[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-seo-291208-105":3,"detail-sidebar-cat-0-en-105":81,"doc-detail-291208-en":131},{"code":4,"msg":5,"data":6},0,"ok",{"site_id":7,"language":8,"slug":9,"title":10,"keywords":11,"description":12,"schema_data":13,"social_meta":74,"head_meta":76,"extra_data":78,"updated_unix":80},105,"en","critical-comparison-of-potential-machine-learning-methods-for-lightning-thermal-damage-assessment-of-composite-laminates","Critical comparison of potential machine learning methods for lightning thermal damage assessment of composite laminates","","The study evaluates supervised machine learning approaches for predicting the extent of lightning thermal damage in fiber-reinforced composite laminates, using linear regression, decision tree models, and multilayer perceptron (MLP) regression. Models rely on ten most influential factors covering current waveform characteristics, composite material configurations, and orthogonal electrical conductivities. Results show strong predictive ability with R2 between 0.84 and 0.96, with the tuned MLP achieving the best performance (R2 > 0.94) and faster convergence. The findings support ML-based regression as an efficient first-pass estimator to reduce costly, time-intensive lightning testing and streamline future damage-model development.",{"@graph":14,"@context":73},[15,34,56],{"@type":16,"itemListElement":17},"BreadcrumbList",[18,23,27,31],{"item":19,"name":20,"@type":21,"position":22},"https://docshare.wps.com","Home","ListItem",1,{"item":24,"name":25,"@type":21,"position":26},"https://docshare.wps.com/document/","Document",2,{"item":28,"name":29,"@type":21,"position":30},"https://docshare.wps.com/document/research-report/","Research & Report",3,{"item":32,"name":10,"@type":21,"position":33},"https://docshare.wps.com/document/critical-comparison-of-potential-machine-learning-methods-for-lightning-thermal-damage-assessment-of-composite-laminates/291208/",4,{"url":32,"name":10,"@type":35,"image":36,"author":41,"headline":10,"publisher":44,"fileFormat":47,"inLanguage":8,"description":12,"dateModified":48,"datePublished":49,"encodingFormat":47,"isAccessibleForFree":50,"interactionStatistic":51},"DigitalDocument",{"url":37,"@type":38,"width":39,"height":40},"https://docshare.wps.com/thumbnails/critical-comparison-of-potential-machine-learning-methods-for-lightning-thermal-damage-assessment-of-composite-laminates/291208.png","ImageObject",300,407,{"name":42,"@type":43},"Valentina","Person",{"url":19,"name":45,"@type":46},"DocShare","Organization","application/pdf","2026-11-07","2026-09-17",true,{"@type":52,"interactionType":53,"userInteractionCount":55},"InteractionCounter",{"@type":54},"ViewAction",17,{"@type":57,"mainEntity":58},"FAQPage",[59,65,69],{"name":60,"@type":61,"acceptedAnswer":62},"Which supervised machine learning algorithms are compared for lightning thermal damage assessment?","Question",{"text":63,"@type":64},"The paper compares linear regression, decision tree-based models, and multilayer perceptron (MLP) regression models.","Answer",{"name":66,"@type":61,"acceptedAnswer":67},"What input factors are used to predict lightning thermal damage severity?",{"text":68,"@type":64},"The models use ten key factors: three current waveform parameters, four material configuration factors, and three orthogonal electrical conductivities for each composite.",{"name":70,"@type":61,"acceptedAnswer":71},"How effective is the best-performing model?",{"text":72,"@type":64},"The tuned MLP regression model shows the most promising results, achieving R2 greater than 0.94, and hyperparameter optimization improves performance slightly while speeding up convergence.","https://schema.org",{"og:url":32,"og:type":75,"og:title":10,"og:site_name":45,"og:description":12},"article",{"robots":77,"canonical":32},"index,follow",{"doc_id":79,"site_id":7},291208,1789643744,{"code":4,"msg":82,"data":83},"success",[84,88,92,96,101,106,111,115,120,123,127],{"id":22,"doc_module":4,"doc_module_name":25,"category_name":85,"show_sort_weight":86,"slug":87},"Story & Novel",90,"story-novel",{"id":26,"doc_module":4,"doc_module_name":25,"category_name":89,"show_sort_weight":90,"slug":91},"Literature",80,"literature",{"id":33,"doc_module":4,"doc_module_name":25,"category_name":93,"show_sort_weight":94,"slug":95},"Exam",70,"exam",{"id":97,"doc_module":4,"doc_module_name":25,"category_name":98,"show_sort_weight":99,"slug":100},5,"Comic",60,"comic",{"id":102,"doc_module":4,"doc_module_name":25,"category_name":103,"show_sort_weight":104,"slug":105},6,"Technology",50,"technology",{"id":107,"doc_module":4,"doc_module_name":25,"category_name":108,"show_sort_weight":109,"slug":110},7,"Healthcare",40,"healthcare",{"id":112,"doc_module":4,"doc_module_name":25,"category_name":29,"show_sort_weight":113,"slug":114},8,30,"research-report",{"id":116,"doc_module":4,"doc_module_name":25,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":25,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":25,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":25,"category_name":129,"show_sort_weight":97,"slug":130},19,"General","general",{"code":4,"msg":82,"data":132},{"doc_id":79,"user_id":133,"nickname":42,"user_avatar":134,"doc_module":4,"category_id":112,"category_name":29,"doc_title":10,"doc_description":12,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":55,"is_deleted":4,"is_public":22,"is_downloadable":22,"audit_status":22,"page_count":140,"language":141,"language_code":8,"site_id":7,"html_lang":8,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":12,"update_tm":80,"read_time":145,"preview_page_count":4},13056703020460,"https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923","Advanced Composite Materials, 2024  \nVol. 00, No. 00, 1–21, [https://doi.org/10.1080/09243046.2024.2416169](https://doi.org/10.1080/09243046.2024.2416169)  \nRESEARCH ARTICLE  \nCritical comparison of potential machine learning methods for lightning thermal damage assessment of composite laminates  \nJuhyeong Lee a, Scott L.J. Millen b and Xiaodong Xu c  \naDepartment ofMechanical and Aerospace Engineering, Utah State University, 84322 Logan, UT, USA; bSchool of Mechanical and Aerospace Engineering, Queen ’s University Belfast, BT9 5AH Belfast, UK; cCentre for Aeronautics, Faculty of Engineering and Applied Sciences, Cranfield  \nUniversity, MK43 0AL Cranfield, UK  \n(Received 12 June 2024; accepted 7 October 2024)  \nThe present study assesses the potential of using machine learning (ML) methods to predict the extent of lightning thermal damage in fiber-reinforced composite laminates using three supervised machine learning (SML) algorithms: (1) linear regression (LR),(2) decision tree (DT)-based, and (3) MLP models. These models were based on the 10 most significant factors that influence the severity of lightning damage, including three current waveform parameters, four material configurations, and three orthogonal electrical conductivities of each composite. All models demonstrated good performance with coefficient of determination (R2) values between 0.84 ~ 0.96. The multilayer perceptron (MLP) regression model trained with the lightning matrix damage dataset showed the most promising results (R2 > 0.94). Additional hyperparameter optimization was performed to improve the prediction performance of the baseline MLP model. The hyperparameter optimization (Adam optimizer, tanh activation function, and three hidden layers with 234 neurons) slightly improved the performance of the baseline MLP model by~0.02, but achieved faster convergence. This result suggests that the baseline MLP model trained with the lightning matrix damage dataset is sufficiently accurate and robust. This paper highlights that MLinformed regression models can serve as an efficient first pass-estimator of lightning matrix damage in composite laminates, potentially reducing the amount of extremely timeconsuming and expensive laboratory-scale lightning tests or streamlining the development of complex lightning damage models for future design.  \nKeywords: Lightning damage assessment; supervised machine learning; multilayer perceptron; composites  \n1. Introduction  \nCompleting experimental lightning strike testing on composite materials is extremely expensive and time-consuming. This means accurate characterization of lightning damage resistance is challenging. In addition, there is no standard measure or method to assess lightning damage. This presents significant challenges in understanding complex lightning interactions and damage mechanisms. As such, this can limit the design of new generation, high-performance aerospace structures.  \nCorresponding author. Juhyeong Lee Email: [Juhyeong.Lee@usu.edu](Juhyeong.Lee@usu.edu); Scott L.J. Millen Email: [Scott.Millen@qub.ac.uk](Scott.Millen@qub.ac.uk)  \n© 2024 The Author(s) . Published by Informa UK Limited, trading as Taylor & Francis Group.  \nThis is an Open Access article distributed under the terms of the Creative Commons Attribution-NonCommercialNoDerivatives License ([http://creativecommons.org/licenses/by-nc-nd/4.0/](http://creativecommons.org/licenses/by-nc-nd/4.0/)), which permits non-commercial re-use, distribution, and reproduction in any medium, provided the original work is properly cited, and is not altered, transformed, or built upon in any way. The terms on which this article has been published allow the posting of the Accepted Manuscript in a repository by the author(s) or with their consent.  \n2 J. Lee et al.  \nLightning has been standardized into four discrete Waveforms A–D used for both experimental and simulation-based research. Waveform A is characterized as the first return stroke; Waveform B is th","cbCaigTi9yF3dQt3","https://ap.wps.com/l/cbCaigTi9yF3dQt3","pdf",7300869,22,"English","# Introduction\n## Machine learning for lightning damage prediction\n## Lightning waveforms and damage mechanisms\n# Simulation and conventional models\n## Finite element analysis approaches\n## Deterministic thermal-damage modeling","[{\"question\":\"Which supervised machine learning algorithms are compared for lightning thermal damage assessment?\",\"answer\":\"The paper compares linear regression, decision tree-based models, and multilayer perceptron (MLP) regression models.\"},{\"question\":\"What input factors are used to predict lightning thermal damage severity?\",\"answer\":\"The models use ten key factors: three current waveform parameters, four material configuration factors, and three orthogonal electrical conductivities for each composite.\"},{\"question\":\"How effective is the best-performing model?\",\"answer\":\"The tuned MLP regression model shows the most promising results, achieving R2 greater than 0.94, and hyperparameter optimization improves performance slightly while speeding up convergence.\"}]","Critical comparison of potential machine learning methods for lightning thermal damage assessment of composite laminates | PDF",55]