[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-291092-105":59,"doc-detail-291092-en":131},{"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":124,"head_meta":126,"extra_data":128,"updated_unix":130},105,"en","system-identification-using-machine-learning-methods","System Identification Using Machine Learning Methods","","Accurate dynamic models are essential in chemical process engineering for control, optimization, and safety, yet nonlinear dynamics often limit linear representations. This thesis evaluates modern machine-learning system identification methods against classical approaches on nonlinear benchmarks, focusing on the accuracy–complexity–robustness trade-off. A simulated two-tank SISO system and a quadruple-tank MIMO system are studied in minimum- and nonminimum-phase regimes. Candidate models use NARX formulations (linear Polynomial ARX, nonlinear Polynomial NARX, Neural NARX, and a CatBoost-based NARX ensemble) trained from white-box-generated datasets and assessed via free-run simulation.",{"@graph":69,"@context":123},[70,84,106],{"@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/system-identification-using-machine-learning-methods/291092/",{"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/system-identification-using-machine-learning-methods/291092.png","ImageObject",300,407,{"name":92,"@type":93},"Theodora","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-31","2026-09-17",true,{"@type":102,"interactionType":103,"userInteractionCount":105},"InteractionCounter",{"@type":104},"ViewAction",15,{"@type":107,"mainEntity":108},"FAQPage",[109,115,119],{"name":110,"@type":111,"acceptedAnswer":112},"What is the core purpose of system identification in this thesis?","Question",{"text":113,"@type":114},"To build predictive dynamic models from observed input-output data, enabling simulation and improved control decisions when first-principles modeling is infeasible or too complex.","Answer",{"name":116,"@type":111,"acceptedAnswer":117},"Which benchmark systems are used for evaluation?",{"text":118,"@type":114},"A simulated two-tank single-input single-output process and a quadruple-tank multiple-input multiple-output system, tested in both minimum-phase and nonminimum-phase regimes.",{"name":120,"@type":111,"acceptedAnswer":121},"What modeling framework and candidate model types are compared?",{"text":122,"@type":114},"All candidate models are expressed in a NARX framework and compared as linear Polynomial ARX, nonlinear Polynomial NARX, a feedforward Neural NARX, and a CatBoost-based NARX ensemble.","https://schema.org",{"og:url":83,"og:type":125,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":127,"canonical":83},"index,follow",{"doc_id":129,"site_id":62},291092,1789643428,{"code":4,"msg":5,"data":132},{"doc_id":129,"user_id":133,"nickname":92,"user_avatar":134,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":135,"file_id":136,"file_url":137,"file_type":138,"file_size":139,"view_count":105,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":140,"language":141,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":142,"faqs":143,"seo_title":144,"seo_description":67,"update_tm":130,"read_time":145,"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","System Identification Using Machine Learning Methods  \nTesi di Laurea Magistrale in  \nChemical Engineering-Ingegneria Chimica  \nKasra Abdolahzade, 10876117  \nAdvisor:  \nProf. Mattia Vallerio  \nCo-advisors:  \nProf. Flavio Manenti  \nDr. Francisco J. NavarroBrull  \nAcademic year:  \n2024-2025  \nAbstract: Accurate dynamic models are critical in chemical process engineering for control, optimization, and safety, yet many processes exhibit nonlinear dynamics that linear models fail to capture. This thesis investigates how modern machine-learning-based system identification methods compare with classical approaches on nonlinear process benchmarks and examines which models offer the best trade-off between accuracy, complexity, and robustness. Two benchmark systems are studied: a simulated two-tank single-input single-output (SISO) process and a quadruple-tank multiple-input multiple-output (MIMO) system, considered in both minimum-phase and nonminimum-phase operating regimes. The inputoutput datasets were generated by simulating the established white-box models for both the two-tank and quadruple-tank systems. All candidate models are formulated in a Nonlinear AutoRegressive with eXogenous input (NARX) framework and trained in series–parallel mode, then evaluated in free-run simulation. The study compares linear Polynomial ARX and nonlinear Polynomial NARX models, a feedforward Neural NARX model, and a CatBoost-based NARX ensemble. The results show that models using only linear regressors are fundamentally limited, whereas nonlinear models achieve substantially higher fidelity. Polynomial NARX and CatBoost NARX with degree = 2 regressors provide clearly better accuracy on the two benchmarks, with Polynomial NARX achieving the highest accuracy overall. The Neural NARX model proves highly sensitive to configuration, performing reasonably with linear regressors but becoming unstable with nonlinear inputs. Overall, the thesis demonstrates that structured nonlinear models such as Polynomial NARX and tree-based ensemble methods like CatBoost can provide highfidelity dynamic models suitable for demanding applications. In the context of process safety, these findings support the use of accurate data-driven models asa basis for advanced monitoring, anomaly detection, and model-based control in chemical process systems.  \nKey-words: System Identification, Machine Learning, Nonlinear System Identification, Black-Box Modeling, Polynomial NARX, CatBoost  \n1. Introduction  \nSystem Identification (SI) is commonly defined as \"the art and science of building mathematical models of dynamical processes from observed input and output signals\" [15, 17] . In essence, SI turns experimental or  \noperational data into a predictive model of a system’s behavior. This data-driven approach is invaluable in situations where first-principles modeling (based on underlying physics or chemistry) is infeasible or overly complex. Indeed, for many real-world processes, deriving a complete analytical model from first principles is either too time-consuming or fundamentally impossible. In such cases, SI offers a practical alternative by empirically determining a model that links inputs to outputs. The resulting models enable engineers to simulate system behavior, design and tune controllers, and perform system analyses without disrupting the actual plant [15, 17] .  \nThis ability to obtain reliable models directly from data has made SI a cornerstone of modern control engineering. Successful applications span a wide range of fields—from aerospace and automotive systems to economics and biology—wherever predictive dynamic models are required [1, 17 , 22] .  \n1.1. The Role of System Identification in Chemical Engineering  \nSI techniques are especially vital in the process industries, where the ability to develop accurate mathematical models is crucial for control, optimization, and safety. Chemical processes often involve complex, nonlinear dynamics and unknown parameters that","cbCaifx7aYmM1SX0","https://ap.wps.com/l/cbCaifx7aYmM1SX0","pdf",5784648,32,"English","# Introduction\n## The Role of System Identification in Chemical Engineering\n## Process Safety as a Driver for Data-Driven Modeling","[{\"question\":\"What is the core purpose of system identification in this thesis?\",\"answer\":\"To build predictive dynamic models from observed input-output data, enabling simulation and improved control decisions when first-principles modeling is infeasible or too complex.\"},{\"question\":\"Which benchmark systems are used for evaluation?\",\"answer\":\"A simulated two-tank single-input single-output process and a quadruple-tank multiple-input multiple-output system, tested in both minimum-phase and nonminimum-phase regimes.\"},{\"question\":\"What modeling framework and candidate model types are compared?\",\"answer\":\"All candidate models are expressed in a NARX framework and compared as linear Polynomial ARX, nonlinear Polynomial NARX, a feedforward Neural NARX, and a CatBoost-based NARX ensemble.\"}]","System Identification Using Machine Learning Methods | PDF",81]