[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117560-en":3,"doc-seo-117560-105":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":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},117560,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","A Supervised Machine Learning Approach for Structural Overload Classification in Railway Bridges - Elsevier Structures Paper","Weigh-in-motion (WIM) measurements of train axle loads can support economical railway bridge safety management, but current structural overload assessment methods using WIM data are time-intensive and often require line closure during analysis. This study develops a supervised machine learning classification approach to speed decision-making and reduce economic loss. Using real WIM data from New Zealand, axle load combinations are classified into “Normal” or “Overload.” Neural network models are shown to achieve F1-scores around 99.2% on an initial small dataset and up to 99.84% with synthetic training data, enabling near real-time overload assessment integrated into WIM post-processing systems.","Structures 71 (2025) 108005  \nContents lists available at ScienceDirect  \nStructures  \njournal [homepage: www.elsevier.com/locate/structures](homepage: www.elsevier.com/locate/structures)  \n| A supervised machine learning approach for structural overload classification in railway bridges using weigh-in-motion data |  |  |  |\n| --- | --- | --- | --- |\n| N.T. Lea,b, M. Keenana,c, A. Nguyen a,*, S. Ghazvinehd, Y. Yue, J. Lif, A. Manaloa\u003Cbr>a University of Southern Queensland, Australia b Hanoi University of Civil Engineering, Vietnam c KiwiRail, New Zealand\u003Cbr>d Kharazmi University, Iran\u003Cbr>e University of New South Wales, Australia f University of Technology Sydney, Australia |  |  |  |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Weigh-in-Motion\u003Cbr>Railway Bridge\u003Cbr>Structural Overload Assessment Axle Load Combination Supervised Machine Learning |  | Weigh-in-motion (WIM) data provides valuable information on vehicle axle load, enabling efficient and economical railway structural safety management programs. However, the current method for assessing structural overload on railway bridges using WIM data is time-consuming and often requires line closure while analyses are being conducted. This paper presents the development of a novel supervised machine learning (ML) approach that can be used as an assessment tool to expedite the decision-making process and minimise economic loss. Variables for model input are carefully considered by analysing real WIM data obtained from measurement sites in New Zealand. Various supervised ML classification models are evaluated for their capability in classifying axle load combinations (ALC) into “Normal”, meaning safe to go, or “Overload”, meaning that line closure is required for detailed inspection of the affected bridges. It is found that the model using Neural Network (NN) outperforms other candidates in this capacity and is therefore selected for detailed model development. An initial investigation using a small dataset derived from real WIM measurements demonstrates that the NN model can achieve impressive evaluation metrics such as F1-score of 99.2 %. Subsequently, a method for artificially generating synthetic ALC data is proposed to create extensive training datasets for comprehensive structural overload model development. It is demonstrated that with sufficient overload data in the training dataset, the model can achieve an exceptional performance, reaching an F1-score of 99.84 % or higher for a single overload level and 99.5 % to 99.86 % for multiple overload thresholds. The developed model can be integrated into the WIM post-processing systems, providing a real-time bridge overload assessment tool that facilitates more efficient and cost-effective railway structural safety management. |  |\n\n1. Introduction  \nRailway transport infrastructure is crucial for any society as they provide an efficient, high-capacity mode of transport over long distances, facilitating the movement of goods and people, which is vital for economic growth and connectivity. Bridges are a key component of the railway network that help to overcome geographical barriers such as rivers and valleys. As reported by its Transport Agency [1], New Zealand has more than 1600 rail bridges, spanning more than 60 kilometres.  \nHowever, a significant number of these bridges are of considerable age, on average being close to 80 years old, which means that they are reaching the end of their designed lifespans. Similar situations are reported around the world [2,3]. As these critical structures approach the end of their service life, designing cost-effective strategies for accommodating emerging transportation needs and mitigating potential dangers are essential [4]. Although structural health monitoring techniques can provide valuable insight into the bridge’s resistant capacity from time to time [5-7], it is equally important to control the vehicle live  \nAbbreviations: AI, Artificial Intelligent; ALC, Axle","cbCainT5kCjsMPOS","https://ap.wps.com/l/cbCainT5kCjsMPOS","pdf",13833788,1,18,"English","en",105,"# Introduction\n## Background and need for overload assessment\n# Machine learning classification approach\n## Data sources and input variables\n## Model evaluation and selection\n# Synthetic data generation\n## Training dataset expansion for robust thresholds\n# Performance and integration\n## Real-time assessment in WIM post-processing","[{\"question\":\"What problem does the supervised ML approach address in railway bridge safety management?\",\"answer\":\"It addresses the slow, analysis-intensive process of assessing structural overload on railway bridges using weigh-in-motion data, which can require line closure during detailed inspection decisions.\"},{\"question\":\"How are axle load combinations classified in the proposed method?\",\"answer\":\"Axle load combinations extracted from WIM data are classified into “Normal” (safe to go) or “Overload” (line closure required for detailed inspection).\"},{\"question\":\"Why does the paper use neural networks instead of other supervised classifiers?\",\"answer\":\"Evaluated supervised classification models show that the neural network outperforms the alternatives for classifying axle load combinations.\"}]","A Supervised Machine Learning Approach for Structural Overload Classification in Railway Bridges - Elsevier Structures Paper | PDF",1785676989,45,{"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},"a-supervised-machine-learning-approach-for-structural-overload-classification-in-railway-bridges-elsevier-structures-paper","",{"@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/a-supervised-machine-learning-approach-for-structural-overload-classification-in-railway-bridges-elsevier-structures-paper/117560/",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","2026-08-02",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the supervised ML approach address in railway bridge safety management?","Question",{"text":75,"@type":76},"It addresses the slow, analysis-intensive process of assessing structural overload on railway bridges using weigh-in-motion data, which can require line closure during detailed inspection decisions.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How are axle load combinations classified in the proposed method?",{"text":80,"@type":76},"Axle load combinations extracted from WIM data are classified into “Normal” (safe to go) or “Overload” (line closure required for detailed inspection).",{"name":82,"@type":73,"acceptedAnswer":83},"Why does the paper use neural networks instead of other supervised classifiers?",{"text":84,"@type":76},"Evaluated supervised classification models show that the neural network outperforms the alternatives for classifying axle load combinations.","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"]