[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291143-105":59,"doc-detail-291143-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","probabilistic-machine-learning-approaches-towards-diagnostic-and-prognostic-of-degrading-engineering-systems","PROBABILISTIC MACHINE LEARNING APPROACHES TOWARDS DIAGNOSTIC AND PROGNOSTIC OF DEGRADING ENGINEERING SYSTEMS","","Damage detection and prognosis are essential for managing degrading engineering infrastructure, yet conventional practice treats them separately using sensor data for detection and historical failure data for prognosis. This thesis proposes an integrated probabilistic machine learning framework for remaining useful life (RUL) estimation, addressing extrapolation in limited data and extending damage detection via surrogate degradation modeling. The work develops a comprehensive GPR-based prognosis strategy with entropy-assisted genetic search for robust hyperparameter global optimum, change-point localization using a Bayesian approach, and two-stage constraint unscented Kalman filtering for parameter estimation. Applications include elastomeric rubber bearing prognosis and fatigue crack monitoring, with results showing improved fault detection timeliness, uncertainty-aware RUL predictions, and robustness across numerical and experimental validation.",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/probabilistic-machine-learning-approaches-towards-diagnostic-and-prognostic-of-degrading-engineering-systems/291143/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/probabilistic-machine-learning-approaches-towards-diagnostic-and-prognostic-of-degrading-engineering-systems/291143.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-11-03","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":46},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is a holistic approach needed for damage detection and prognosis in degrading engineering systems?","Question",{"text":112,"@type":113},"Damage detection using sensor data and prognosis using historical failure data are often handled separately. A holistic probabilistic framework is required to capture degradation early and support unified RUL estimation.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What major challenge does the thesis address when training data is limited?",{"text":117,"@type":113},"When only partial datasets are available, RUL estimation requires extrapolation, which is difficult. The thesis develops methods to improve accurate predictions beyond the training data range.",{"name":119,"@type":110,"acceptedAnswer":120},"How does the thesis improve hyperparameter optimization for Gaussian Process Regression?",{"text":121,"@type":113},"It proposes an entropy-assisted genetic algorithm that uses Renyi’s entropy to diversify the initial population, achieve global convergence, and reduce the risk of premature optimization and local minima.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},291143,1789643551,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":46,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":14,"language":139,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":140,"faqs":141,"seo_title":142,"seo_description":67,"update_tm":129,"read_time":24,"preview_page_count":4},687197207919,"https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552","INDIAN INSTITUTE OF TECHNOLOGY GUWAHATI SHORT ABSTRACT OF THESIS  \nName of the Student Roll Number  \nProgramme of Study  \n: SHIVAM OJHA  \n: 196104026  \n: Ph. D.  \nThesis Title: : PROBABILISTIC MACHINE LEARNING APPROACHES TOWARDS DIAGNOSTIC AND PROGNOSTIC OF DEGRADING ENGINEERING SYSTEMS  \nName of Thesis Supervisor(s) : Dr. Amit Shelke  \nThesis Submitted to the Department/ Center : Department of Civil Engineering Date of completion of Thesis Viva-Voce Exam : 16-04-2025  \nKey words for description of Thesis Work : Bayesian Filter, Diagnosis, Prognosis, Machine Learning  \nSHORT ABSTRACT  \nDamage detection and prognosis are critical to managing degrading systems in the engineering infrastructure. The damage detection relying on sensor data and prognosis on historical failure data, usually both are treated separately. However, a holistic approach is needed to capture degradation at initial stages and prognosis. When implementing a machine learning framework for remaining useful life (RUL) estimation, two primary scenarios emerge: (1) utilizing a complete run-to-failure dataset for training, and (2) relying on a partial dataset. The latter presents significant challenges due to the necessity for extrapolation. Furthermore, limited research has explored extending damage detection results to RUL estimation by modeling the underlying degradation process using a surrogate measure. Moreover, few studies extend damage detection results to remaining useful life (RUL) estimation by modeling the underlying degradation process using a surrogate measure. An integrated probabilistic machine learning framework that systematically undertakes diagnosis, prognosis, and RUL estimation is lacking in the literature. Additionally, parameters for the surrogate degradation model used for prognosis are often estimated using conjugate gradient methods, which often fall into local minima. These surrogate models also ignore general population trends.  \nThe main objectives of this thesis are threefold: First, a comprehensive prognosis framework is developed that integrates Gaussian Process Regression (GPR) with a robust solution to address extrapolation challenges, ensuring accurate and reliable predictions beyond the training data range. Second, the set of GPR hyperparameters for achieving the global optimum value of maximum likelihood is obtained through the proposed entropy-assisted genetic algorithm. This incorporates Renyi’s entropy to diversify the initial population, achieve global convergence, and  \nmitigate the risk of premature optimization. Finally, the proposed probabilistic framework is applied to real-world scenarios, specifically the prognosis of elastomeric rubber bearings and fatigue crack monitoring in lap joints. The aim is to demonstrate the framework’s practical applicability, effectiveness in predicting RUL, and ability to account for uncertainties in different engineering domains.  \nDamage initiation in these applications is often followed by a sudden change in the degradation path. With this shock, the degradation path changes its trajectory, leading to multi-stage degradation that requires shifting the adaptive mean function. Hence, this thesis attempts to locate change points through a Bayesian approach, presenting  \nAbstract-TH-3624_ 196104026  \ntheoretical formulations for multi-functional forms in two phases (pre and post-change point) with damage detection in the context of structural health monitoring.  \nFor case-specific surrogate measures, the development of a system identification tool using the two-stage constraint unscented Kalman filter (CUKF) is proposed for complex structural systems like elastomeric high damping rubber bearings. These are modeled through the Biaxial Bouc-Wen model to account for bidirectional effects observed in structures under seismic excitations. The effectiveness of the two-stage CUKF in parameter estimation is validated through numerical case studies and experimental validation, establishing a robu","cbCaiuJHwCAv1yao","https://ap.wps.com/l/cbCaiuJHwCAv1yao","pdf",116807,"English","# Thesis Objectives\n## Integrated Probabilistic Framework for Diagnosis, Prognosis, and RUL\n## GPR with Entropy-Assisted Genetic Algorithm\n## Bayesian Change-Point Formulation\n## Case Studies and Validation","[{\"question\":\"Why is a holistic approach needed for damage detection and prognosis in degrading engineering systems?\",\"answer\":\"Damage detection using sensor data and prognosis using historical failure data are often handled separately. A holistic probabilistic framework is required to capture degradation early and support unified RUL estimation.\"},{\"question\":\"What major challenge does the thesis address when training data is limited?\",\"answer\":\"When only partial datasets are available, RUL estimation requires extrapolation, which is difficult. The thesis develops methods to improve accurate predictions beyond the training data range.\"},{\"question\":\"How does the thesis improve hyperparameter optimization for Gaussian Process Regression?\",\"answer\":\"It proposes an entropy-assisted genetic algorithm that uses Renyi’s entropy to diversify the initial population, achieve global convergence, and reduce the risk of premature optimization and local minima.\"}]","PROBABILISTIC MACHINE LEARNING APPROACHES TOWARDS DIAGNOSTIC AND PROGNOSTIC OF DEGRADING ENGINEERING SYSTEMS | PDF"]