[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-126671-en":3,"doc-seo-126671-105":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},126671,962084925502,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_6f874abed73319feea01a86fa6f0fab8",8,"Research & Report","Development of a Surrogate Model of an Amine Scrubbing Digital Twin Using Machine Learning Methods","Advancements in the process industry demand more complex simulations and computationally intensive optimization, which can hit the limits of conventional process models. A surrogate model offers an effective alternative by reproducing a digital-twin workflow with far lower runtime cost. This work develops an industrial amine scrubbing digital twin surrogate using an Aspen HYSYS process simulation validated with steady-state real-plant data. A Latin hypercube design-of-experiments strategy defines nested domains around the nominal condition, multiple machine-learning models are cross-validated, and the best model is selected per target.","Computers and Chemical Engineering 174 (2023) 108252  \n| Development of a surrogate model ofan amine scrubbing digital twin using machine learning methods\u003Cbr>Andrea Galeazzi a, Kristiano Prifti a, Carlo Cortellini a, Alessandro Di Pretorob, Francesco Gallo c, Flavio Manenti a,∗\u003Cbr>a Dipartimento di Chimica, Materiali e Ingegneria Chimica ‘‘Giulio Natta’’, Politecnico di Milano, Piazza Leonardo Da Vinci, 32, Milan, 20133, Italy b Laboratoire de Génie Chimique, Université de Toulouse, CNRS/INP/UPS, Allée E. Monso, 4, Toulouse, 31431, France\u003Cbr>c Itelyum Regeneration S.p.A., Via Tavernelle, 19, Pieve Fissiraga, 26854, Italy |  |  |  |\n| --- | --- | --- | --- |\n| A R T I C L E I N F O |  | A B S T R A C T |  |\n| Keywords:\u003Cbr>Machine-learning Surrogate modeling Digital twin\u003Cbr>Amine scrubbing Design of experiments Latin hypercube |  | Advancements in the process industry require building more complex simulations and performing computationally intensive operations like optimization. To overcome the numerical limit of conventional process simulations a surrogate model is a viable strategy. In this work, a surrogate model of an industrial amine scrubbing digital twin has been developed. The surrogate model has been built based on the process simulation created in Aspen HYSYS and validated as a digital twin against real process data collected during a steady-state operation. The surrogate relies on an accurate Design of Experiments procedure. In this case, the LatinHypercube method has been chosen and several nested domains have been defined in ranges around the nominal steady state operative condition. Several machine learning models have been trained using crossvalidation, and the most accurate has been selected to predict each target. The resulting surrogate model showed a satisfactory performance, given the data available. |  |\n\n1. Introduction  \nThe role of the digital twin will be central in revolutionizing the chemical engineering industry in the near future (Liu et al., 2021; VanDerHorn and Mahadevan, 2021). More and more industrial applications start from the development of a digital twin of the process (Kritzinger et al., 2018). The role of the digital twin is becoming critical to generate competitive solutions in a wide variety of use cases, such as process operation or maintenance (Errandonea et al., 2020), risk control and prevention (Bevilacqua et al., 2020), process design (Damiani et al., 2018), smart manufacturing (Hu et al., 2018), process optimization (Jeon and Schuesslbauer, 2020), asset lifecycle management (Macchi et al., 2018), process monitoring (Zipper et al., 2018), decision making support (Zhou et al., 2021).  \nVanDerHorn and Mahadevan (2021) defined the digital twin as a virtual representation of a physical system that is updated through information exchange between the physical and virtual systems. Based on this definition, the digital twin can exist only when a physical asset is present, thus a process simulation model may not be technically defined as a digital twin unless the process is actually built and the simulation is updated accordingly. However, in the design phase of engineering a new process, even though it should not be called a rigorous digital twin, a reliable process simulation can be used for the same kind of  \n∗ Corresponding author.  \nE-mail address: [flavio.manenti@polimi.it](flavio.manenti@polimi.it) (F. Manenti).  \napplications. Moreover, designing an optimal process configuration is of utmost importance, and the usage of non-rigorous digital twins helps in achieving it (Tian et al., 2018). In any case, the process simulation, also called non-rigorous digital twin, might be the first building block for constructing a rigorous digital twin, dynamically integrated with the physical system.  \nProcess simulations and digital twins may be based on fundamental models which can be computationally demanding, thus impeding realtime or highly iterative applications, e.g. optimization (Zhao et al","cbCaihQhajwoMjju","https://ap.wps.com/l/cbCaihQhajwoMjju","pdf",22798442,1,19,"English","en",105,"# Introduction\n## Digital twin concepts and role in chemical engineering\n## Surrogate modeling motivation versus fundamental simulations\n## Data-driven model limits and the accuracy–speed challenge","[{\"question\":\"What problem does the surrogate model address in amine-scrubbing digital twins?\",\"answer\":\"It tackles the numerical runtime limitations of conventional process simulations in tasks like optimization and highly iterative workflows by providing a faster predictive surrogate.\"},{\"question\":\"How is the surrogate model constructed and validated?\",\"answer\":\"The surrogate is built from an Aspen HYSYS process simulation, then validated against real process data collected during steady-state operation.\"},{\"question\":\"Why is the Latin hypercube design-of-experiments approach used?\",\"answer\":\"It supports an accurate experimental design by defining nested domains around the nominal steady-state condition, enabling better coverage of input space for model training and prediction.\"}]","Development of a Surrogate Model of an Amine Scrubbing Digital Twin Using Machine Learning Methods | PDF",1785934150,48,{"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},"development-of-a-surrogate-model-of-an-amine-scrubbing-digital-twin-using-machine-learning-methods","",{"@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/development-of-a-surrogate-model-of-an-amine-scrubbing-digital-twin-using-machine-learning-methods/126671/",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","2026-08-05",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},"What problem does the surrogate model address in amine-scrubbing digital twins?","Question",{"text":75,"@type":76},"It tackles the numerical runtime limitations of conventional process simulations in tasks like optimization and highly iterative workflows by providing a faster predictive surrogate.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the surrogate model constructed and validated?",{"text":80,"@type":76},"The surrogate is built from an Aspen HYSYS process simulation, then validated against real process data collected during steady-state operation.",{"name":82,"@type":73,"acceptedAnswer":83},"Why is the Latin hypercube design-of-experiments approach used?",{"text":84,"@type":76},"It supports an accurate experimental design by defining nested domains around the nominal steady-state condition, enabling better coverage of input space for model training and prediction.","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":21,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},"General","general"]