Acoustic Feature Representation Based on Timbre for Fault Detection of Rotary Machines

研究成果: Conference contribution

抄録

A new acoustic feature representation is proposed to detect faults of rotary machinery using acoustic signals. Acoustic features include the amplitude, frequency, and timbre, with the former two often used as diagnostics features. The timbre is also an indicator of the abnormal operation of machinery. The present study therefore focuses on the use of timbre-based features. Changes in stationary parts of observed acoustic signals (e.g., a change in period, which corresponds to the number of rotations) can be considered a physical quantity of the timbre. Because a rotary machine normally operates at a certain rotational speed, differences in the rotational period between adjacent frames are ideally zero in such normal operation. In contrast, the period differences should not be zero for a machine with a fault because observed signals contain characteristics of both the normal and faulty states and these characteristics vary over time. The present study therefore attempts to exploit the period difference of acoustic signals as a feature representation for fault detection. Experimental analysis conducted using acoustic signals recorded by microphones demonstrates that the proposed feature extraction contributes to the fault detection of rotary machines.

元の言語English
ホスト出版物のタイトルProceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018
編集者Dian Wang, Yong Zhou, Diego Cabrera, Chuan Li, Chunlin Zhang
出版者Institute of Electrical and Electronics Engineers Inc.
ページ302-305
ページ数4
ISBN(電子版)9781538660577
DOI
出版物ステータスPublished - 2019 3 11
イベント2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018 - Xi'an, China
継続期間: 2018 8 152018 8 17

出版物シリーズ

名前Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018

Conference

Conference2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018
China
Xi'an
期間18/8/1518/8/17

Fingerprint

fault detection
Fault Detection
Fault detection
Acoustics
acoustics
machinery
Fault
Rotating machinery
Zero
Experimental Analysis
Microphones
microphones
pattern recognition
Feature Extraction
Machinery
Feature extraction
Diagnostics
Adjacent
Vary
Demonstrate

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Safety, Risk, Reliability and Quality
  • Control and Optimization
  • Instrumentation

これを引用

Minemura, K., Ogawa, T., & Kobayashi, T. (2019). Acoustic Feature Representation Based on Timbre for Fault Detection of Rotary Machines. : D. Wang, Y. Zhou, D. Cabrera, C. Li, & C. Zhang (版), Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018 (pp. 302-305). [8664991] (Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SDPC.2018.8664991

Acoustic Feature Representation Based on Timbre for Fault Detection of Rotary Machines. / Minemura, Kesaaki; Ogawa, Tetsuji; Kobayashi, Tetsunori.

Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018. 版 / Dian Wang; Yong Zhou; Diego Cabrera; Chuan Li; Chunlin Zhang. Institute of Electrical and Electronics Engineers Inc., 2019. p. 302-305 8664991 (Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018).

研究成果: Conference contribution

Minemura, K, Ogawa, T & Kobayashi, T 2019, Acoustic Feature Representation Based on Timbre for Fault Detection of Rotary Machines. : D Wang, Y Zhou, D Cabrera, C Li & C Zhang (版), Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018., 8664991, Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018, Institute of Electrical and Electronics Engineers Inc., pp. 302-305, 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018, Xi'an, China, 18/8/15. https://doi.org/10.1109/SDPC.2018.8664991
Minemura K, Ogawa T, Kobayashi T. Acoustic Feature Representation Based on Timbre for Fault Detection of Rotary Machines. : Wang D, Zhou Y, Cabrera D, Li C, Zhang C, 編集者, Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018. Institute of Electrical and Electronics Engineers Inc. 2019. p. 302-305. 8664991. (Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018). https://doi.org/10.1109/SDPC.2018.8664991
Minemura, Kesaaki ; Ogawa, Tetsuji ; Kobayashi, Tetsunori. / Acoustic Feature Representation Based on Timbre for Fault Detection of Rotary Machines. Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018. 編集者 / Dian Wang ; Yong Zhou ; Diego Cabrera ; Chuan Li ; Chunlin Zhang. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 302-305 (Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018).
@inproceedings{40c26f680d4b411cb0023ab1b1f72bd6,
title = "Acoustic Feature Representation Based on Timbre for Fault Detection of Rotary Machines",
abstract = "A new acoustic feature representation is proposed to detect faults of rotary machinery using acoustic signals. Acoustic features include the amplitude, frequency, and timbre, with the former two often used as diagnostics features. The timbre is also an indicator of the abnormal operation of machinery. The present study therefore focuses on the use of timbre-based features. Changes in stationary parts of observed acoustic signals (e.g., a change in period, which corresponds to the number of rotations) can be considered a physical quantity of the timbre. Because a rotary machine normally operates at a certain rotational speed, differences in the rotational period between adjacent frames are ideally zero in such normal operation. In contrast, the period differences should not be zero for a machine with a fault because observed signals contain characteristics of both the normal and faulty states and these characteristics vary over time. The present study therefore attempts to exploit the period difference of acoustic signals as a feature representation for fault detection. Experimental analysis conducted using acoustic signals recorded by microphones demonstrates that the proposed feature extraction contributes to the fault detection of rotary machines.",
keywords = "Acoustic diagnosis, Fault detection, Feature extraction, Rotary machine, Timbre",
author = "Kesaaki Minemura and Tetsuji Ogawa and Tetsunori Kobayashi",
year = "2019",
month = "3",
day = "11",
doi = "10.1109/SDPC.2018.8664991",
language = "English",
series = "Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "302--305",
editor = "Dian Wang and Yong Zhou and Diego Cabrera and Chuan Li and Chunlin Zhang",
booktitle = "Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018",

}

TY - GEN

T1 - Acoustic Feature Representation Based on Timbre for Fault Detection of Rotary Machines

AU - Minemura, Kesaaki

AU - Ogawa, Tetsuji

AU - Kobayashi, Tetsunori

PY - 2019/3/11

Y1 - 2019/3/11

N2 - A new acoustic feature representation is proposed to detect faults of rotary machinery using acoustic signals. Acoustic features include the amplitude, frequency, and timbre, with the former two often used as diagnostics features. The timbre is also an indicator of the abnormal operation of machinery. The present study therefore focuses on the use of timbre-based features. Changes in stationary parts of observed acoustic signals (e.g., a change in period, which corresponds to the number of rotations) can be considered a physical quantity of the timbre. Because a rotary machine normally operates at a certain rotational speed, differences in the rotational period between adjacent frames are ideally zero in such normal operation. In contrast, the period differences should not be zero for a machine with a fault because observed signals contain characteristics of both the normal and faulty states and these characteristics vary over time. The present study therefore attempts to exploit the period difference of acoustic signals as a feature representation for fault detection. Experimental analysis conducted using acoustic signals recorded by microphones demonstrates that the proposed feature extraction contributes to the fault detection of rotary machines.

AB - A new acoustic feature representation is proposed to detect faults of rotary machinery using acoustic signals. Acoustic features include the amplitude, frequency, and timbre, with the former two often used as diagnostics features. The timbre is also an indicator of the abnormal operation of machinery. The present study therefore focuses on the use of timbre-based features. Changes in stationary parts of observed acoustic signals (e.g., a change in period, which corresponds to the number of rotations) can be considered a physical quantity of the timbre. Because a rotary machine normally operates at a certain rotational speed, differences in the rotational period between adjacent frames are ideally zero in such normal operation. In contrast, the period differences should not be zero for a machine with a fault because observed signals contain characteristics of both the normal and faulty states and these characteristics vary over time. The present study therefore attempts to exploit the period difference of acoustic signals as a feature representation for fault detection. Experimental analysis conducted using acoustic signals recorded by microphones demonstrates that the proposed feature extraction contributes to the fault detection of rotary machines.

KW - Acoustic diagnosis

KW - Fault detection

KW - Feature extraction

KW - Rotary machine

KW - Timbre

UR - http://www.scopus.com/inward/record.url?scp=85064140496&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85064140496&partnerID=8YFLogxK

U2 - 10.1109/SDPC.2018.8664991

DO - 10.1109/SDPC.2018.8664991

M3 - Conference contribution

AN - SCOPUS:85064140496

T3 - Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018

SP - 302

EP - 305

BT - Proceedings - 2018 International Conference on Sensing, Diagnostics, Prognostics, and Control, SDPC 2018

A2 - Wang, Dian

A2 - Zhou, Yong

A2 - Cabrera, Diego

A2 - Li, Chuan

A2 - Zhang, Chunlin

PB - Institute of Electrical and Electronics Engineers Inc.

ER -