[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122557-en":3,"doc-seo-122557-105":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},122557,13056703020460,"Valentina","https://ap-avatar.wpscdn.com/avatar/be000253dac470eee5d?_k=1778207105932848923",8,"Research & Report","Probabilistic machine learning for the elimination of thermoacoustic instabilities","Thermoacoustic instabilities have long obstructed the development of high energy density combustors used in jet engines, gas turbines, and rockets, largely because they are difficult to model and can arise unexpectedly. This thesis applies Bayesian machine learning to model, design against, and avoid thermoacoustic instabilities. Bayesian neural networks assimilate flame-derived parameters to make qualitative instability models quantitatively accurate, while gradient-augmented Bayesian optimization optimizes unstable combustor geometry with fewer evaluations. The work also predicts stability from sensor histories and provides uncertainty estimates and interpretable attributions, enabling real-time monitoring in a Rijke tube and earlier instability precursors in an experimental rocket chamber.","Probabilistic machine learning for the elimination of thermoacoustic instabilities  \nUshnish Sengupta  \nSupervisor: Professor Carl Rasmussen  \nAdvisor: Professor Matthew Juniper  \nDepartment of Engineering  \nUniversity of Cambridge  \nThis dissertation is submitted for the degree of Doctor of Philosophy  \nClare College September 2022  \nDeclaration  \nThis thesis is the result of my own work and includes nothing which is the outcome of work done in collaboration except as declared in the preface and specified in the text. It is not substantially the same as any work that has already been submitted, or is being concurrently submitted, for any degree, diploma or other qualification at the University of Cambridge or any other University or similar institution except as declared in the preface and specified in the text. It does not exceed the prescribed word limit for the relevant Degree Committee.  \nUshnish Sengupta September 2022  \nAbstract  \nThermoacoustic instabilities have hindered the development of high energy density combustors, such as those in jet engines, gas turbines or rockets, for decades. They are notoriously difficult to model and despite efforts to eliminate them, can show up unexpectedly. The current thesis demonstrates how Bayesian machine learning techniques may be of benefit when modeling, designing against and trying to avoid thermoacoustic instabilities. We show that Bayesian Neural Network can be used to assimilate model parameters from flame data and make our qualitative instability models quantitatively accurate. Next, we use gradient-augmented Bayesian optimization to globally optimize the geometric parameters of a thermoacoustically unstable combustor design. The Bayesian algorithm automatically manages the trade-off between exploration and exploitation and therefore, requires fewer evaluations of the underlying adjoint model to arrive at the global optimum. We also use Bayesian neural networks to learn functional relationships between sensor data and measures of thermoacoustic stability. First, we demonstrate on a laboratory-scale Rijke tube driven by a turbulent flame that it is possible to predict decay rates of acoustic pulses from the spectrum of 100 millisecond combustion noise samples, thus enabling us to monitor the combustor’s thermoacoustic stability in real time. We then apply these ideas to predict instabilities in an experimental rocket chamber, where we use the history of sensor data, including measurements of dynamic pressure, temperature, static pressure, etc. to find precursors of instabilities upto 500 milliseconds before they occur. The Bayesian nature of our algorithms allows principled estimates of uncertainty to accompany each prediction while the technique of Integrated Gradients lets us interpret our models.  \nIt is hoped that this thesis will serve as a first step towards establishing Bayesian machine learning techniques as tools to help us model combustion instabilities better, design against them and discover trustworthy, robust and reliable instability prognostics.  \nDedicated to my parents.  \nAcknowledgements  \nI’m deeply grateful to my advisor Professor Matthew Juniper, who, for the last four years, made sure to meet me every week and provide the support that I needed. Whether I got stuck on a specific technical issue, needed to discuss the direction or significance of our work or wanted help with mundane administrative matters, Matthew was always there. Research is typically a task with sparse and underspecified rewards and it is hard to overstate the importance of his regular feedback and enthusiasm. I would also like to thank my supervisor Professor Carl Rasmussen for his encouragement and advice. I’d like to acknowledge the Hopkinson lab technicians Roy Slater and Mark Garner because it would have been impossible to set up the experiments in Chapters 3 and 5 without their aid.  \nI am also thankful for the funding I received from the European Union’s Horizon 2020 research a","cbCaifxZJzNkJPe5","https://ap.wps.com/l/cbCaifxZJzNkJPe5","pdf",6525740,1,99,"English","en",105,"# Table of contents\n## 1 Introduction\n## 1.1 The problem of thermoacoustic instabilities\n## 1.2 Mitigation strategies for thermoacoustic instabilities\n## 1.3 Opportunities for Probabilistic Machine Learning\n## 2 Bayesian machine learning\n## 2.1 Introduction\n## 2.2 Uncertainty Quantification in Machine Learning Models\n## 2.3 Bayesian neural netw","[{\"question\":\"How does the thesis use Bayesian neural networks for thermoacoustic instability modeling?\",\"answer\":\"It uses Bayesian neural networks to assimilate model parameters from flame data, turning qualitative instability models into quantitatively accurate ones.\"},{\"question\":\"What is the role of gradient-augmented Bayesian optimization in the combustor design workflow?\",\"answer\":\"It globally optimizes geometric parameters of an unstable combustor, automatically balancing exploration and exploitation to reach the global optimum with fewer evaluations of the underlying adjoint model.\"},{\"question\":\"How are instability predictions generated from experimental sensor data?\",\"answer\":\"Bayesian neural networks learn functional relationships between sensor measurements and thermoacoustic stability metrics; predictions include principled uncertainty estimates, and integrated gradients are used for model interpretability.\"}]","Probabilistic machine learning for the elimination of thermoacoustic instabilities | PDF",1785811282,249,{"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},"probabilistic-machine-learning-for-the-elimination-of-thermoacoustic-instabilities","",{"@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/probabilistic-machine-learning-for-the-elimination-of-thermoacoustic-instabilities/122557/",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","2026-08-04",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},"How does the thesis use Bayesian neural networks for thermoacoustic instability modeling?","Question",{"text":75,"@type":76},"It uses Bayesian neural networks to assimilate model parameters from flame data, turning qualitative instability models into quantitatively accurate ones.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the role of gradient-augmented Bayesian optimization in the combustor design workflow?",{"text":80,"@type":76},"It globally optimizes geometric parameters of an unstable combustor, automatically balancing exploration and exploitation to reach the global optimum with fewer evaluations of the underlying adjoint model.",{"name":82,"@type":73,"acceptedAnswer":83},"How are instability predictions generated from experimental sensor data?",{"text":84,"@type":76},"Bayesian neural networks learn functional relationships between sensor measurements and thermoacoustic stability metrics; predictions include principled uncertainty estimates, and integrated gradients are used for model interpretability.","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"]