[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-120796-en":3,"doc-seo-120796-105":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},120796,8796095360427,"Lucas Martin","https://ap-avatar.wpscdn.com/davatar_994ba38a5ba835b3df7d355c54d3ed8d",8,"Research & Report","An Interpretable Systematic Review of Machine Learning Models for Predictive Maintenance of Aircraft Engine","The paper provides an interpretable systematic review of machine learning and deep learning approaches for predictive maintenance of aircraft engines, aiming to reduce accidents by anticipating failures early. Sensor time-series data are used to predict engine failure within a fixed number of cycles using LSTM, Bi-LSTM, RNN, Bi-RNN, GRU, Random Forest, KNN, Naive Bayes, and Gradient Boosting. The study applies LIME to interpret why models underperform compared with deep learning, and reports strong early-stage predictive accuracy with GRU, Bi-LSTM, and LSTM.","arXiv :2309 . 13310v1 [ cs .LG] 23 Sep 2023  \nAn Interpretable Systematic Review of Machine Learning Models for Predictive Maintenance of  \nAircraft Engine  \nAbdullah Al Hasib, Ashikur Rahman, Mahpara Khabir, and Md. Tanvir Rouf  \nShawon  \nDepartment of Computer Science and Engineering, Ahsanullah University of Science  \nand Technology, Dhaka, Bangladesh  \n[aahasib.aust@gmail.com](aahasib.aust@gmail.com) , [ashiq4998@gmail.com](ashiq4998@gmail.com) , [khabirmk98@gmail.com](khabirmk98@gmail.com) ,  \n[shawontanvir95@gmail.com](shawontanvir95@gmail.com)  \nAbstract. This paper presents an interpretable review of various ma  \nchine learning and deep learning models to predict the maintenance of  \naircraft engine to avoid any kind of disaster. One of the advantages of the  \nstrategy is that it can work with modest datasets. In this study, sensor  \ndata is utilized to predict aircraft engine failure within a predetermined  \nnumber of cycles using LSTM, Bi-LSTM, RNN, Bi-RNN GRU, Random  \nForest, KNN, Naive Bayes, and Gradient Boosting. We explain how deep  \nlearning and machine learning can be used to generate predictions in pre  \ndictive maintenance using a straightforward scenario with just one data  \nsource. We applied lime to the models to help us understand why ma  \nchine learning models did not perform well than deep learning models.  \nAn extensive analysis of the model’s behavior is presented for several test  \ndata to understand the black box scenario of the models. A lucrative ac  \ncuracy of 97.8%, 97.14%, and 96.42% are achieved by GRU, Bi-LSTM,  \nand LSTM respectively which denotes the capability of the models to  \npredict maintenance at an early stage.  \nKeywords: Predictive Maintenance, CMAPSS, Deep Learning, Machine  \nLearning, Lime  \n1 Introduction  \nIt is true that air travel is one of the safest ways of transportation. However, when they do occur, aviation accidents frequently have disastrous consequences. approximately the course of a recent five-year period, there were approximately  \n4,000 accidents 1 with engine failure as a contributing factor, or nearly two accidents every day. the NTSB claims. Indian Navy reports the fifth MiG-29K crash in four years2  \nA piece of machinery’s capacity cannot be maintained indefinitely; occasionally, it will break down due to antiquated procedures. Systems for monitoring  \n1 [https://www.psbr.law/aviation](https://www.psbr.law/aviation) accident statistics.html  \n2 [https://www.janes.com/defence-news/news-detail/indian-navy-reports-crash-of-fifth-mig-29k-in-four-years](https://www.janes.com/defence-news/news-detail/indian-navy-reports-crash-of-fifth-mig-29k-in-four-years)  \n2 Abdullah Al Hasib et al.  \nmachinery that incorporate sensors can only report on the state of the equipment and not whether it is in good or bad condition. An inspection is performed on a machine to prevent the worst scenario (failure) and to learn more about its condition. To the scheduled machinery system, strategy must be used. Three maintenance strategies represent the best practices: Predictive and preventive maintenance Continual preventive maintenance is the foundation of predictive maintenance (PdM) . keeping an eye on the machine’s condition and performing maintenance as best you can. Based on historical data, integrity factors, statistical inference techniques, and engineering methodologies, PdM indicated the machine’s state for scheduling maintenance. Predictive modeling research has advanced significantly in recent years, both academically and commercially. Predictive maintenance modeling techniques come in four different flavors: knowledgebased, data-driven, physics-based, and hybrid-based [1][2] .  \nIn aircraft, predictive maintenance is essential for lowering costs, improving safety, and raising reliability. It improves maintenance expenditures and reduces downtime by identifying probable issues early. By averting crises during flight, this proactive method guarantees passenger safety. Additi","cbCaiqLFH5WPnXQs","https://ap.wps.com/l/cbCaiqLFH5WPnXQs","pdf",3348017,1,15,"English","en",105,"# Introduction\n## Predictive maintenance motivation and impact\n## Maintenance strategies and PdM fundamentals\n## Prior work and research gap\n# Method overview\n## Dataset and preprocessing\n## Models evaluated\n## Interpretability with LIME\n# Results\n## Model performance and early-stage accuracy\n# Discussion\n## Interpreting model behavior","[{\"question\":\"Which datasets and inputs are used for predictive maintenance in the study?\",\"answer\":\"The work uses the well-known CMAPSS dataset by NASA and sensor readings as the single data source after necessary preprocessing.\"},{\"question\":\"How do the authors predict aircraft engine failure?\",\"answer\":\"They predict failure within a predetermined number of cycles using a range of models including LSTM, Bi-LSTM, RNN, Bi-RNN GRU, Random Forest, KNN, Naive Bayes, and Gradient Boosting.\"},{\"question\":\"What role does LIME play in the analysis?\",\"answer\":\"LIME is applied to help explain why certain machine learning models do not perform as well as deep learning models, and to interpret model behavior in a black-box scenario.\"}]","An Interpretable Systematic Review of Machine Learning Models for Predictive Maintenance of Aircraft Engine | PDF",1785732078,38,{"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},"an-interpretable-systematic-review-of-machine-learning-models-for-predictive-maintenance-of-aircraft-engine","",{"@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/an-interpretable-systematic-review-of-machine-learning-models-for-predictive-maintenance-of-aircraft-engine/120796/",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","2026-08-03",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},"Which datasets and inputs are used for predictive maintenance in the study?","Question",{"text":75,"@type":76},"The work uses the well-known CMAPSS dataset by NASA and sensor readings as the single data source after necessary preprocessing.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How do the authors predict aircraft engine failure?",{"text":80,"@type":76},"They predict failure within a predetermined number of cycles using a range of models including LSTM, Bi-LSTM, RNN, Bi-RNN GRU, Random Forest, KNN, Naive Bayes, and Gradient Boosting.",{"name":82,"@type":73,"acceptedAnswer":83},"What role does LIME play in the analysis?",{"text":84,"@type":76},"LIME is applied to help explain why certain machine learning models do not perform as well as deep learning models, and to interpret model behavior in a black-box scenario.","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"]