Deep learning-based anomaly-onset aware remaining useful life estimation of bearings

Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy fun...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Pooja Vinayak Kamat, Rekha Sugandhi, Satish Kumar
Formato: article
Lenguaje:EN
Publicado: PeerJ Inc. 2021
Materias:
Acceso en línea:https://doaj.org/article/352093102f5a464598971be0a57f886a
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:352093102f5a464598971be0a57f886a
record_format dspace
spelling oai:doaj.org-article:352093102f5a464598971be0a57f886a2021-11-28T15:05:21ZDeep learning-based anomaly-onset aware remaining useful life estimation of bearings10.7717/peerj-cs.7952376-5992https://doaj.org/article/352093102f5a464598971be0a57f886a2021-11-01T00:00:00Zhttps://peerj.com/articles/cs-795.pdfhttps://peerj.com/articles/cs-795/https://doaj.org/toc/2376-5992Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.Pooja Vinayak KamatRekha SugandhiSatish KumarPeerJ Inc.articleDeep learningPredictive maintenanceAnomaly detectionRemaining useful lifeBearingLSTMElectronic computers. Computer scienceQA75.5-76.95ENPeerJ Computer Science, Vol 7, p e795 (2021)
institution DOAJ
collection DOAJ
language EN
topic Deep learning
Predictive maintenance
Anomaly detection
Remaining useful life
Bearing
LSTM
Electronic computers. Computer science
QA75.5-76.95
spellingShingle Deep learning
Predictive maintenance
Anomaly detection
Remaining useful life
Bearing
LSTM
Electronic computers. Computer science
QA75.5-76.95
Pooja Vinayak Kamat
Rekha Sugandhi
Satish Kumar
Deep learning-based anomaly-onset aware remaining useful life estimation of bearings
description Remaining Useful Life (RUL) estimation of rotating machinery based on their degradation data is vital for machine supervisors. Deep learning models are effective and popular methods for forecasting when rotating machinery such as bearings may malfunction and ultimately break down. During healthy functioning of the machinery, however, RUL is ill-defined. To address this issue, this study recommends using anomaly monitoring during both RUL estimator training and operation. Essential time-domain data is extracted from the raw bearing vibration data, and deep learning models are used to detect the onset of the anomaly. This further acts as a trigger for data-driven RUL estimation. The study employs an unsupervised clustering approach for anomaly trend analysis and a semi-supervised method for anomaly detection and RUL estimation. The novel combined deep learning-based anomaly-onset aware RUL estimation framework showed enhanced results on the benchmarked PRONOSTIA bearings dataset under non-varying operating conditions. The framework consisting of Autoencoder and Long Short Term Memory variants achieved an accuracy of over 90% in anomaly detection and RUL prediction. In the future, the framework can be deployed under varying operational situations using the transfer learning approach.
format article
author Pooja Vinayak Kamat
Rekha Sugandhi
Satish Kumar
author_facet Pooja Vinayak Kamat
Rekha Sugandhi
Satish Kumar
author_sort Pooja Vinayak Kamat
title Deep learning-based anomaly-onset aware remaining useful life estimation of bearings
title_short Deep learning-based anomaly-onset aware remaining useful life estimation of bearings
title_full Deep learning-based anomaly-onset aware remaining useful life estimation of bearings
title_fullStr Deep learning-based anomaly-onset aware remaining useful life estimation of bearings
title_full_unstemmed Deep learning-based anomaly-onset aware remaining useful life estimation of bearings
title_sort deep learning-based anomaly-onset aware remaining useful life estimation of bearings
publisher PeerJ Inc.
publishDate 2021
url https://doaj.org/article/352093102f5a464598971be0a57f886a
work_keys_str_mv AT poojavinayakkamat deeplearningbasedanomalyonsetawareremainingusefullifeestimationofbearings
AT rekhasugandhi deeplearningbasedanomalyonsetawareremainingusefullifeestimationofbearings
AT satishkumar deeplearningbasedanomalyonsetawareremainingusefullifeestimationofbearings
_version_ 1718407825770676224