Fault diagnosis for multi-state equipment with multiple failure modes

Ramin Moghaddass, Ming J. Zuo

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

1 Citation (Scopus)

Abstract

Multi-state systems have received considerable attention recently with regards to reliability and maintenance. Since most mechanical equipment operates under some sort of stress or load, it tends to deteriorate or degrade over time, thus possibly resulting in discrete degradation states (damage degrees), ranging from perfect functioning to complete failure. This multi-state deterioration is the motivation for using condition monitoring tools for the purpose of modeling, diagnosis, prognosis, and condition-based maintenance. Most mechanical equipment is subject to multiple independent failure modes and degradation processes. Rather than independently diagnosing and prognosing the health condition of the equipment for a single failure mode, it is important to investigate how multi-dimensional condition monitoring information can be used for recognition purposes of the state of the health of equipment with multiple independent failure modes. This paper focuses on a non-repairable piece of equipment with multiple independent failure modes, in which the state of the equipment for each single failure mode is not directly observable and only incomplete information is available through condition monitoring. The main objective of this paper is to develop a method to obtain an observation probability matrix which can be used as the main tool for damage degree classification of each failure mode. An observation probability matrix represents the statistical relationship between the actual health state (damage degree and failure mode) of the equipment and the condition monitoring information. This observation probability matrix is an input for such methods, as hidden Markov models, hidden Semi-Markov models, and Nave Bayes classifiers. We modify the Nave Bayes classifier to use this observation probability matrix for classification. The result of this paper is applied for damage degree classification of a planetary gearbox, which is subject to multiple failure modes.

Original languageEnglish (US)
Title of host publicationProceedings - Annual Reliability and Maintainability Symposium
DOIs
StatePublished - 2012
Externally publishedYes
Event2012 Annual Reliability and Maintainability Symposium, RAMS 2012 - Reno, NV, United States
Duration: Jan 23 2012Jan 26 2012

Other

Other2012 Annual Reliability and Maintainability Symposium, RAMS 2012
CountryUnited States
CityReno, NV
Period1/23/121/26/12

Fingerprint

Multi-state
Failure Mode
Fault Diagnosis
Failure modes
Failure analysis
Condition Monitoring
Condition monitoring
Damage
Bayes Classifier
Health
Degradation
Classifiers
Multi-state System
Condition-based Maintenance
Semi-Markov Model
Gearbox
Prognosis
Incomplete Information
Hidden Markov models
Deterioration

Keywords

  • condition monitoring
  • fault diagnosis
  • multi-state deterioration
  • multiple failure modes

ASJC Scopus subject areas

  • Safety, Risk, Reliability and Quality
  • Mathematics(all)
  • Computer Science Applications

Cite this

Moghaddass, R., & Zuo, M. J. (2012). Fault diagnosis for multi-state equipment with multiple failure modes. In Proceedings - Annual Reliability and Maintainability Symposium [6175470] https://doi.org/10.1109/RAMS.2012.6175470

Fault diagnosis for multi-state equipment with multiple failure modes. / Moghaddass, Ramin; Zuo, Ming J.

Proceedings - Annual Reliability and Maintainability Symposium. 2012. 6175470.

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

Moghaddass, R & Zuo, MJ 2012, Fault diagnosis for multi-state equipment with multiple failure modes. in Proceedings - Annual Reliability and Maintainability Symposium., 6175470, 2012 Annual Reliability and Maintainability Symposium, RAMS 2012, Reno, NV, United States, 1/23/12. https://doi.org/10.1109/RAMS.2012.6175470
Moghaddass R, Zuo MJ. Fault diagnosis for multi-state equipment with multiple failure modes. In Proceedings - Annual Reliability and Maintainability Symposium. 2012. 6175470 https://doi.org/10.1109/RAMS.2012.6175470
Moghaddass, Ramin ; Zuo, Ming J. / Fault diagnosis for multi-state equipment with multiple failure modes. Proceedings - Annual Reliability and Maintainability Symposium. 2012.
@inproceedings{ed9c8b5e784f4a94b1d3a2071ac935b2,
title = "Fault diagnosis for multi-state equipment with multiple failure modes",
abstract = "Multi-state systems have received considerable attention recently with regards to reliability and maintenance. Since most mechanical equipment operates under some sort of stress or load, it tends to deteriorate or degrade over time, thus possibly resulting in discrete degradation states (damage degrees), ranging from perfect functioning to complete failure. This multi-state deterioration is the motivation for using condition monitoring tools for the purpose of modeling, diagnosis, prognosis, and condition-based maintenance. Most mechanical equipment is subject to multiple independent failure modes and degradation processes. Rather than independently diagnosing and prognosing the health condition of the equipment for a single failure mode, it is important to investigate how multi-dimensional condition monitoring information can be used for recognition purposes of the state of the health of equipment with multiple independent failure modes. This paper focuses on a non-repairable piece of equipment with multiple independent failure modes, in which the state of the equipment for each single failure mode is not directly observable and only incomplete information is available through condition monitoring. The main objective of this paper is to develop a method to obtain an observation probability matrix which can be used as the main tool for damage degree classification of each failure mode. An observation probability matrix represents the statistical relationship between the actual health state (damage degree and failure mode) of the equipment and the condition monitoring information. This observation probability matrix is an input for such methods, as hidden Markov models, hidden Semi-Markov models, and Nave Bayes classifiers. We modify the Nave Bayes classifier to use this observation probability matrix for classification. The result of this paper is applied for damage degree classification of a planetary gearbox, which is subject to multiple failure modes.",
keywords = "condition monitoring, fault diagnosis, multi-state deterioration, multiple failure modes",
author = "Ramin Moghaddass and Zuo, {Ming J.}",
year = "2012",
doi = "10.1109/RAMS.2012.6175470",
language = "English (US)",
isbn = "9781457718496",
booktitle = "Proceedings - Annual Reliability and Maintainability Symposium",

}

TY - GEN

T1 - Fault diagnosis for multi-state equipment with multiple failure modes

AU - Moghaddass, Ramin

AU - Zuo, Ming J.

PY - 2012

Y1 - 2012

N2 - Multi-state systems have received considerable attention recently with regards to reliability and maintenance. Since most mechanical equipment operates under some sort of stress or load, it tends to deteriorate or degrade over time, thus possibly resulting in discrete degradation states (damage degrees), ranging from perfect functioning to complete failure. This multi-state deterioration is the motivation for using condition monitoring tools for the purpose of modeling, diagnosis, prognosis, and condition-based maintenance. Most mechanical equipment is subject to multiple independent failure modes and degradation processes. Rather than independently diagnosing and prognosing the health condition of the equipment for a single failure mode, it is important to investigate how multi-dimensional condition monitoring information can be used for recognition purposes of the state of the health of equipment with multiple independent failure modes. This paper focuses on a non-repairable piece of equipment with multiple independent failure modes, in which the state of the equipment for each single failure mode is not directly observable and only incomplete information is available through condition monitoring. The main objective of this paper is to develop a method to obtain an observation probability matrix which can be used as the main tool for damage degree classification of each failure mode. An observation probability matrix represents the statistical relationship between the actual health state (damage degree and failure mode) of the equipment and the condition monitoring information. This observation probability matrix is an input for such methods, as hidden Markov models, hidden Semi-Markov models, and Nave Bayes classifiers. We modify the Nave Bayes classifier to use this observation probability matrix for classification. The result of this paper is applied for damage degree classification of a planetary gearbox, which is subject to multiple failure modes.

AB - Multi-state systems have received considerable attention recently with regards to reliability and maintenance. Since most mechanical equipment operates under some sort of stress or load, it tends to deteriorate or degrade over time, thus possibly resulting in discrete degradation states (damage degrees), ranging from perfect functioning to complete failure. This multi-state deterioration is the motivation for using condition monitoring tools for the purpose of modeling, diagnosis, prognosis, and condition-based maintenance. Most mechanical equipment is subject to multiple independent failure modes and degradation processes. Rather than independently diagnosing and prognosing the health condition of the equipment for a single failure mode, it is important to investigate how multi-dimensional condition monitoring information can be used for recognition purposes of the state of the health of equipment with multiple independent failure modes. This paper focuses on a non-repairable piece of equipment with multiple independent failure modes, in which the state of the equipment for each single failure mode is not directly observable and only incomplete information is available through condition monitoring. The main objective of this paper is to develop a method to obtain an observation probability matrix which can be used as the main tool for damage degree classification of each failure mode. An observation probability matrix represents the statistical relationship between the actual health state (damage degree and failure mode) of the equipment and the condition monitoring information. This observation probability matrix is an input for such methods, as hidden Markov models, hidden Semi-Markov models, and Nave Bayes classifiers. We modify the Nave Bayes classifier to use this observation probability matrix for classification. The result of this paper is applied for damage degree classification of a planetary gearbox, which is subject to multiple failure modes.

KW - condition monitoring

KW - fault diagnosis

KW - multi-state deterioration

KW - multiple failure modes

UR - http://www.scopus.com/inward/record.url?scp=84860615115&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84860615115&partnerID=8YFLogxK

U2 - 10.1109/RAMS.2012.6175470

DO - 10.1109/RAMS.2012.6175470

M3 - Conference contribution

SN - 9781457718496

BT - Proceedings - Annual Reliability and Maintainability Symposium

ER -