[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-128762-en":3,"doc-seo-128762-105":31,"detail-sidebar-cat-0-en-105":92},{"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":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},128762,1099523882367,"Hazel","https://ap-avatar.wpscdn.com/davatar_9964176cb1d06d4a9deccf72a44ae3dc",8,"Research & Report","Predicting Failures in Industrial Compressor-Based Machines - Tesi di Laurea Magistrale in Computer Science and Engineering","Non-neural machine learning and deep learning models are widely used for predicting system failures in industrial maintenance, yet few studies evaluate how the amount of past data and the future forecast horizon jointly affect performance. This thesis investigates the impact of the reading window size and the prediction window length for failure forecasting on three industrial datasets: a discrete-session wrapping machine, a continuously operating blood refrigerator, and a continuously operating nitrogen generator. The task is framed as binary classification, comparing six algorithms using multivariate telemetry time series.","Predicting Failures in Industrial Compressor-Based Machines  \nTesi di Laurea Magistrale in  \nComputer Science and Engineering - Ingegneria Informatica  \nAuthor: Francesca Forbicini  \nStudent ID: 10628756  \nAdvisor: Prof. Piero Fraternali  \nCo-advisors: Nicolò Oreste Pinciroli Vago  \nAcademic Year: 2022-23  \niii  \nRingraziamenti  \nSi è chiuso un percorso importante dei mie studi. Questi anni sono sembrati interminabili, ma allo stesso tempo sono volati. Vorrei ringraziare tutte le persone importanti che mihanno sostenuto in questo lungo percorso.  \nIn primis, vorrei ringraziare il professor Piero Fraternali per l’opportunità che mi ha datoe per la sua costante presenza durante i miei mesi di ricerca. Un enorme ringraziamentova a Nicolò che mi ha sempre affiancato e dedicato molto tempo. Grazie per essere statosempre pronto a rispondere e per tutti i consigli che mi hai dato.  \nUn grazie va al Politecnico di Milano che mi ha permesso di apprendere moltissimo in diversi ambiti. Qui ho potuto conoscere fantastici colleghi dell’università (le uniche BimbeDiCarminati) e compagni di residenza (la mitica CdS), i quali ringrazio per tutte le lezioni, sessioni, esami e feste passate insieme.  \nRingrazio anche la mia famiglia allargata. A partire dalle mie sorelle Federica, Maria, Benedetta, mia madre Gloria, mio padre Fabrizio, Valentina e mia zia Lea che mi hannosempre sostenuto anche nei momenti più difficili e stressanti. Ringrazio Simone per il sostegno che mi ha dato lungo questi anni e per avermi supportato in tutte le mie scelte. Ringrazio anche Silvia, Giuliano e Andrea per avermi sempre accolta e trattata come un componente della famiglia e avermi sempre sostenuta. Un ringraziamento finale lo dedicoa mio nonno Carlo che anche se non ha avuto la possibilità di assistere a quest’ultimo traguardo, mi ha sempre insegnato l’importanza dello studio e di perseguire i miei obiettivi.  \ni  \nAbstract  \nNon-neural Machine Learning (ML) and Deep Learning (DL) models are often used to predict system failures in the context of industrial maintenance. However, only a few researches jointly assess the effect of varying the amount of past data used to make a prediction and the extension in the future of the forecast. This study evaluates the impact of the size of the reading window and of the prediction window on the performances of models trained to forecast failures in three data sets concerning the operation of (1) an industrial wrapping machine working in discrete sessions,(2) an industrial blood refrigerator working continuously, and (3) a nitrogen generator working continuously. The problem is formulated as a binary classification task that assigns the positive label to the prediction window based on the probability of a failure to occur in such an interval. Six algorithms (Linear Regression (LR), Random Forest (RF), Support Vector Machine (SVM), Long short-term memory (LSTM), Convolutional Long Short Term Memory (ConvLSTM), and Transformers) are compared using multivariate telemetry time series. The results indicate that, in the considered scenarios, the dimension of the prediction windows plays a crucial role and highlight the effectiveness of DL approaches at classifying data with diverse time-dependent patterns preceding a failure and the effectiveness of ML approaches at classifying similar and repetitive patterns preceding a failure.  \nKeywords: Failure prediction, Machine Learning, Deep Learning, Predictive Maintenance  \nSommario  \nI modelli non neurali di Machine Learning e quelli di Deep Learning sono spesso usati per predire dei fallimenti nei sistemi nel contesto di manutenzione industriale. Tuttavia, solo alcune ricerche analizzano l’effetto di variare il numero di dati storici usati per fare le predizioni e l’estendere la predizione nel futuro. Questo studio valuta l’impatto della dimensione della finestra di lettura e della finestra di predizione sulle performance del modello allenato per predire fallimenti in tre datasets c","cbCaicrom9iZhsG6","https://ap.wps.com/l/cbCaicrom9iZhsG6","pdf",1226698,3,1,114,"English","en",105,"# Introduction\n# Related Work\n## Compressor-based Machines\n## Research methodology\n## Tasks\n## Evaluation\n# Methods\n## Data sets\n## Data Processing","[{\"question\":\"What is the main focus of the study on industrial failure forecasting?\",\"answer\":\"The study evaluates how varying the past data amount (reading window) and the future forecast horizon (prediction window) affects model performance for failure prediction.\"},{\"question\":\"How is the failure prediction problem formulated?\",\"answer\":\"It is formulated as a binary classification task that assigns a positive label to a prediction window based on the probability that a failure will occur within that interval.\"},{\"question\":\"Which types of industrial machines and datasets are used?\",\"answer\":\"Three datasets are used, covering a discrete-session industrial wrapping machine, a continuously operating industrial blood refrigerator, and a continuously operating nitrogen generator.\"}]","Predicting Failures in Industrial Compressor-Based Machines - Tesi di Laurea Magistrale in Computer Science and Engineering | PDF",1786003194,287,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"predicting-failures-in-industrial-compressor-based-machines-masters-thesis-in-computer-science-and-engineering","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,49,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":48},"https://docshare.wps.com/document/","Document",2,{"item":50,"name":12,"@type":44,"position":20},"https://docshare.wps.com/document/research-report/",{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/predicting-failures-in-industrial-compressor-based-machines-masters-thesis-in-computer-science-and-engineering/128762/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-23","2026-08-06",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the main focus of the study on industrial failure forecasting?","Question",{"text":76,"@type":77},"The study evaluates how varying the past data amount (reading window) and the future forecast horizon (prediction window) affects model performance for failure prediction.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How is the failure prediction problem formulated?",{"text":81,"@type":77},"It is formulated as a binary classification task that assigns a positive label to a prediction window based on the probability that a failure will occur within that interval.",{"name":83,"@type":74,"acceptedAnswer":84},"Which types of industrial machines and datasets are used?",{"text":85,"@type":77},"Three datasets are used, covering a discrete-session industrial wrapping machine, a continuously operating industrial blood refrigerator, and a continuously operating nitrogen generator.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,121,124,129,132,136],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":48,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":117,"doc_module":4,"doc_module_name":47,"category_name":118,"show_sort_weight":119,"slug":120},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":122,"slug":123},30,"research-report",{"id":125,"doc_module":4,"doc_module_name":47,"category_name":126,"show_sort_weight":127,"slug":128},9,"Religion & Spirituality",20,"religion-spirituality",{"id":127,"doc_module":4,"doc_module_name":47,"category_name":130,"show_sort_weight":127,"slug":131},"World Cup","world-cup",{"id":133,"doc_module":4,"doc_module_name":47,"category_name":134,"show_sort_weight":133,"slug":135},10,"Lifestyle","lifestyle",{"id":137,"doc_module":4,"doc_module_name":47,"category_name":138,"show_sort_weight":107,"slug":139},19,"General","general"]