[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120568-en":3,"doc-seo-120568-105":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},120568,687197207919,"Theodora","https://ap-avatar.wpscdn.com/avatar/a000253d6f5f7c60be?x-image-process=image/resize,m_fixed,w_180,h_180&k=1779446848396160552",8,"Research & Report","Intelligent Control Systems and Machine Learning Approaches for Particle Accelerators","Particle accelerators serve fundamental physics research, medical diagnosis, and industrial applications, yet their operation relies on complex control systems with thousands of sensors and actuators generating massive datasets. This thesis applies machine learning and deep learning to improve performance, increase accelerator uptime, and reduce setup and maintenance effort. Anomaly detection supports fault prediction through classical ML and time-series forecasting models. Reinforcement learning enables beam emittance optimization by online tuning of beam transport parameters. Finally, data-driven dynamic sampling strategies optimize metrology plans for quality control in manufacturing processes.","UNIVERSITY OF PADOVA DEPARTMENT OF INFORMATION ENGINEERING  \nPh.D. Course in Information Engineering  \nIntelligent Control Systems and Machine Learning Approaches for Particle Accelerators  \nSupervisor  \nProf. Gian Antonio Susto  \nPh. D. Student  \nDavide Marcato  \nAcademic Year 2022/2023  \nSeptember 2023  \n2  \nAbstract  \nParticle accelerators are used all around the world for fundamental physics research, medical diagnosis and industrial applications. These can be extremely complex machines, with control systems composed of thousands of sensors and actuators producing an enormous amount of data. By exploiting this data, it’s possible to reach new levels of performance, improve the uptime of the accelerator and reduce the effort required to setup, control and maintain it. This thesis focuses on the application of Machine Learning and Deep Learning models to the field of particle accelerator control systems. Anomaly Detection is applied to the task of fault prediction, both using classical Machine Learning algorithms and Deep Learning time-series forecasting models. By discovering anomalies in the trends of the process variables we can predict the insurgence of fault conditions, or the breakage of a critical component, thus allowing to intervene in time to avoid it. Reinforcement Learning is applied to the task of beam emittance optimization, with the aim of training a model which is able to automatically tune the beam transport parameters online to reach the optimal beam dynamics. These methods are validated on the particle accelerators at the INFN National Laboratories of Legnaro, Italy, but can be extended to other facilities with similar challenges. Finally, we explore data-driven Dynamic Sampling strategies to optimize metrology plans for quality control in industrial manufacturing processes.  \n4  \nContents  \nAbstract 3  \nScientific Publications 9  \n1 Introduction 13  \n2 Particle Accelerators 17  \n2.1 Overview .................................... 17  \n2.2 Particle Accelerators at Legnaro National Laboratories ........... 19  \n2.3 ALPI ....................................... 20  \n2.3.1 RF cavities ............................... 22  \n2.3.2 Control System Architecture ..................... 23  \n2.3.3 The Archiver .............................. 24  \n2.3.4 RF control system ........................... 25  \n2.4 ADIGE ..................................... 27  \n2.4.1 Medium Resolution Mass Separator (MRMS) ............ 29  \n2.5 Control Systems Challenges .......................... 34  \n2.5.1 RF Runtime Faults ........................... 34  \n2.5.2 ADIGE multipole configuration .................... 35  \n3 Machine Learning Elements 37  \n3.1 AI and ML brief introduction ......................... 37  \n3.2 Anomaly Detection ............................... 41  \n3.2.1 Outliers ................................. 42  \n3.2.2 Taxonomy and classes of algorithms ................. 44  \n3.2.3 Performance Metrics .......................... 46  \n3.2.4 Machine Learning Methods ...................... 47  \n3.2.5 Isolation tree based methods ..................... 51  \n3.3 Deep Learning Techniques ........................... 61  \n3.3.1 Vanilla Neural Networks ........................ 61  \n3.3.2 Convolutional Neural Networks (CNNs) ............... 64  \n3.3.3 Autoencoders .............................. 66  \n3.3.4 Deep Learning Forecasting ....................... 67  \n3.4 Reinforcement Learning ............................ 72  \n3.4.1 Value Functions Methods ....................... 75  \n3.4.2 Policy Gradient Methods ....................... 77  \n4 Machine Learning for Particle Accelerators 83  \n4.1 ML in physics laboratories ........................... 83  \n4.2 Literature Review ................................ 85  \n4.2.1 Anomaly detection and Fault Prediction ............... 86  \n4.2.2 Virtual Sensors ............................. 87  \n4.2.3 Beam Dynamics Optimization and Optimal Control ........ 88  \n4.2.4 Industrial applications ......................... ","cbCaikyGqVIVFbu4","https://ap.wps.com/l/cbCaikyGqVIVFbu4","pdf",14092870,1,193,"English","en",105,"# Contents\n## Abstract\n## Scientific Publications\n## 1 Introduction\n## 2 Particle Accelerators\n## 3 Machine Learning Elements\n## 4 Machine Learning for Particle Accelerators\n## 5 Anomaly Detection and Fault Prediction\n## 6 Reinforcement Learning for Beam Emittance Optimization\n## 7 Dynamic Sampling","[{\"question\":\"How does the thesis use machine learning for fault prediction in particle accelerators?\",\"answer\":\"It applies anomaly detection to process variable trends to predict the onset of fault conditions, using both classical machine learning algorithms and deep learning time-series forecasting models.\"},{\"question\":\"What role does reinforcement learning play in the proposed beam emittance optimization?\",\"answer\":\"Reinforcement learning trains a model to automatically tune beam transport parameters online to reach optimal beam dynamics and improve beam emittance.\"},{\"question\":\"What is Dynamic Sampling used for in this work?\",\"answer\":\"The thesis explores data-driven dynamic sampling strategies to optimize metrology plans for quality control in industrial manufacturing processes.\"}]","Intelligent Control Systems and Machine Learning Approaches for Particle Accelerators | PDF",1785730690,486,{"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},"intelligent-control-systems-and-machine-learning-approaches-for-particle-accelerators","",{"@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/intelligent-control-systems-and-machine-learning-approaches-for-particle-accelerators/120568/",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","2026-08-03",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 machine learning for fault prediction in particle accelerators?","Question",{"text":75,"@type":76},"It applies anomaly detection to process variable trends to predict the onset of fault conditions, using both classical machine learning algorithms and deep learning time-series forecasting models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What role does reinforcement learning play in the proposed beam emittance optimization?",{"text":80,"@type":76},"Reinforcement learning trains a model to automatically tune beam transport parameters online to reach optimal beam dynamics and improve beam emittance.",{"name":82,"@type":73,"acceptedAnswer":83},"What is Dynamic Sampling used for in this work?",{"text":84,"@type":76},"The thesis explores data-driven dynamic sampling strategies to optimize metrology plans for quality control in industrial manufacturing processes.","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"]