[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-118237-en":3,"doc-seo-118237-105":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},118237,1099514068035,"Ezra","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Aided Uncertainty Quantification for Engineering Structures - Thesis","Uncertainty is intrinsic to engineering practice and arises from material properties, structural geometry, load and environmental conditions, which directly influence structural performance and contribute to incidents and accidents. To represent uncertainty more comprehensively, the thesis investigates hybrid models including polyphase and polymorphic uncertainty as well as imperfect datasets, while addressing the resulting increase in modeling complexity. It proposes machine learning-aided structural reliability analysis strategies that build surrogate models for structural responses, enabling cost-efficient sampling, robust estimation of fuzzy-valued PDFs/CDFs, and updates of predictions without rerunning exhaustive Monte Carlo simulation.","Machine Learning Aided Uncertainty Quantification for Engineering Structures  \nAuthor:  \nWang , Qihan  \nPublication Date:  \n2024  \nDOI:  \n[https://doi.org/10.26190/unsworks/30149](https://doi.org/10.26190/unsworks/30149)  \nLicense:  \n[https://creativecommons.org/licenses/by/4.0/](https://creativecommons.org/licenses/by/4.0/)  \nLink to license to see what you are allowed to do with this resource.  \nDownloaded from [http://hdl.handle. net/1959.4/102220](http://hdl.handle. net/1959.4/102220) in [https://](https://)[ ](https://)[unsworks. unsw.edu.au](unsworks. unsw.edu.au) on 2024-10-11  \nMachine Learning Aided Uncertainty Quantification for Engineering Structures  \nQihan Wang  \nA thesis in fulfilment of the requirements for the degree of  \nDoctor of Philosophy  \nSchool of Civil and Environmental Engineering The University of New South Wales Sydney, Australia  \nMarch 2024  \nDeclarations  \nPublications Statement  \nAbstract  \nUncertainty is an inherent feature in engineering applications. The uncertainty exists within the material properties, structural geometry, load conditions, environments, etc. Furthermore, they can be reflected in structural performance. Numerous structural incidents and accidents have continuously revealed that appropriate consideration of these effects is necessary.  \nTo describe the uncertainty in engineering more generally, several hybrid uncertainty models are investigated, including polyphase uncertainty, polymorphic uncertainty, and ‘imperfect’ datasets. Involving these uncertainties, the complexity of the system surges dramatically. Thus, to provide operationally feasible access to quantify the effects of these uncertainties on structural performance, this thesis proposes novel machine learning-aided structural reliability analysis strategies. Through machine learning techniques, surrogate models are constructed to alternatively replicate the relationship between the inputs and the concerned structural response. Technically, three machine learning techniques, viz., the Twin Extended Support Vector Regression (TXSVR), the Capped Extended Support Vector Regression (CX-SVR), and the AdaBoost Extended Support Vector Regression (Ada-X-SVR), are developed with specific features. The generality and user-friendliness of the proposed scheme are further improved by some built-in novel kernel functions, Bayesian hyperparameter auto-tuning, and other strategies.  \nThen, based on these surrogate models, sampling methods and optimization programming can be implemented with greatly reduced computational costs. A sufficient amount of statistical information can be estimated, e.g., fuzzy-valued probability density function (PDF) and cumulative distribution function (CDF) of the bounds of interest, when the fuzziness and randomness are integrated. Moreover, the proposed approaches provide high robustness: unrestricted selection of inputs and outputs, membership functions for fuzzy sets, distribution types for random variables, geometric and material uncertainties, and various physical problems. In addition, information updates can be another inherent feature of the proposed approach. Without the necessary of re-running the exhaustive Monte Carlo simulation (MCS) on the physical models, the established surrogate models significantly facilitate the programs to achieve predictions of interest on the updated information.  \nGenerally, this research proposes several improved machine learning methods and these methods aided structural analyses to provide possible solutions for practice-stimulated challenges, i.e., structural analyses with polyphase uncertainty, polymorphic uncertainty, and material-geometric uncertainties. These proposed machine learning techniques and their corresponding structural reliability analysis methods are expected to serve engineering applications and potentially benefit condition-based maintenance, structural health monitoring, and smart cities.  \nAcknowledgments  \nFirstly, my heartfelt appreciation","cbCaiuHD24hsqwaK","https://ap.wps.com/l/cbCaiuHD24hsqwaK","pdf",13266805,1,374,"English","en",105,"# Abstract\n## Uncertainty in engineering applications\n## Hybrid uncertainty models\n## Machine learning-aided reliability analysis strategies\n## Surrogate models and computational efficiency\n## Sampling, optimization, and robustness\n## Prediction updating and reduced Monte Carlo cost\n## Applications and expected benefits","[{\"question\":\"What types of uncertainty are addressed in the thesis?\",\"answer\":\"The thesis considers uncertainty in material properties, structural geometry, load conditions, and environments. It further investigates hybrid uncertainty models such as polyphase uncertainty, polymorphic uncertainty, and imperfect datasets.\"},{\"question\":\"How does the proposed method reduce computational cost?\",\"answer\":\"Machine learning surrogate models replicate the relationship between inputs and structural responses. These surrogates enable sampling and optimization with greatly reduced computational costs compared with exhaustive Monte Carlo simulation.\"},{\"question\":\"Which machine learning techniques are developed for surrogate modeling?\",\"answer\":\"The thesis develops three techniques: Twin Extended Support Vector Regression (TXSVR), Capped Extended Support Vector Regression (CX-SVR), and AdaBoost Extended Support Vector Regression (Ada-X-SVR), together with novel kernel functions and Bayesian hyperparameter auto-tuning.\"}]","Machine Learning Aided Uncertainty Quantification for Engineering Structures - Thesis | PDF",1785682543,942,{"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},"machine-learning-aided-uncertainty-quantification-for-engineering-structures-thesis","",{"@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/machine-learning-aided-uncertainty-quantification-for-engineering-structures-thesis/118237/",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 types of uncertainty are addressed in the thesis?","Question",{"text":75,"@type":76},"The thesis considers uncertainty in material properties, structural geometry, load conditions, and environments. It further investigates hybrid uncertainty models such as polyphase uncertainty, polymorphic uncertainty, and imperfect datasets.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed method reduce computational cost?",{"text":80,"@type":76},"Machine learning surrogate models replicate the relationship between inputs and structural responses. These surrogates enable sampling and optimization with greatly reduced computational costs compared with exhaustive Monte Carlo simulation.",{"name":82,"@type":73,"acceptedAnswer":83},"Which machine learning techniques are developed for surrogate modeling?",{"text":84,"@type":76},"The thesis develops three techniques: Twin Extended Support Vector Regression (TXSVR), Capped Extended Support Vector Regression (CX-SVR), and AdaBoost Extended Support Vector Regression (Ada-X-SVR), together with novel kernel functions and Bayesian hyperparameter auto-tuning.","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"]