Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU Dataset
Predictive maintenance in machines aims to anticipate failures. In rotating machines, the component that suffers the most wear and tear is the bearings. Currently, based on the Industry 4.0 paradigm, advances have been made in obtaining data, specifically, vibration signals that can be used to predi...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10145440/ |
| _version_ | 1797803138622685184 |
|---|---|
| author | Miguel Alonso-Gonzalez Vicente Garcia Diaz Benjamin Lopez Perez B. Cristina Pelayo G-Bustelo John Petearson Anzola |
| author_facet | Miguel Alonso-Gonzalez Vicente Garcia Diaz Benjamin Lopez Perez B. Cristina Pelayo G-Bustelo John Petearson Anzola |
| author_sort | Miguel Alonso-Gonzalez |
| collection | DOAJ |
| description | Predictive maintenance in machines aims to anticipate failures. In rotating machines, the component that suffers the most wear and tear is the bearings. Currently, based on the Industry 4.0 paradigm, advances have been made in obtaining data, specifically, vibration signals that can be used to predict deterioration using various techniques. In this study, we have applied vibration analysis to obtain features that can be used in an optimal Machine Learning model using a public dataset from CWRU, widely used in research, which contains data on bearing failures. The main objective of this research is to detect bearing failures using a minimum set of observations and selecting the minimum number of features. To achieve this, frequency domain vibration analysis, combined with envelope analysis, is utilized as an effective method for detecting bearing failures. The results were further improved by incorporating an optimal bandwidth determined using the kurtogram. When the results of the envelope analysis are applied to various machine learning models, using the calculated amplitudes as predictors, the Kernel Naive Bayes model achieved an accuracy of 94.4%. Meanwhile, the Decision Tree (Fine Tree) and KNN (Fine KNN) models demonstrate exceptional accuracy, achieving a perfect accuracy rate of 100%. |
| first_indexed | 2024-03-13T05:16:20Z |
| format | Article |
| id | doaj.art-9763ae1b8048485c9ee4523e37cad073 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-03-13T05:16:20Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-9763ae1b8048485c9ee4523e37cad0732023-06-15T23:00:17ZengIEEEIEEE Access2169-35362023-01-0111577965780510.1109/ACCESS.2023.328346610145440Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU DatasetMiguel Alonso-Gonzalez0https://orcid.org/0000-0002-7482-9167Vicente Garcia Diaz1https://orcid.org/0000-0003-2037-8548Benjamin Lopez Perez2B. Cristina Pelayo G-Bustelo3https://orcid.org/0000-0002-8246-8840John Petearson Anzola4https://orcid.org/0000-0001-8503-5410Department of Computer Science, University of Oviedo, Oviedo, SpainDepartment of Computer Science, University of Oviedo, Oviedo, SpainDepartment of Computer Science, University of Oviedo, Oviedo, SpainDepartment of Computer Science, University of Oviedo, Oviedo, SpainDepartment of Electronics and Mechatronics, Facultad de Ingeniería y Ciencias Básicas Ciencias, Fundación Universitaria Los Libertadores, Bogotá, ColombiaPredictive maintenance in machines aims to anticipate failures. In rotating machines, the component that suffers the most wear and tear is the bearings. Currently, based on the Industry 4.0 paradigm, advances have been made in obtaining data, specifically, vibration signals that can be used to predict deterioration using various techniques. In this study, we have applied vibration analysis to obtain features that can be used in an optimal Machine Learning model using a public dataset from CWRU, widely used in research, which contains data on bearing failures. The main objective of this research is to detect bearing failures using a minimum set of observations and selecting the minimum number of features. To achieve this, frequency domain vibration analysis, combined with envelope analysis, is utilized as an effective method for detecting bearing failures. The results were further improved by incorporating an optimal bandwidth determined using the kurtogram. When the results of the envelope analysis are applied to various machine learning models, using the calculated amplitudes as predictors, the Kernel Naive Bayes model achieved an accuracy of 94.4%. Meanwhile, the Decision Tree (Fine Tree) and KNN (Fine KNN) models demonstrate exceptional accuracy, achieving a perfect accuracy rate of 100%.https://ieeexplore.ieee.org/document/10145440/Bearing faultdeep learningindustry 40machine learningpredictive maintenance |
| spellingShingle | Miguel Alonso-Gonzalez Vicente Garcia Diaz Benjamin Lopez Perez B. Cristina Pelayo G-Bustelo John Petearson Anzola Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU Dataset IEEE Access Bearing fault deep learning industry 40 machine learning predictive maintenance |
| title | Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU Dataset |
| title_full | Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU Dataset |
| title_fullStr | Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU Dataset |
| title_full_unstemmed | Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU Dataset |
| title_short | Bearing Fault Diagnosis With Envelope Analysis and Machine Learning Approaches Using CWRU Dataset |
| title_sort | bearing fault diagnosis with envelope analysis and machine learning approaches using cwru dataset |
| topic | Bearing fault deep learning industry 40 machine learning predictive maintenance |
| url | https://ieeexplore.ieee.org/document/10145440/ |
| work_keys_str_mv | AT miguelalonsogonzalez bearingfaultdiagnosiswithenvelopeanalysisandmachinelearningapproachesusingcwrudataset AT vicentegarciadiaz bearingfaultdiagnosiswithenvelopeanalysisandmachinelearningapproachesusingcwrudataset AT benjaminlopezperez bearingfaultdiagnosiswithenvelopeanalysisandmachinelearningapproachesusingcwrudataset AT bcristinapelayogbustelo bearingfaultdiagnosiswithenvelopeanalysisandmachinelearningapproachesusingcwrudataset AT johnpetearsonanzola bearingfaultdiagnosiswithenvelopeanalysisandmachinelearningapproachesusingcwrudataset |