[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-117994-en":3,"doc-seo-117994-105":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},117994,4810365810221,"Aurora","https://ap-avatar.wpscdn.com/davatar_155a257f0dc6eb9ab79c44ca47cae57d",8,"Research & Report","Machine Learning based Prognostics of On-Board Electromechanical Actuators - Paper","This paper presents a machine learning-based prognostic approach for on-board electromechanical actuators, targeting the drawbacks of model-based frameworks that depend on expensive optimization. System signal characteristics are mapped directly to parameters used in fault simulation through machine learning. Experiments with five of eight implemented fault types show highly promising artificial neural network performance for fault prediction and detection with minimal error. A second test includes all fault types and evaluates robustness, error rates, and computational cost, enabling practical real-time fault detection and characterization for industrial use.","# Machine Learning based Prognostics of On-Board\n\nElectromechanical Actuators  \nEdmondo MINISCI 1[0000-0001-9951-8528] , Matteo D.L. DALLA VEDOVA2[0000-0002-3124 -  \n2198],  \nParid ALIMHILLAJ3[0009-0009-7755-702X], Leonardo BALDO2[0000-0001-5073-4166], andPaolo MAGGIORE2[0000-0003-0218-0730]  \n1 University of Strathclyde, Glasgow G1 1XJ, United Kingdom  \n2 Politecnico di Torino, Turin 10129, Italy  \n3 Polytechnic University of Tirana, Tirana 1000, Albaniaedmondo.minisci@strath.ac.uk, matteo.dallavedova@polito. it,  \nparid.alimhillaj@fim.edu.al, leonardo.baldo@polito. it,paolo.maggiore@polito. it  \nAbstract. This paper presents a novel machine learning-based prognostic ap -proach for on-board electromechanical actuators. The study is centered aroundovercoming the limitations of model-based prognostic frameworks that rely onexpensive optimization processes. Machine learning techniques were employedto map system signal characteristics directly into parameters related to faultsimulation. A first test, utilizing only five of eight implemented fault types,demonstrates a highly promising potential of artificial neural networks to pre -dict and detect faults with minimal error. A second test expand the investiga -tionto include all fault types and provides an analysis of the model's robustness,error rates, and computational costs. The practical outcome of the work is a via -ble real-time solution for fault detection and characterization in electromechani -cal actuators, highlighting the efficiency and effectiveness of machine learningtechniques for industrial applications.  \nKeywords: Machine Learning, Prognostics, Electro-Mechanical Actuators, Re -liability, Fault Implementation, Failure Analysis  \n## 1 Introduction\n\nElectromechanical actuators (EMAs) play a pivotal role in modern technological sys -tems, converting electrical energy into mechanical energy and performing precisemotion control tasks. As crucial components in industries such as manufacturing,automotive, and robotics, they underpin the smooth functioning of a myriad of sys -tems. Their importance is even further underscored in the aerospace and aeronauticalsectors where EMAs are vital components in aircraft systems including flight control,landing gears, and engine control, with the contemporary trend of transitioning fromhydraulic and pneumatic systems to \"more electric aircraft\" [1] . This transition isdriven by the advantages of EMAs, such as weight reduction, simplified maintenance,and overall efficiency improvement[2,3] .  \nThese wide-ranging applications accentuate the necessity for early fault detection andsystem reliability. Failures can lead to substantial financial costs, operational delays,or catastrophic consequences, particularly in safety-critical aerospace applications,fully justifying the carried out exploration into machine learning-based prognosticsfor on-board EMAs.  \nFault detection in EMAs can be conducted through model-based diagnostic methodsand approaches, which involve complex and computationally heavy optimizationprocesses[3,4] . These techniques require detailed models of the system and its faults,which can be a resource-intensive and intricate process, often requiring specific ex -pertise, and necessitate exhaustive simulations and the application of heuristic searchalgorithms to match observed and simulated behavior, making them unsuitable forreal-time fault detection and characterization.  \nRecent research on prognostics and fault detection has seen a shift towards data -driven approaches, notably machine learning techniques. These techniques havedemonstrated the potential to identify complex patterns, allowing for the detectionand characterization of faultsin nonlinear systems like EMAs.  \nHowever, there is a persisting gap in the development of methods that facilitate quickand efficient real-time prognostics in EMAs. The carried out research aims to bridgethe previous work about the use of metaheuristics by utilizing artificial neural net","cbCaiowUjcMHBFzp","https://ap.wps.com/l/cbCaiowUjcMHBFzp","pdf",1537291,1,12,"English","en",105,"# 1 Introduction\n# 2 Models and Methods\n## 2.1 EMA Model and Fault Implementation","[{\"question\":\"What problem does the paper address for on-board prognostics of electromechanical actuators?\",\"answer\":\"It addresses the limitations of model-based prognostic frameworks that require costly and computationally heavy optimization, making real-time fault detection difficult.\"},{\"question\":\"How does the proposed machine learning method relate signals to faults?\",\"answer\":\"The method maps system signal characteristics directly to parameters associated with fault simulation, using artificial neural networks to learn nonlinear patterns.\"},{\"question\":\"What do the two tests in the study compare?\",\"answer\":\"The first test validates performance using five of eight fault types with minimal error, while the second includes all fault types to assess robustness, error rates, and computational costs for real-time feasibility.\"}]","Machine Learning based Prognostics of On-Board Electromechanical Actuators - Paper | PDF",1785680671,30,{"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-based-prognostics-of-on-board-electromechanical-actuators-paper","",{"@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-based-prognostics-of-on-board-electromechanical-actuators-paper/117994/",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","2026-08-02",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 paper address for on-board prognostics of electromechanical actuators?","Question",{"text":75,"@type":76},"It addresses the limitations of model-based prognostic frameworks that require costly and computationally heavy optimization, making real-time fault detection difficult.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does the proposed machine learning method relate signals to faults?",{"text":80,"@type":76},"The method maps system signal characteristics directly to parameters associated with fault simulation, using artificial neural networks to learn nonlinear patterns.",{"name":82,"@type":73,"acceptedAnswer":83},"What do the two tests in the study compare?",{"text":84,"@type":76},"The first test validates performance using five of eight fault types with minimal error, while the second includes all fault types to assess robustness, error rates, and computational costs for real-time feasibility.","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},[93,97,101,105,110,115,120,122,127,130,134],{"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":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]