[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117988-en":3,"doc-seo-117988-105":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},117988,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Novel models for fatigue life prediction under wideband random loads based on machine learning - Abstract and key methods","Machine learning as a data-driven solution has been widely used for fatigue lifetime prediction. This study constructs three wideband fatigue life prediction models using SVM, GPR, and ANN, and improves generalization by training on many power-spectra samples with different bandwidth parameters together with diverse material properties related to fatigue life. Monte Carlo numerical simulations verify that the proposed machine learning models outperform traditional frequency-domain methods in life prediction accuracy, with the ANN achieving the best overall performance.","Novel models for fatigue life prediction under wideband random loads based on  \nmachine learning  \nHong Sun1, Yuanying Qiu 1, *, Jing Li 1, *, Jin Bai 2, Ming Peng 3  \n1 School of Mechatronic Engineering, Xidian University, No. 2 South Taibai Road, Xi’an, China, 710071.  \n2 Xi’an Aerospace Propulsion Test Technology Institude, Xi’an, China, 710100.  \n3 Hunan Province Motor Vehicle Technician College, Shaoyang, China, 422001.  \n* Corresponding author.  \n[E-mail addresses: yyqiu@mail.xidian.edu.cn](E-mail addresses: yyqiu@mail.xidian.edu.cn) (Yuanying Qiu),  \n[lijing02010303@163.com](lijing02010303@163.com) (Jing Li).  \nAbstract：Machine learning as a data-driven solution has been widely applied in the field of fatigue lifetime prediction. In this paper, three models for wideband fatigue life prediction are built based on three machine learning models, i.e. support vector machine (SVM), Gaussian process regression (GPR) and artificial neural network (ANN) . The generalization ability of the models is enhanced by employing numerous power spectra samples with different bandwidth parameters and a variety of material properties related to fatigue life. Sufficient Monte Carlo numerical simulations demonstrate that the newly developed machine learning models are superior to the traditional frequencydomain models in terms of life prediction accuracy and the ANN model has the best overall performance among the three developed machine learning models.  \nKeywords：Fatigue life prediction Machine learning Bandwidth parameters Frequency-domain models Wideband random loads  \n1.Introduction  \nIn reality, there are many engineering structures subjected to random loads arising from wind, rough pavements and waves [1] . The power spectra of the structural  \nresponse can usually be determined by spectral analysis. Once the power spectra is determined, as illustrated in Fig. 1, there exist generally two approaches [2] for conducting random fatigue life prediction, i.e. the time-domain fatigue analysis (TDFA) and the frequency-domain fatigue analysis (FDFA) .  \nAs for TDFA, firstly the response power spectra is converted into stress timedomain signals through Monte Carlo numerical simulation, then many stress rainflow cycles are obtained from these signals using the rainflow counting [3], and finally the estimation of random fatigue life is achieved by using the amplitudes of stress cycles, material properties and Miner’s rule [4] . With regard to FDFA, every frequency-domain model describing the intricate relation between the power spectra of a random load and the fatigue damage can be used directly to predict random fatigue life, omitting therainflow counting and numerical simulation [2,5-9] .  \n TDFA    \nRandom load spectrum  \nFrequency response function  \nThe response power spectra  \nNumerical simulation  \nStress time-domain signals  \nRandom fatigue life  \nFrequency-domain models  \nRainflow counting  \nFDFA  \nFig. 1 The flowchart of two types of analysis methods for predicting random fatigue life  \nWhile acknowledged as the more precise technique for predicting random fatigue life, TDFA demands significant computational resources [10,11] . Thus, various  \nfrequency-domain models [2,5-9] have been devised to enhance computational efficiency. Remarkably, FDFA using these models achieve a prediction accuracy that is nearly on par with TDFA using the rainflow counting method.  \nFrequency-domain models can be categorized into narrowband and wideband models. For the former, Bendat [7] has formulated the famous narrowband approximation formula, but the result may be rather conservative if this formula is used to estimate the fatigue life of an engineering structure under a wideband random load whose Vanmarcke bandwidth parameter is 0.1 to 0.95 [12] . Therefore, some researchers have developed several wideband models for predicting the wideband random fatigue life [2,5,6,8] . Wirsching and Light [8] adopted a correction factor to modify the wideband rando","cbCaiuGm7Ec8Cnhb","https://ap.wps.com/l/cbCaiuGm7Ec8Cnhb","pdf",1609529,1,23,"English","en",105,"# Introduction\n## Time-domain vs frequency-domain fatigue analysis\n## Wideband models and limitations of existing approaches\n## Machine learning for fatigue life prediction","[{\"question\":\"Which machine learning models are used for wideband fatigue life prediction?\",\"answer\":\"Three models are built: support vector machine (SVM), Gaussian process regression (GPR), and artificial neural network (ANN).\"},{\"question\":\"How does the study improve the generalization ability of the models?\",\"answer\":\"It employs numerous power-spectrum samples with different bandwidth parameters and includes a variety of material properties related to fatigue life in the training dataset.\"},{\"question\":\"How do the proposed machine learning models compare with traditional frequency-domain models?\",\"answer\":\"Monte Carlo numerical simulations show the new machine learning models are superior in prediction accuracy, and the ANN model has the best overall performance among the three.\"}]","Novel models for fatigue life prediction under wideband random loads based on machine learning - Abstract and key methods | PDF",1785680650,58,{"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},"novel-models-for-fatigue-life-prediction-under-wideband-random-loads-based-on-machine-learning-abstract-and-key-methods","",{"@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/novel-models-for-fatigue-life-prediction-under-wideband-random-loads-based-on-machine-learning-abstract-and-key-methods/117988/",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},"Which machine learning models are used for wideband fatigue life prediction?","Question",{"text":75,"@type":76},"Three models are built: support vector machine (SVM), Gaussian process regression (GPR), and artificial neural network (ANN).","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the study improve the generalization ability of the models?",{"text":80,"@type":76},"It employs numerous power-spectrum samples with different bandwidth parameters and includes a variety of material properties related to fatigue life in the training dataset.",{"name":82,"@type":73,"acceptedAnswer":83},"How do the proposed machine learning models compare with traditional frequency-domain models?",{"text":84,"@type":76},"Monte Carlo numerical simulations show the new machine learning models are superior in prediction accuracy, and the ANN model has the best overall performance among the three.","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"]