Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification
Vibration signals captured with an accelerometer carry essential information about Rolling Element Bearings (REBs) faults in rotating machinery, and the envelope spectrum has proven to be a robust tool for their diagnosis at an early stage of development. In this paper, Cepstrum Pre-Whitening (CPW)...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2022-10-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/12/21/10882 |
_version_ | 1797469183940755456 |
---|---|
author | David Cascales-Fulgencio Eduardo Quiles-Cucarella Emilio García-Moreno |
author_facet | David Cascales-Fulgencio Eduardo Quiles-Cucarella Emilio García-Moreno |
author_sort | David Cascales-Fulgencio |
collection | DOAJ |
description | Vibration signals captured with an accelerometer carry essential information about Rolling Element Bearings (REBs) faults in rotating machinery, and the envelope spectrum has proven to be a robust tool for their diagnosis at an early stage of development. In this paper, Cepstrum Pre-Whitening (CPW) has been applied to REBs’ signals to enhance and extract health-state condition indicators from the preprocessed signals’ envelope spectra. These features are used to train some of the state-of-the-art Machine Learning (ML) algorithms, combined with time-domain features such as basic statistics, high-order statistics and impulsive metrics. Before training, these features were ranked according to statistical techniques such as one-way ANOVA and the Kruskal–Wallis test. A Convolutional Neural Network (CNN) has been designed to implement the classification of REBs’ signals from a Deep Learning (DL) point of view, receiving raw time signals’ greyscale images as inputs. The different ML models have yielded validation accuracies of up to 87.6%, while the CNN yielded accuracy of up to 77.61%, for the entire dataset. In addition, the same models have yielded validation accuracies of up to 97.8%, while the CNN, 90.67%, where signals from REBs with faulty balls have been removed from the dataset, highlighting the difficulty of classifying such faults. Furthermore, from the results of the different ML algorithms compared to those of the CNN, frequency-domain features have proven to be highly relevant condition indicators combined with some time-domain features. These models can be potentially helpful in applications that require early diagnosis of REBs faults, such as wind turbines, vehicle transmissions and industrial machinery. |
first_indexed | 2024-03-09T19:17:51Z |
format | Article |
id | doaj.art-274194920ec5456cba1d0518cd8e6f26 |
institution | Directory Open Access Journal |
issn | 2076-3417 |
language | English |
last_indexed | 2024-03-09T19:17:51Z |
publishDate | 2022-10-01 |
publisher | MDPI AG |
record_format | Article |
series | Applied Sciences |
spelling | doaj.art-274194920ec5456cba1d0518cd8e6f262023-11-24T03:34:25ZengMDPI AGApplied Sciences2076-34172022-10-0112211088210.3390/app122110882Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based ClassificationDavid Cascales-Fulgencio0Eduardo Quiles-Cucarella1Emilio García-Moreno2Escuela Técnica Superior de Ingeniería Industrial, Universitat Politècnica de València, Camino de Vera, s/n, 46022 Valencia, SpainInstituto de Automática e Informática Industrial, Universitat Politècnica de València, Camino de Vera, s/n, 46022 Valencia, SpainInstituto de Automática e Informática Industrial, Universitat Politècnica de València, Camino de Vera, s/n, 46022 Valencia, SpainVibration signals captured with an accelerometer carry essential information about Rolling Element Bearings (REBs) faults in rotating machinery, and the envelope spectrum has proven to be a robust tool for their diagnosis at an early stage of development. In this paper, Cepstrum Pre-Whitening (CPW) has been applied to REBs’ signals to enhance and extract health-state condition indicators from the preprocessed signals’ envelope spectra. These features are used to train some of the state-of-the-art Machine Learning (ML) algorithms, combined with time-domain features such as basic statistics, high-order statistics and impulsive metrics. Before training, these features were ranked according to statistical techniques such as one-way ANOVA and the Kruskal–Wallis test. A Convolutional Neural Network (CNN) has been designed to implement the classification of REBs’ signals from a Deep Learning (DL) point of view, receiving raw time signals’ greyscale images as inputs. The different ML models have yielded validation accuracies of up to 87.6%, while the CNN yielded accuracy of up to 77.61%, for the entire dataset. In addition, the same models have yielded validation accuracies of up to 97.8%, while the CNN, 90.67%, where signals from REBs with faulty balls have been removed from the dataset, highlighting the difficulty of classifying such faults. Furthermore, from the results of the different ML algorithms compared to those of the CNN, frequency-domain features have proven to be highly relevant condition indicators combined with some time-domain features. These models can be potentially helpful in applications that require early diagnosis of REBs faults, such as wind turbines, vehicle transmissions and industrial machinery.https://www.mdpi.com/2076-3417/12/21/10882condition monitoring of wind turbinesrolling element bearingsvibration analysisenvelope spectrumcepstrum pre-whiteningtime-domain features |
spellingShingle | David Cascales-Fulgencio Eduardo Quiles-Cucarella Emilio García-Moreno Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification Applied Sciences condition monitoring of wind turbines rolling element bearings vibration analysis envelope spectrum cepstrum pre-whitening time-domain features |
title | Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification |
title_full | Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification |
title_fullStr | Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification |
title_full_unstemmed | Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification |
title_short | Computation and Statistical Analysis of Bearings’ Time- and Frequency-Domain Features Enhanced Using Cepstrum Pre-Whitening: A ML- and DL-Based Classification |
title_sort | computation and statistical analysis of bearings time and frequency domain features enhanced using cepstrum pre whitening a ml and dl based classification |
topic | condition monitoring of wind turbines rolling element bearings vibration analysis envelope spectrum cepstrum pre-whitening time-domain features |
url | https://www.mdpi.com/2076-3417/12/21/10882 |
work_keys_str_mv | AT davidcascalesfulgencio computationandstatisticalanalysisofbearingstimeandfrequencydomainfeaturesenhancedusingcepstrumprewhiteningamlanddlbasedclassification AT eduardoquilescucarella computationandstatisticalanalysisofbearingstimeandfrequencydomainfeaturesenhancedusingcepstrumprewhiteningamlanddlbasedclassification AT emiliogarciamoreno computationandstatisticalanalysisofbearingstimeandfrequencydomainfeaturesenhancedusingcepstrumprewhiteningamlanddlbasedclassification |