neural network, fatigue life, crack length, QSTE340TM steel  \n1. Introduction  \nQSTE340TM steel is a thermomechanically hardened low-alloy steel used in the automotive and mechanical engineering industries. Due to its high strength, QSTE340TM steel can reduce the weight of structures, which is important for automotive parts such as chassis, suspensions, and body components. It has good fatigue resistance, which ensures durability in harsh environments. The chemical composition of the steel includes manganese, silicon, phosphorus, sulfur, and other alloying elements that give it the required mechanical properties [1] .  \nMachine learning methods allow us to model the fatigue life of QSTE340TM steel and effectively predict the material's durability under cyclic loading. By applying machine learning algorithms, a large amount of experimental data can be analyzed automatically and the relationship between various parameters affecting material properties can be determined [2,3,4,5,6] .  \n⋆ITTAP’2024: 4th International Workshop on Information Technologies: Theoretical and Applied Problems, October 23-25, 2024, Ternopil, Ukraine, Opole, Poland  \n1∗ Corresponding author.  \n† These authors contributed equally.  \n [oleh.yasniy@gmail.com](oleh.yasniy@gmail.com) (O. Yasniy); [oleh.yasniy@gmail.com](oleh.yasniy@gmail.com) (D. Tymoshchuk); [iryna.didych1101@gmail.com](iryna.didych1101@gmail.com)  \n(I. Didych); [Zagorodna.n@gmail.com](Zagorodna.n@gmail.com) (N. Zagorodna); [o16r02@gmail.com](o16r02@gmail.com) (O. Malyshevska)  \n 0000-0002-9820-9093 (O. Yasniy); 0000-0003-0246-2236 (D. Tymoshchuk); 0000-0003-2846-6040 (I. Didych); 0000- 0002-1808-835X (N. Zagorodna); 0000-0003-0180-2112 (O. Malyshevska)  \n © 2023 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0) .  \nCEUR ~~  ~~[Workshop](Workshop ceur-ws.org)[ ceur-ws.org](Workshop ceur-ws.org)[ ](Workshop ceur-ws.org)[Proceedings](Proceedings ISSN 1613-0073)[ ISSN 1613-0073](Proceedings ISSN 1613-0073)   \n2. Methods  \nNeural networks allow us to model the fatigue life of QSTE340TM steel and effectively predict crack growth in the material under cyclic loading. Functional dependencies were modelled for experimental data obtained in [7]. The dataset [8] contained the dependence of the crack length a on the number of loading cycles N for four stress ratios R, namely, R = 0.1, 0.3, 0.5, and 0.7 at a constant amplitude (CA) and after a single tensile overload with overload ratiosRol = 1.5, 2.0. The neural network was trained on a dataset where the input parameters are the number of loading cycles N, the stress ratio R, and the overload ratio Rol, and the output parameter is the crack length a. The load cycle N reflects the number of cycles the steel has been loaded and isone of the main parameters for assessing fatigue crack growth. The","cbCaipwlCKPABPMU","https://ap.wps.com/l/cbCaipwlCKPABPMU","pdf",1037314,1,"English","en",105,"# Introduction\n# Methods\n# Results and discussion","[{\"question\":\"What material and outcome does the study model?\",\"answer\":\"The study models the fatigue life of QSTE340TM steel and predicts crack length a as the primary output.\"},{\"question\":\"Which machine learning model and input parameters are used?\",\"answer\":\"A Multi-Layer Perceptron (MLP) with a 3-75-1 architecture is used. Inputs are the number of load cycles N, the stress ratio R, and the overload ratio Rol, while the output is crack length a.\"},{\"question\":\"How is the model trained and evaluated?\",\"answer\":\"The dataset is split so that the first 80% of loading cycles are used for training/validation and the next 20% for testing. Training, validation, and testing sets are created from the 80% portion, and prediction error is computed using MAPE.\"}]","Modelling of automotive steel fatigue lifetime by machine learning method | PDF",1785723659,20,{"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},"modelling-of-automotive-steel-fatigue-lifetime-by-machine-learning-method","",{"@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/modelling-of-automotive-steel-fatigue-lifetime-by-machine-learning-method/119311/",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","2026-08-03",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 material and outcome does the study model?","Question",{"text":74,"@type":75},"The study models the fatigue life of QSTE340TM steel and predicts crack length a as the primary output.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Which machine learning model and input parameters are used?",{"text":79,"@type":75},"A Multi-Layer Perceptron (MLP) with a 3-75-1 architecture is used. Inputs are the number of load cycles N, the stress ratio R, and the overload ratio Rol, while the output is crack length a.",{"name":81,"@type":72,"acceptedAnswer":82},"How is the model trained and evaluated?",{"text":83,"@type":75},"The dataset is split so that the first 80% of loading cycles are used for training/validation and the next 20% for testing. Training, validation, and testing sets are created from the 80% portion, and prediction error is computed using MAPE.","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"]