Vibration based blind identification of bearing failures for autonomous wireless sensor nodes

Andrea Sanchez Ramirez, Richard Loendersloot, Tiedo Tinga

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

48 Downloads (Pure)

Abstract

Despite all the attention received by maintainers, undetected roller bearings failures are still a major source of concern in relation with reliability losses and high maintenance costs. Because of that, bearing condition assessment through vibration monitoring remains an intensive topic of scientific research, focusing on the definition of monitoring strategies that allow early stage damage detection, failure causes identification and remaining life prediction. Next to the developments on signal processing, new opportunities of advanced monitoring platforms are devised as those based on Wireless Sensor Networks (WSNs). The combination of integrated sensing, embedded computing and wireless communication provides interesting elements on the development of a new generation of vibration monitoring systems. The algorithms for bearing assessment remain a crucial point for achieving a balance between efficient monitoring strategies and highly flexible monitoring platforms. Though current trends on signal processing for mechanical vibrations focuses on the development of robust techniques, the constraints of embedded processing in relation to energy and memory consumption hamper their implementation on WSN. The present paper discusses the problem of bearing condition characterization from the basis of extraction of damage features associated with the specific stage of its deterioration process. This, other than data driven methods, allow to find the best compromise between robustness of the bearing assessment algorithm and the applicability of the algorithm on a WSN. Two cases are presented as validation of this approach: an artificial damage on a lab setup and a train bearing, for which the possibilities for detection, diagnostics and prognostics are discussed. The advantages and constraints of the use of autonomous wireless sensor nodes is discussed as final part of the paper
Original languageEnglish
Title of host publicationProceedings of the European Conference of the Prognostics and Health Management Society
EditorsA. Bregon, M.J. Daigle
Place of PublicationNantes
PublisherPHM society
Pages452-462
ISBN (Print)978-1-936263-16-5
Publication statusPublished - 8 Jul 2014
Event2nd European Conference of the Prognostics and Health Management Society, PHME 2014 - La Cité, the Nantes Events Center, Nantes, France
Duration: 8 Jul 201410 Jul 2014
Conference number: 2

Publication series

Name
PublisherPHM society

Conference

Conference2nd European Conference of the Prognostics and Health Management Society, PHME 2014
Abbreviated titlePHME2014
CountryFrance
CityNantes
Period8/07/1410/07/14

Fingerprint

Bearings (structural)
Sensor nodes
Monitoring
Wireless sensor networks
Signal processing
Roller bearings
Damage detection
Deterioration
Data storage equipment
Communication
Processing

Keywords

  • METIS-304225
  • IR-92977

Cite this

Sanchez Ramirez, A., Loendersloot, R., & Tinga, T. (2014). Vibration based blind identification of bearing failures for autonomous wireless sensor nodes. In A. Bregon, & M. J. Daigle (Eds.), Proceedings of the European Conference of the Prognostics and Health Management Society (pp. 452-462). Nantes: PHM society.
Sanchez Ramirez, Andrea ; Loendersloot, Richard ; Tinga, Tiedo. / Vibration based blind identification of bearing failures for autonomous wireless sensor nodes. Proceedings of the European Conference of the Prognostics and Health Management Society. editor / A. Bregon ; M.J. Daigle. Nantes : PHM society, 2014. pp. 452-462
@inproceedings{2e91246a36e24f46aade97e204137860,
title = "Vibration based blind identification of bearing failures for autonomous wireless sensor nodes",
abstract = "Despite all the attention received by maintainers, undetected roller bearings failures are still a major source of concern in relation with reliability losses and high maintenance costs. Because of that, bearing condition assessment through vibration monitoring remains an intensive topic of scientific research, focusing on the definition of monitoring strategies that allow early stage damage detection, failure causes identification and remaining life prediction. Next to the developments on signal processing, new opportunities of advanced monitoring platforms are devised as those based on Wireless Sensor Networks (WSNs). The combination of integrated sensing, embedded computing and wireless communication provides interesting elements on the development of a new generation of vibration monitoring systems. The algorithms for bearing assessment remain a crucial point for achieving a balance between efficient monitoring strategies and highly flexible monitoring platforms. Though current trends on signal processing for mechanical vibrations focuses on the development of robust techniques, the constraints of embedded processing in relation to energy and memory consumption hamper their implementation on WSN. The present paper discusses the problem of bearing condition characterization from the basis of extraction of damage features associated with the specific stage of its deterioration process. This, other than data driven methods, allow to find the best compromise between robustness of the bearing assessment algorithm and the applicability of the algorithm on a WSN. Two cases are presented as validation of this approach: an artificial damage on a lab setup and a train bearing, for which the possibilities for detection, diagnostics and prognostics are discussed. The advantages and constraints of the use of autonomous wireless sensor nodes is discussed as final part of the paper",
keywords = "METIS-304225, IR-92977",
author = "{Sanchez Ramirez}, Andrea and Richard Loendersloot and Tiedo Tinga",
year = "2014",
month = "7",
day = "8",
language = "English",
isbn = "978-1-936263-16-5",
publisher = "PHM society",
pages = "452--462",
editor = "A. Bregon and M.J. Daigle",
booktitle = "Proceedings of the European Conference of the Prognostics and Health Management Society",

}

Sanchez Ramirez, A, Loendersloot, R & Tinga, T 2014, Vibration based blind identification of bearing failures for autonomous wireless sensor nodes. in A Bregon & MJ Daigle (eds), Proceedings of the European Conference of the Prognostics and Health Management Society. PHM society, Nantes, pp. 452-462, 2nd European Conference of the Prognostics and Health Management Society, PHME 2014, Nantes, France, 8/07/14.

Vibration based blind identification of bearing failures for autonomous wireless sensor nodes. / Sanchez Ramirez, Andrea; Loendersloot, Richard; Tinga, Tiedo.

Proceedings of the European Conference of the Prognostics and Health Management Society. ed. / A. Bregon; M.J. Daigle. Nantes : PHM society, 2014. p. 452-462.

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Vibration based blind identification of bearing failures for autonomous wireless sensor nodes

AU - Sanchez Ramirez, Andrea

AU - Loendersloot, Richard

AU - Tinga, Tiedo

PY - 2014/7/8

Y1 - 2014/7/8

N2 - Despite all the attention received by maintainers, undetected roller bearings failures are still a major source of concern in relation with reliability losses and high maintenance costs. Because of that, bearing condition assessment through vibration monitoring remains an intensive topic of scientific research, focusing on the definition of monitoring strategies that allow early stage damage detection, failure causes identification and remaining life prediction. Next to the developments on signal processing, new opportunities of advanced monitoring platforms are devised as those based on Wireless Sensor Networks (WSNs). The combination of integrated sensing, embedded computing and wireless communication provides interesting elements on the development of a new generation of vibration monitoring systems. The algorithms for bearing assessment remain a crucial point for achieving a balance between efficient monitoring strategies and highly flexible monitoring platforms. Though current trends on signal processing for mechanical vibrations focuses on the development of robust techniques, the constraints of embedded processing in relation to energy and memory consumption hamper their implementation on WSN. The present paper discusses the problem of bearing condition characterization from the basis of extraction of damage features associated with the specific stage of its deterioration process. This, other than data driven methods, allow to find the best compromise between robustness of the bearing assessment algorithm and the applicability of the algorithm on a WSN. Two cases are presented as validation of this approach: an artificial damage on a lab setup and a train bearing, for which the possibilities for detection, diagnostics and prognostics are discussed. The advantages and constraints of the use of autonomous wireless sensor nodes is discussed as final part of the paper

AB - Despite all the attention received by maintainers, undetected roller bearings failures are still a major source of concern in relation with reliability losses and high maintenance costs. Because of that, bearing condition assessment through vibration monitoring remains an intensive topic of scientific research, focusing on the definition of monitoring strategies that allow early stage damage detection, failure causes identification and remaining life prediction. Next to the developments on signal processing, new opportunities of advanced monitoring platforms are devised as those based on Wireless Sensor Networks (WSNs). The combination of integrated sensing, embedded computing and wireless communication provides interesting elements on the development of a new generation of vibration monitoring systems. The algorithms for bearing assessment remain a crucial point for achieving a balance between efficient monitoring strategies and highly flexible monitoring platforms. Though current trends on signal processing for mechanical vibrations focuses on the development of robust techniques, the constraints of embedded processing in relation to energy and memory consumption hamper their implementation on WSN. The present paper discusses the problem of bearing condition characterization from the basis of extraction of damage features associated with the specific stage of its deterioration process. This, other than data driven methods, allow to find the best compromise between robustness of the bearing assessment algorithm and the applicability of the algorithm on a WSN. Two cases are presented as validation of this approach: an artificial damage on a lab setup and a train bearing, for which the possibilities for detection, diagnostics and prognostics are discussed. The advantages and constraints of the use of autonomous wireless sensor nodes is discussed as final part of the paper

KW - METIS-304225

KW - IR-92977

M3 - Conference contribution

SN - 978-1-936263-16-5

SP - 452

EP - 462

BT - Proceedings of the European Conference of the Prognostics and Health Management Society

A2 - Bregon, A.

A2 - Daigle, M.J.

PB - PHM society

CY - Nantes

ER -

Sanchez Ramirez A, Loendersloot R, Tinga T. Vibration based blind identification of bearing failures for autonomous wireless sensor nodes. In Bregon A, Daigle MJ, editors, Proceedings of the European Conference of the Prognostics and Health Management Society. Nantes: PHM society. 2014. p. 452-462