Bearing fault parameter identification under varying operating conditions using vibration signals and evolutionary algorithms

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper presents an effective bearing fault parameter identification scheme based on evolutionary optimization techniques. Three seeded faults in the rotating machinery supported by the test roller bearing include inner race fault, outer race fault and a single ball defect. The fault related features are extracted experimentally by processing the acquired vibration signals in both the time and frequency domain. Techniques based on the power spectral density (PSD) and wavelet transform (WT) are utilized for feature extraction. The sensitivity of the proposed method is investigated under varying operating speeds and radial bearing load. In this study, the inverse problem of parameter identification is investigated. The problem of parameter identification is recast as an optimization problem and two well known evolutionary algorithms, differential evolution (DE) and particle swarm optimization (PSO), are used to identify system parameters given a system response. For online parameter identification, differential evolution outperforms particle both in terms of adaptability and tighter convergence properties. The distinction between the two methods is not distinctively obvious on the offline parameter identification problem.

Original languageEnglish (US)
Title of host publicationDynamics, Vibration, and Control
PublisherAmerican Society of Mechanical Engineers (ASME)
ISBN (Electronic)9780791846483
DOIs
StatePublished - Jan 1 2014
EventASME 2014 International Mechanical Engineering Congress and Exposition, IMECE 2014 - Montreal, Canada
Duration: Nov 14 2014Nov 20 2014

Publication series

NameASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)
Volume4B

Other

OtherASME 2014 International Mechanical Engineering Congress and Exposition, IMECE 2014
CountryCanada
CityMontreal
Period11/14/1411/20/14

Fingerprint

Bearings (structural)
Evolutionary algorithms
Identification (control systems)
Roller bearings
Rotating machinery
Power spectral density
Inverse problems
Particle swarm optimization (PSO)
Wavelet transforms
Feature extraction
Defects
Processing

All Science Journal Classification (ASJC) codes

  • Mechanical Engineering

Cite this

Abu-Mahfouz, I., & Banerjee, A. (2014). Bearing fault parameter identification under varying operating conditions using vibration signals and evolutionary algorithms. In Dynamics, Vibration, and Control (ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE); Vol. 4B). American Society of Mechanical Engineers (ASME). https://doi.org/10.1115/IMECE2014-39124
Abu-Mahfouz, Issam ; Banerjee, Amit. / Bearing fault parameter identification under varying operating conditions using vibration signals and evolutionary algorithms. Dynamics, Vibration, and Control. American Society of Mechanical Engineers (ASME), 2014. (ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)).
@inproceedings{cb73d831d749444581e6b34f3aa2af4d,
title = "Bearing fault parameter identification under varying operating conditions using vibration signals and evolutionary algorithms",
abstract = "This paper presents an effective bearing fault parameter identification scheme based on evolutionary optimization techniques. Three seeded faults in the rotating machinery supported by the test roller bearing include inner race fault, outer race fault and a single ball defect. The fault related features are extracted experimentally by processing the acquired vibration signals in both the time and frequency domain. Techniques based on the power spectral density (PSD) and wavelet transform (WT) are utilized for feature extraction. The sensitivity of the proposed method is investigated under varying operating speeds and radial bearing load. In this study, the inverse problem of parameter identification is investigated. The problem of parameter identification is recast as an optimization problem and two well known evolutionary algorithms, differential evolution (DE) and particle swarm optimization (PSO), are used to identify system parameters given a system response. For online parameter identification, differential evolution outperforms particle both in terms of adaptability and tighter convergence properties. The distinction between the two methods is not distinctively obvious on the offline parameter identification problem.",
author = "Issam Abu-Mahfouz and Amit Banerjee",
year = "2014",
month = "1",
day = "1",
doi = "10.1115/IMECE2014-39124",
language = "English (US)",
series = "ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)",
publisher = "American Society of Mechanical Engineers (ASME)",
booktitle = "Dynamics, Vibration, and Control",

}

Abu-Mahfouz, I & Banerjee, A 2014, Bearing fault parameter identification under varying operating conditions using vibration signals and evolutionary algorithms. in Dynamics, Vibration, and Control. ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE), vol. 4B, American Society of Mechanical Engineers (ASME), ASME 2014 International Mechanical Engineering Congress and Exposition, IMECE 2014, Montreal, Canada, 11/14/14. https://doi.org/10.1115/IMECE2014-39124

Bearing fault parameter identification under varying operating conditions using vibration signals and evolutionary algorithms. / Abu-Mahfouz, Issam; Banerjee, Amit.

Dynamics, Vibration, and Control. American Society of Mechanical Engineers (ASME), 2014. (ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE); Vol. 4B).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Bearing fault parameter identification under varying operating conditions using vibration signals and evolutionary algorithms

AU - Abu-Mahfouz, Issam

AU - Banerjee, Amit

PY - 2014/1/1

Y1 - 2014/1/1

N2 - This paper presents an effective bearing fault parameter identification scheme based on evolutionary optimization techniques. Three seeded faults in the rotating machinery supported by the test roller bearing include inner race fault, outer race fault and a single ball defect. The fault related features are extracted experimentally by processing the acquired vibration signals in both the time and frequency domain. Techniques based on the power spectral density (PSD) and wavelet transform (WT) are utilized for feature extraction. The sensitivity of the proposed method is investigated under varying operating speeds and radial bearing load. In this study, the inverse problem of parameter identification is investigated. The problem of parameter identification is recast as an optimization problem and two well known evolutionary algorithms, differential evolution (DE) and particle swarm optimization (PSO), are used to identify system parameters given a system response. For online parameter identification, differential evolution outperforms particle both in terms of adaptability and tighter convergence properties. The distinction between the two methods is not distinctively obvious on the offline parameter identification problem.

AB - This paper presents an effective bearing fault parameter identification scheme based on evolutionary optimization techniques. Three seeded faults in the rotating machinery supported by the test roller bearing include inner race fault, outer race fault and a single ball defect. The fault related features are extracted experimentally by processing the acquired vibration signals in both the time and frequency domain. Techniques based on the power spectral density (PSD) and wavelet transform (WT) are utilized for feature extraction. The sensitivity of the proposed method is investigated under varying operating speeds and radial bearing load. In this study, the inverse problem of parameter identification is investigated. The problem of parameter identification is recast as an optimization problem and two well known evolutionary algorithms, differential evolution (DE) and particle swarm optimization (PSO), are used to identify system parameters given a system response. For online parameter identification, differential evolution outperforms particle both in terms of adaptability and tighter convergence properties. The distinction between the two methods is not distinctively obvious on the offline parameter identification problem.

UR - http://www.scopus.com/inward/record.url?scp=84926483131&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84926483131&partnerID=8YFLogxK

U2 - 10.1115/IMECE2014-39124

DO - 10.1115/IMECE2014-39124

M3 - Conference contribution

AN - SCOPUS:84926483131

T3 - ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)

BT - Dynamics, Vibration, and Control

PB - American Society of Mechanical Engineers (ASME)

ER -

Abu-Mahfouz I, Banerjee A. Bearing fault parameter identification under varying operating conditions using vibration signals and evolutionary algorithms. In Dynamics, Vibration, and Control. American Society of Mechanical Engineers (ASME). 2014. (ASME International Mechanical Engineering Congress and Exposition, Proceedings (IMECE)). https://doi.org/10.1115/IMECE2014-39124