Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Identification of Incipient Defects in New Ship Machinery Units During Adaptive Vibration Diagnostics Based on Multidimensional Features

Identification of Incipient Defects in New Ship Machinery Units During Adaptive Vibration... A method has been developed for identifying the occurrence of incipient defects in the new ship machinery units that have not previously passed vibrodiagnostic testing, in the absence of statistical data on changes in the vibroacoustic parameters and diagnostic features under the action of characteristic malfunctions. A method for identifying faulty units with incipient defects under the action of unknown malfunctions has been implemented. An algorithm has been developed for constructing the boundaries of reference domains by integrating conditional multidimensional probability densities of feature spaces, which characterize the distribution of incipient defects for the operational state of the machinery. A rule is proposed for identifying the occurrence of incipient defects in individual machinery units in the case of multidimensional features passing beyond the boundaries of the reference domains. A rule is proposed for identifying the occurrence of incipient defects in the machinery units constructed based on a nonparametric goodness-of-fit criterion for assessing the coincidence of conditional distribution functions of multidimensional features characterizing these defects. Experimental verification of the developed method was carried out during in situ vibroacoustic tests of ship machinery. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Acoustical Physics Springer Journals

Identification of Incipient Defects in New Ship Machinery Units During Adaptive Vibration Diagnostics Based on Multidimensional Features

Acoustical Physics , Volume 67 (5) – Sep 1, 2021

Loading next page...
 
/lp/springer-journals/identification-of-incipient-defects-in-new-ship-machinery-units-during-pzNDtAVOeF
Publisher
Springer Journals
Copyright
Copyright © Pleiades Publishing, Ltd. 2021. ISSN 1063-7710, Acoustical Physics, 2021, Vol. 67, No. 5, pp. 528–536. © Pleiades Publishing, Ltd., 2021. Russian Text © The Author(s), 2021, published in Akusticheskii Zhurnal, 2021, Vol. 67, No. 5, pp. 551–560.
ISSN
1063-7710
eISSN
1562-6865
DOI
10.1134/s1063771021050018
Publisher site
See Article on Publisher Site

Abstract

A method has been developed for identifying the occurrence of incipient defects in the new ship machinery units that have not previously passed vibrodiagnostic testing, in the absence of statistical data on changes in the vibroacoustic parameters and diagnostic features under the action of characteristic malfunctions. A method for identifying faulty units with incipient defects under the action of unknown malfunctions has been implemented. An algorithm has been developed for constructing the boundaries of reference domains by integrating conditional multidimensional probability densities of feature spaces, which characterize the distribution of incipient defects for the operational state of the machinery. A rule is proposed for identifying the occurrence of incipient defects in individual machinery units in the case of multidimensional features passing beyond the boundaries of the reference domains. A rule is proposed for identifying the occurrence of incipient defects in the machinery units constructed based on a nonparametric goodness-of-fit criterion for assessing the coincidence of conditional distribution functions of multidimensional features characterizing these defects. Experimental verification of the developed method was carried out during in situ vibroacoustic tests of ship machinery.

Journal

Acoustical PhysicsSpringer Journals

Published: Sep 1, 2021

Keywords: vibrodiagnostics; vibroacoustic signal; incipient defects; multidimensional feature spaces; spectral power density; state of machinery

References