Cargando…

Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis

The engineering challenge of rolling bearing condition monitoring has led to a large number of method developments over the past few years. Most commonly, vibration measurement data are used for fault diagnosis using machine learning algorithms. In current research, purely data-driven deep learning...

Descripción completa

Detalles Bibliográficos
Autores principales: Bienefeld, Christoph, Becker-Dombrowsky, Florian Michael, Shatri, Etnik, Kirchner, Eckhard
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10528534/
https://www.ncbi.nlm.nih.gov/pubmed/37761577
http://dx.doi.org/10.3390/e25091278
_version_ 1785111273615130624
author Bienefeld, Christoph
Becker-Dombrowsky, Florian Michael
Shatri, Etnik
Kirchner, Eckhard
author_facet Bienefeld, Christoph
Becker-Dombrowsky, Florian Michael
Shatri, Etnik
Kirchner, Eckhard
author_sort Bienefeld, Christoph
collection PubMed
description The engineering challenge of rolling bearing condition monitoring has led to a large number of method developments over the past few years. Most commonly, vibration measurement data are used for fault diagnosis using machine learning algorithms. In current research, purely data-driven deep learning methods are becoming increasingly popular, aiming for accurate predictions of bearing faults without requiring bearing-specific domain knowledge. Opposing this trend in popularity, the present paper takes a more traditional approach, incorporating domain knowledge by evaluating a variety of feature engineering methods in combination with a random forest classifier. For a comprehensive feature engineering study, a total of 42 mathematical feature formulas are combined with the preprocessing methods of envelope analysis, empirical mode decomposition, wavelet transforms, and frequency band separations. While each single processing method and feature formula is known from the literature, the presented paper contributes to the body of knowledge by investigating novel series connections of processing methods and feature formulas. Using the CWRU bearing fault data for performance evaluation, feature calculation based on the processing method of frequency band separation leads to particularly high prediction accuracies, while at the same time being very efficient in terms of low computational effort. Additionally, in comparison with deep learning approaches, the proposed feature engineering method provides excellent accuracies and enables explainability.
format Online
Article
Text
id pubmed-10528534
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-105285342023-09-28 Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis Bienefeld, Christoph Becker-Dombrowsky, Florian Michael Shatri, Etnik Kirchner, Eckhard Entropy (Basel) Article The engineering challenge of rolling bearing condition monitoring has led to a large number of method developments over the past few years. Most commonly, vibration measurement data are used for fault diagnosis using machine learning algorithms. In current research, purely data-driven deep learning methods are becoming increasingly popular, aiming for accurate predictions of bearing faults without requiring bearing-specific domain knowledge. Opposing this trend in popularity, the present paper takes a more traditional approach, incorporating domain knowledge by evaluating a variety of feature engineering methods in combination with a random forest classifier. For a comprehensive feature engineering study, a total of 42 mathematical feature formulas are combined with the preprocessing methods of envelope analysis, empirical mode decomposition, wavelet transforms, and frequency band separations. While each single processing method and feature formula is known from the literature, the presented paper contributes to the body of knowledge by investigating novel series connections of processing methods and feature formulas. Using the CWRU bearing fault data for performance evaluation, feature calculation based on the processing method of frequency band separation leads to particularly high prediction accuracies, while at the same time being very efficient in terms of low computational effort. Additionally, in comparison with deep learning approaches, the proposed feature engineering method provides excellent accuracies and enables explainability. MDPI 2023-08-30 /pmc/articles/PMC10528534/ /pubmed/37761577 http://dx.doi.org/10.3390/e25091278 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Bienefeld, Christoph
Becker-Dombrowsky, Florian Michael
Shatri, Etnik
Kirchner, Eckhard
Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis
title Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis
title_full Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis
title_fullStr Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis
title_full_unstemmed Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis
title_short Investigation of Feature Engineering Methods for Domain-Knowledge-Assisted Bearing Fault Diagnosis
title_sort investigation of feature engineering methods for domain-knowledge-assisted bearing fault diagnosis
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10528534/
https://www.ncbi.nlm.nih.gov/pubmed/37761577
http://dx.doi.org/10.3390/e25091278
work_keys_str_mv AT bienefeldchristoph investigationoffeatureengineeringmethodsfordomainknowledgeassistedbearingfaultdiagnosis
AT beckerdombrowskyflorianmichael investigationoffeatureengineeringmethodsfordomainknowledgeassistedbearingfaultdiagnosis
AT shatrietnik investigationoffeatureengineeringmethodsfordomainknowledgeassistedbearingfaultdiagnosis
AT kirchnereckhard investigationoffeatureengineeringmethodsfordomainknowledgeassistedbearingfaultdiagnosis