Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models. Forest, F., Cochard, Q., Noyer, C., Cabut, A., Joncour, M., Lacaille, J., Lebbah, M., & Azzag, H. In Annual Conference of the PHM Society, 2020. 
![Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models [link]](https://bibbase.org/img/filetypes/link.svg "link")
Link Paper ![Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Slides doi abstract bibtex 57 downloads
Link Paper Slides doi abstract bibtex 57 downloads Vibration analysis is an important component of industrial equipment health monitoring. Aircraft engines in particular are complex rotating machines where vibrations, mainly caused by unbalance, misalignment, or damaged bearings, put engine parts under dynamic structural stress. Thus, monitoring the vibratory behavior of engines is essential to detect anomalies and trends, avoid faults and improve availability. Intrinsic properties of parts can be described by the evolution of vibration as function of rotation speed, called a vibration signature. This work presents a methodology for large-scale vibration monitoring on operating civil aircraft engines, based on unsupervised learning algorithms and a flight recorder database. Firstly, we present a pipeline for massive extraction of vibration signatures from raw flight data, consisting in time-domain medium-frequency sensor measurements. Then, signatures are classified and visualized using interpretable self-organized clustering algorithms, yielding a visual cartography of vibration profiles. Domain experts can then extract various insights from resulting models. An abnormal temporal evolution of a signature gives early warning before failure of an engine. In a post-finding situation after an event has occurred, similar at-risk engines are detectable. The approach is global, end-to-end and scalable, which is yet uncommon in our industry, and has been tested on real flight data.
@inproceedings{forest2020largescale,
abstract = {Vibration analysis is an important component of industrial equipment health monitoring. Aircraft engines in particular are complex rotating machines where vibrations, mainly caused by unbalance, misalignment, or damaged bearings, put engine parts under dynamic structural stress. Thus, monitoring the vibratory behavior of engines is essential to detect anomalies and trends, avoid faults and improve availability. Intrinsic properties of parts can be described by the evolution of vibration as function of rotation speed, called a vibration signature. This work presents a methodology for large-scale vibration monitoring on operating civil aircraft engines, based on unsupervised learning algorithms and a flight recorder database. Firstly, we present a pipeline for massive extraction of vibration signatures from raw flight data, consisting in time-domain medium-frequency sensor measurements. Then, signatures are classified and visualized using interpretable self-organized clustering algorithms, yielding a visual cartography of vibration profiles. Domain experts can then extract various insights from resulting models. An abnormal temporal evolution of a signature gives early warning before failure of an engine. In a post-finding situation after an event has occurred, similar at-risk engines are detectable. The approach is global, end-to-end and scalable, which is yet uncommon in our industry, and has been tested on real flight data.},
author = {Forest, Florent and Cochard, Quentin and Noyer, Cecile and Cabut, Adrien and Joncour, Marc and Lacaille, J{\'{e}}r{\^{o}}me and Lebbah, Mustapha and Azzag, Hanene},
booktitle = {Annual Conference of the PHM Society},
keywords = {aircraft engine, vibration analysis, health monitoring, big data, clustering, self-organizing map},
doi = {10.36001/phmconf.2020.v12i1.1131},
title = {{Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models}},
year = {2020},
url_Link = {https://www.phmpapers.org/index.php/phmconf/article/view/1131},
url_Paper = {https://www.phmpapers.org/index.php/phmconf/article/download/1131/913},
url_Slides = {pres-PHM-2020.pdf},
bibbase_note = {<img src="assets/img/papers/vib.png">}
}Downloads: 57
{"_id":"wi6yTiSfmNFoGqBFS","bibbaseid":"forest-cochard-noyer-cabut-joncour-lacaille-lebbah-azzag-largescalevibrationmonitoringofaircraftenginesfromoperationaldatausingselforganizedmodels-2020","authorIDs":["FzQCQZZM2MyWCZ2Nk"],"author_short":["Forest, F.","Cochard, Q.","Noyer, C.","Cabut, A.","Joncour, M.","Lacaille, J.","Lebbah, M.","Azzag, H."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","abstract":"Vibration analysis is an important component of industrial equipment health monitoring. Aircraft engines in particular are complex rotating machines where vibrations, mainly caused by unbalance, misalignment, or damaged bearings, put engine parts under dynamic structural stress. Thus, monitoring the vibratory behavior of engines is essential to detect anomalies and trends, avoid faults and improve availability. Intrinsic properties of parts can be described by the evolution of vibration as function of rotation speed, called a vibration signature. This work presents a methodology for large-scale vibration monitoring on operating civil aircraft engines, based on unsupervised learning algorithms and a flight recorder database. Firstly, we present a pipeline for massive extraction of vibration signatures from raw flight data, consisting in time-domain medium-frequency sensor measurements. Then, signatures are classified and visualized using interpretable self-organized clustering algorithms, yielding a visual cartography of vibration profiles. Domain experts can then extract various insights from resulting models. An abnormal temporal evolution of a signature gives early warning before failure of an engine. In a post-finding situation after an event has occurred, similar at-risk engines are detectable. The approach is global, end-to-end and scalable, which is yet uncommon in our industry, and has been tested on real flight data.","author":[{"propositions":[],"lastnames":["Forest"],"firstnames":["Florent"],"suffixes":[]},{"propositions":[],"lastnames":["Cochard"],"firstnames":["Quentin"],"suffixes":[]},{"propositions":[],"lastnames":["Noyer"],"firstnames":["Cecile"],"suffixes":[]},{"propositions":[],"lastnames":["Cabut"],"firstnames":["Adrien"],"suffixes":[]},{"propositions":[],"lastnames":["Joncour"],"firstnames":["Marc"],"suffixes":[]},{"propositions":[],"lastnames":["Lacaille"],"firstnames":["Jérôme"],"suffixes":[]},{"propositions":[],"lastnames":["Lebbah"],"firstnames":["Mustapha"],"suffixes":[]},{"propositions":[],"lastnames":["Azzag"],"firstnames":["Hanene"],"suffixes":[]}],"booktitle":"Annual Conference of the PHM Society","keywords":"aircraft engine, vibration analysis, health monitoring, big data, clustering, self-organizing map","doi":"10.36001/phmconf.2020.v12i1.1131","title":"Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models","year":"2020","url_link":"https://www.phmpapers.org/index.php/phmconf/article/view/1131","url_paper":"https://www.phmpapers.org/index.php/phmconf/article/download/1131/913","url_slides":"pres-PHM-2020.pdf","bibbase_note":"<img src=\"assets/img/papers/vib.png\">","bibtex":"@inproceedings{forest2020largescale,\nabstract = {Vibration analysis is an important component of industrial equipment health monitoring. Aircraft engines in particular are complex rotating machines where vibrations, mainly caused by unbalance, misalignment, or damaged bearings, put engine parts under dynamic structural stress. Thus, monitoring the vibratory behavior of engines is essential to detect anomalies and trends, avoid faults and improve availability. Intrinsic properties of parts can be described by the evolution of vibration as function of rotation speed, called a vibration signature. This work presents a methodology for large-scale vibration monitoring on operating civil aircraft engines, based on unsupervised learning algorithms and a flight recorder database. Firstly, we present a pipeline for massive extraction of vibration signatures from raw flight data, consisting in time-domain medium-frequency sensor measurements. Then, signatures are classified and visualized using interpretable self-organized clustering algorithms, yielding a visual cartography of vibration profiles. Domain experts can then extract various insights from resulting models. An abnormal temporal evolution of a signature gives early warning before failure of an engine. In a post-finding situation after an event has occurred, similar at-risk engines are detectable. The approach is global, end-to-end and scalable, which is yet uncommon in our industry, and has been tested on real flight data.},\nauthor = {Forest, Florent and Cochard, Quentin and Noyer, Cecile and Cabut, Adrien and Joncour, Marc and Lacaille, J{\\'{e}}r{\\^{o}}me and Lebbah, Mustapha and Azzag, Hanene},\nbooktitle = {Annual Conference of the PHM Society},\nkeywords = {aircraft engine, vibration analysis, health monitoring, big data, clustering, self-organizing map},\ndoi = {10.36001/phmconf.2020.v12i1.1131},\ntitle = {{Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models}},\nyear = {2020},\nurl_Link = {https://www.phmpapers.org/index.php/phmconf/article/view/1131},\nurl_Paper = {https://www.phmpapers.org/index.php/phmconf/article/download/1131/913},\nurl_Slides = {pres-PHM-2020.pdf},\nbibbase_note = {<img src=\"assets/img/papers/vib.png\">}\n}\n\n","author_short":["Forest, F.","Cochard, Q.","Noyer, C.","Cabut, A.","Joncour, M.","Lacaille, J.","Lebbah, M.","Azzag, H."],"key":"forest2020largescale","id":"forest2020largescale","bibbaseid":"forest-cochard-noyer-cabut-joncour-lacaille-lebbah-azzag-largescalevibrationmonitoringofaircraftenginesfromoperationaldatausingselforganizedmodels-2020","role":"author","urls":{" link":"https://www.phmpapers.org/index.php/phmconf/article/view/1131"," paper":"https://www.phmpapers.org/index.php/phmconf/article/download/1131/913"," slides":"https://florentfo.rest/files/pres-PHM-2020.pdf"},"keyword":["aircraft engine","vibration analysis","health monitoring","big data","clustering","self-organizing map"],"metadata":{"authorlinks":{"forest, f":"https://florentfo.rest/publications"}},"downloads":57},"bibtype":"inproceedings","biburl":"https://florentfo.rest/files/publications.bib","creationDate":"2020-11-09T16:04:01.713Z","downloads":57,"keywords":["aircraft engine","vibration analysis","health monitoring","big data","clustering","self-organizing map"],"search_terms":["large","scale","vibration","monitoring","aircraft","engines","operational","data","using","self","organized","models","forest","cochard","noyer","cabut","joncour","lacaille","lebbah","azzag"],"title":"Large-scale Vibration Monitoring of Aircraft Engines from Operational Data using Self-organized Models","year":2020,"dataSources":["pBkCjKbyeirr5jeAd","DgnR6pzJ98ZEp97PW","2puawT8ZAQyYRypA3","6rNfa4Kp6dL5sGmf5","xH8ySTsEPTLou9gyR"]}