[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-122339-en":3,"doc-seo-122339-105":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":20,"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},122339,2336464648746,"Skyler","https://ap-avatar.wpscdn.com/davatar_276721f389ce27ea32af1340a28f341c",8,"Research & Report","Machine Learning Methods for Modeling and Control of Dynamic Systems - Doctoral Dissertation","The dissertation investigates machine learning methods for system identification and model-based control design, with an emphasis on recurrent neural network (RNN) models. It develops RNN identification results by analyzing stability properties such as input-to-state stability (ISS) and incremental ISS, providing training cost regularization to enforce the conditions and improving interpretability through physical information. It further proposes lifelong adaptation after dynamics drift. For control, it studies MPC and IMC, introducing robust offset-free MPC for NNARX models and CA-NNARX-based IMC to accelerate online computation. Industrial temperature control validates the approach.","POLITECNICO DI MILANO DEPARTMENT OF ELECTRONICS, INFORMATION AND BIOENGINEERING  \nDOCTORAL PROGRAMME IN INFORMATION TECHNOLOGY  \nMACHINE LEARNING METHODS FOR MODELING  \nAND CONTROL OF DYNAMIC SYSTEMS  \nDoctoral Dissertation of:  \nJing Xie  \nSupervisor:  \nProf. Riccardo Scattolini  \nTutor:  \nProf. Lorenzo Fagiano  \nThe Chair of the Doctoral Program:  \nProf. Luigi Piroddi  \n2021 – XXXVI Cycle  \n无用之用，方为大用  \n—庄子  \nThe usefulness of unusefulness is the greatest usefulness  \n—Zhuangzi  \nAcknowledgement  \nC  \nOMPLETING this doctoral thesis has been a journey filled with challenges, growth, and invaluable support from numerous individuals and institutions. As I reflect on this accomplishment, I am filled  \nwith deep gratitude for the many people who have contributed to its realization.  \nFirst and foremost, I extend my profound appreciation to my supervisor, Prof. Riccardo Scattolini, whose guidance and patience have been the cornerstone of this journey. His expertise and mentorship have not only shaped the direction of this research but have also fostered my academic and personal growth.  \nI am deeply grateful to be a part of the European project ELO-X. It does not only provide many opportunities for (free) traveling, but also insightful exchange of ideas and academic experiences. Numerous research and non-research activities have enriched my PhD lives and vastly expand my horizons.  \nI am thankful to Prof. Moritz Diehl for hosting me at University of Freiburg for three months, where I get the chance to learn more about optimization theory and German beer culture. I am also appreciative of my exchange spent at Tool-Temp in Switzerland. Working with Leo and Jonas on first-hand industrial applications has been an enlightening and rewarding experience.  \nMy heartfelt thanks go to my colleagues, Kristoffer, Nicolas, Lorenzos (a couple of them), Laura, Andres, Alessandro, Isabella, Araavind, Luca, Eva, Alessio, Fabio, Lucrezia, Miao, Fei, Rob,..., they are not only my  \nlunch mates, play dates but also sincere friends who make the PhD journey much easier for me.  \nTo my family, I owe an immeasurable debt of gratitude. My mother, father, grandparents, uncle, aunt and three cousins. Their unwavering love and encouragement through countless video chats and huge food packages from China have empowered me to go through the hard times.  \nThis project has received funding from the European Union’s Horizon 2020 research and innovation program under the Marie Sklodowska-Curie grant agreement No. 953348  \nAbstract  \nTHE thesis topic revolves around machine learning methods for sys  \ntem identification and model-based control design, with a specific  \nemphasis on Recurrent Neural Network (RNN) models. The thesis comprises three main parts.  \nThe first part delves into RNN model identification, addressing several key issues. Stability properties such as Input-to-State Stability (ISS) and incremental ISS (δISS) are analyzed, and sufficient conditions are derived. These conditions can be enforced by adding a regularization term to the training cost. Additionally, the incorporation of physical information into RNN model design is explored to enhance interpretability and modeling performance. Furthermore, a lifelong learning method for model adaptation after dynamics drift is proposed.  \nIn the second part of the thesis, the focus shifts to model-based control design. Two schemes are considered: Model Predictive Control (MPC) and Internal Model Control (IMC) . A robust offset-free MPC tracking scheme is proposed for NNARX models, wherein an integrator and derivative action are added to the system model. Moreover, a Control Affine NNARX model is introduced, mirroring the input affine structure of the system dynamics. An IMC scheme leveraging CA-NNARX models is also proposed to expedite online computation.  \nThe final part of the thesis is dedicated to industrial application. A tailored NNARX-based MPC algorithm is implemented for temperature control units","cbCaiul1wOqv4Tpp","https://ap.wps.com/l/cbCaiul1wOqv4Tpp","pdf",9679522,1,153,"English","en",105,"# Abstract\n## RNN model identification\n## Model-based control design (MPC and IMC)\n## Industrial application and validation","[{\"question\":\"What is the dissertation’s main topic and which model family is emphasized?\",\"answer\":\"The thesis focuses on machine learning for system identification and model-based control, with an emphasis on recurrent neural network (RNN) models.\"},{\"question\":\"How does the thesis address stability during RNN model identification?\",\"answer\":\"It analyzes ISS and incremental ISS (δISS) and derives sufficient conditions, which can be enforced by adding a regularization term to the training cost.\"},{\"question\":\"What control strategies are studied and what industrial application is demonstrated?\",\"answer\":\"The thesis considers model predictive control (MPC) and internal model control (IMC), including a robust offset-free MPC for NNARX models and an IMC scheme using CA-NNARX. It demonstrates a tailored NNARX-based MPC algorithm for temperature control units manufactured by Tool-Temp AG.\"}]","Machine Learning Methods for Modeling and Control of Dynamic Systems - Doctoral Dissertation | PDF",1785810106,386,{"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-methods-for-modeling-and-control-of-dynamic-systems-doctoral-dissertation","",{"@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-methods-for-modeling-and-control-of-dynamic-systems-doctoral-dissertation/122339/",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":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What is the dissertation’s main topic and which model family is emphasized?","Question",{"text":75,"@type":76},"The thesis focuses on machine learning for system identification and model-based control, with an emphasis on recurrent neural network (RNN) models.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the thesis address stability during RNN model identification?",{"text":80,"@type":76},"It analyzes ISS and incremental ISS (δISS) and derives sufficient conditions, which can be enforced by adding a regularization term to the training cost.",{"name":82,"@type":73,"acceptedAnswer":83},"What control strategies are studied and what industrial application is demonstrated?",{"text":84,"@type":76},"The thesis considers model predictive control (MPC) and internal model control (IMC), including a robust offset-free MPC for NNARX models and an IMC scheme using CA-NNARX. It demonstrates a tailored NNARX-based MPC algorithm for temperature control units manufactured by Tool-Temp AG.","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"]