Feature extraction for rotary machine acoustic diagnostics focused on periodic period

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

    1 Citation (Scopus)

    Abstract

    A new feature extraction method is proposed to detect abnormality of rotary machines using sounds. It is important to detect the abnormality at an early stage to efficiently maintain industrial machines. The rotary machines generally yield abnormal sounds in operation with a technical failure. Acoustic sensors, i.e., microphones, have an advantage in diagnostic that they can avoid a direct contact to the machines. For employing acoustic information, however, the acoustic feature suitable for abnormality detection has to be investigated because it is difficult to extract a periodic period originated number of rotations, especially low frequency due to signal-to-noise ratio detection range is low, based on Fourier transform. In the present study, we attempt to estimate the rotational period based on peak selection method for the feature parameter. Experimental investigation carried out by simulating motor failures demonstrates that the period estimate is the feature suitable for abnormal sound detection: The rotational periods is estimated when the normal operation sound period is electromagnetic frequency and abnormal one is another period. It varies in the histogram by more than 20% and the outliers that were not detected in the normal operation mode are observed.

    Original languageEnglish
    Title of host publicationINTER-NOISE 2015 - 44th International Congress and Exposition on Noise Control Engineering
    PublisherThe Institute of Noise Control Engineering of the USA, Inc.
    Publication statusPublished - 2015
    Event44th International Congress and Exposition on Noise Control Engineering, INTER-NOISE 2015 - San Francisco, United States
    Duration: 2015 Aug 92015 Aug 12

    Other

    Other44th International Congress and Exposition on Noise Control Engineering, INTER-NOISE 2015
    CountryUnited States
    CitySan Francisco
    Period15/8/915/8/12

    Fingerprint

    pattern recognition
    acoustics
    abnormalities
    estimates
    microphones
    histograms
    signal to noise ratios
    electromagnetism
    low frequencies
    sensors

    ASJC Scopus subject areas

    • Acoustics and Ultrasonics

    Cite this

    Minemura, K., Ogawa, T., & Kobayashi, T. (2015). Feature extraction for rotary machine acoustic diagnostics focused on periodic period. In INTER-NOISE 2015 - 44th International Congress and Exposition on Noise Control Engineering The Institute of Noise Control Engineering of the USA, Inc..

    Feature extraction for rotary machine acoustic diagnostics focused on periodic period. / Minemura, Kesaaki; Ogawa, Tetsuji; Kobayashi, Tetsunori.

    INTER-NOISE 2015 - 44th International Congress and Exposition on Noise Control Engineering. The Institute of Noise Control Engineering of the USA, Inc., 2015.

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

    Minemura, K, Ogawa, T & Kobayashi, T 2015, Feature extraction for rotary machine acoustic diagnostics focused on periodic period. in INTER-NOISE 2015 - 44th International Congress and Exposition on Noise Control Engineering. The Institute of Noise Control Engineering of the USA, Inc., 44th International Congress and Exposition on Noise Control Engineering, INTER-NOISE 2015, San Francisco, United States, 15/8/9.
    Minemura K, Ogawa T, Kobayashi T. Feature extraction for rotary machine acoustic diagnostics focused on periodic period. In INTER-NOISE 2015 - 44th International Congress and Exposition on Noise Control Engineering. The Institute of Noise Control Engineering of the USA, Inc. 2015
    Minemura, Kesaaki ; Ogawa, Tetsuji ; Kobayashi, Tetsunori. / Feature extraction for rotary machine acoustic diagnostics focused on periodic period. INTER-NOISE 2015 - 44th International Congress and Exposition on Noise Control Engineering. The Institute of Noise Control Engineering of the USA, Inc., 2015.
    @inproceedings{a2fd4cebedc94fa8b9b25a5eca2143c8,
    title = "Feature extraction for rotary machine acoustic diagnostics focused on periodic period",
    abstract = "A new feature extraction method is proposed to detect abnormality of rotary machines using sounds. It is important to detect the abnormality at an early stage to efficiently maintain industrial machines. The rotary machines generally yield abnormal sounds in operation with a technical failure. Acoustic sensors, i.e., microphones, have an advantage in diagnostic that they can avoid a direct contact to the machines. For employing acoustic information, however, the acoustic feature suitable for abnormality detection has to be investigated because it is difficult to extract a periodic period originated number of rotations, especially low frequency due to signal-to-noise ratio detection range is low, based on Fourier transform. In the present study, we attempt to estimate the rotational period based on peak selection method for the feature parameter. Experimental investigation carried out by simulating motor failures demonstrates that the period estimate is the feature suitable for abnormal sound detection: The rotational periods is estimated when the normal operation sound period is electromagnetic frequency and abnormal one is another period. It varies in the histogram by more than 20{\%} and the outliers that were not detected in the normal operation mode are observed.",
    author = "Kesaaki Minemura and Tetsuji Ogawa and Tetsunori Kobayashi",
    year = "2015",
    language = "English",
    booktitle = "INTER-NOISE 2015 - 44th International Congress and Exposition on Noise Control Engineering",
    publisher = "The Institute of Noise Control Engineering of the USA, Inc.",

    }

    TY - GEN

    T1 - Feature extraction for rotary machine acoustic diagnostics focused on periodic period

    AU - Minemura, Kesaaki

    AU - Ogawa, Tetsuji

    AU - Kobayashi, Tetsunori

    PY - 2015

    Y1 - 2015

    N2 - A new feature extraction method is proposed to detect abnormality of rotary machines using sounds. It is important to detect the abnormality at an early stage to efficiently maintain industrial machines. The rotary machines generally yield abnormal sounds in operation with a technical failure. Acoustic sensors, i.e., microphones, have an advantage in diagnostic that they can avoid a direct contact to the machines. For employing acoustic information, however, the acoustic feature suitable for abnormality detection has to be investigated because it is difficult to extract a periodic period originated number of rotations, especially low frequency due to signal-to-noise ratio detection range is low, based on Fourier transform. In the present study, we attempt to estimate the rotational period based on peak selection method for the feature parameter. Experimental investigation carried out by simulating motor failures demonstrates that the period estimate is the feature suitable for abnormal sound detection: The rotational periods is estimated when the normal operation sound period is electromagnetic frequency and abnormal one is another period. It varies in the histogram by more than 20% and the outliers that were not detected in the normal operation mode are observed.

    AB - A new feature extraction method is proposed to detect abnormality of rotary machines using sounds. It is important to detect the abnormality at an early stage to efficiently maintain industrial machines. The rotary machines generally yield abnormal sounds in operation with a technical failure. Acoustic sensors, i.e., microphones, have an advantage in diagnostic that they can avoid a direct contact to the machines. For employing acoustic information, however, the acoustic feature suitable for abnormality detection has to be investigated because it is difficult to extract a periodic period originated number of rotations, especially low frequency due to signal-to-noise ratio detection range is low, based on Fourier transform. In the present study, we attempt to estimate the rotational period based on peak selection method for the feature parameter. Experimental investigation carried out by simulating motor failures demonstrates that the period estimate is the feature suitable for abnormal sound detection: The rotational periods is estimated when the normal operation sound period is electromagnetic frequency and abnormal one is another period. It varies in the histogram by more than 20% and the outliers that were not detected in the normal operation mode are observed.

    UR - http://www.scopus.com/inward/record.url?scp=84947609574&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84947609574&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:84947609574

    BT - INTER-NOISE 2015 - 44th International Congress and Exposition on Noise Control Engineering

    PB - The Institute of Noise Control Engineering of the USA, Inc.

    ER -