From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty

Bearings are pivotal components of rotating machines where any defects could propagate and trigger systematic failures. Once faults are detected, accurately predicting remaining useful life (RUL) is essential for optimizing predictive maintenance. Although data-driven methods demonstrate promising p...

Full description

Saved in:
Bibliographic Details
Main Authors: Haobin Wen, Long Zhang, Jyoti K. Sinha
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/24/22/7257
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846152481626652672
author Haobin Wen
Long Zhang
Jyoti K. Sinha
author_facet Haobin Wen
Long Zhang
Jyoti K. Sinha
author_sort Haobin Wen
collection DOAJ
description Bearings are pivotal components of rotating machines where any defects could propagate and trigger systematic failures. Once faults are detected, accurately predicting remaining useful life (RUL) is essential for optimizing predictive maintenance. Although data-driven methods demonstrate promising performance in direct RUL prediction, their robustness and practicability need further improvement regarding physical interpretation and uncertainty quantification. This work leverages variational neural networks to model bearing degradation behind envelope spectra. A convolutional variational autoencoder for regression (CVAER) is developed to probabilistically predict RUL distributions with confidence measures. Enhanced average envelope spectra (AES) are used as network input for its physical robustness in bearing condition assessment and fault detection. The use of the envelope spectrum ensures that it contains only bearing-related information by removing other rotor-related frequencies, hence it improves the RUL prediction. Unlike traditional variational autoencoders, the probabilistic regressor and latent generator are formulated to quantify uncertainty in RUL estimates and learn meaningful latent representations conditioned on specific RUL. Experimental validations are conducted on vibration data collected using multiple accelerometers whose natural frequencies cover bearing resonance ranges to ensure fault detection reliability. Beyond conventional bearing diagnosis, envelope spectra are extended for statistical RUL prediction integrating physical knowledge of actual defect conditions. Comparative and ablation studies are conducted against benchmark models to demonstrate their effectiveness.
format Article
id doaj-art-33c0bdc385be422384a0bdaaa9c37a4c
institution Kabale University
issn 1424-8220
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-33c0bdc385be422384a0bdaaa9c37a4c2024-11-26T18:21:17ZengMDPI AGSensors1424-82202024-11-012422725710.3390/s24227257From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified UncertaintyHaobin Wen0Long Zhang1Jyoti K. Sinha2Dynamics Laboratory, The Department of Mechanical and Aerospace Engineering, The University of Manchester, Manchester M13 9PL, UKThe Department of Electrical and Electronic Engineering, The University of Manchester, Manchester M13 9PL, UKDynamics Laboratory, The Department of Mechanical and Aerospace Engineering, The University of Manchester, Manchester M13 9PL, UKBearings are pivotal components of rotating machines where any defects could propagate and trigger systematic failures. Once faults are detected, accurately predicting remaining useful life (RUL) is essential for optimizing predictive maintenance. Although data-driven methods demonstrate promising performance in direct RUL prediction, their robustness and practicability need further improvement regarding physical interpretation and uncertainty quantification. This work leverages variational neural networks to model bearing degradation behind envelope spectra. A convolutional variational autoencoder for regression (CVAER) is developed to probabilistically predict RUL distributions with confidence measures. Enhanced average envelope spectra (AES) are used as network input for its physical robustness in bearing condition assessment and fault detection. The use of the envelope spectrum ensures that it contains only bearing-related information by removing other rotor-related frequencies, hence it improves the RUL prediction. Unlike traditional variational autoencoders, the probabilistic regressor and latent generator are formulated to quantify uncertainty in RUL estimates and learn meaningful latent representations conditioned on specific RUL. Experimental validations are conducted on vibration data collected using multiple accelerometers whose natural frequencies cover bearing resonance ranges to ensure fault detection reliability. Beyond conventional bearing diagnosis, envelope spectra are extended for statistical RUL prediction integrating physical knowledge of actual defect conditions. Comparative and ablation studies are conducted against benchmark models to demonstrate their effectiveness.https://www.mdpi.com/1424-8220/24/22/7257bearingsremaining useful lifevibrationprognostics and health managementvariational autoencoderuncertainty quantification
spellingShingle Haobin Wen
Long Zhang
Jyoti K. Sinha
From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty
Sensors
bearings
remaining useful life
vibration
prognostics and health management
variational autoencoder
uncertainty quantification
title From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty
title_full From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty
title_fullStr From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty
title_full_unstemmed From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty
title_short From Envelope Spectra to Bearing Remaining Useful Life: An Intelligent Vibration-Based Prediction Model with Quantified Uncertainty
title_sort from envelope spectra to bearing remaining useful life an intelligent vibration based prediction model with quantified uncertainty
topic bearings
remaining useful life
vibration
prognostics and health management
variational autoencoder
uncertainty quantification
url https://www.mdpi.com/1424-8220/24/22/7257
work_keys_str_mv AT haobinwen fromenvelopespectratobearingremainingusefullifeanintelligentvibrationbasedpredictionmodelwithquantifieduncertainty
AT longzhang fromenvelopespectratobearingremainingusefullifeanintelligentvibrationbasedpredictionmodelwithquantifieduncertainty
AT jyotiksinha fromenvelopespectratobearingremainingusefullifeanintelligentvibrationbasedpredictionmodelwithquantifieduncertainty