Measure and optimize sample confidence of acoustic signal for fault identification in ships

Linke Zhang, Na Wei, Xuhao Du

Research output: Contribution to journalArticle

Abstract

The shortage of sufficient "real" acoustic data under fault conditions on ships has been a challenge for accurate structure diagnosis. The common solution is generating semi-artificial data while the data quality is unknown. Thus, a kernel-based confidence measure (KBCM) is proposed for evaluating the expanded acoustic data. The deviation between the expanded and real data has been deduced to establish a KBCM model for measuring confidence. Furthermore, an optimization algorithm termed as the maximum class separability is formulated for the kernel optimization. Successful applications on experimental acoustics datasets under various fault conditions have demonstrated the proposed method's effectiveness.

Original languageEnglish
Pages (from-to)EL198-EL204
JournalJournal of the Acoustical Society of America
Volume146
Issue number3
DOIs
Publication statusPublished - 1 Sep 2019

Fingerprint

ships
confidence
acoustics
optimization
deviation
Confidence
Fault
Ship
Acoustics
Kernel

Cite this

@article{303dcb3ea6714f6fb08b96d088696328,
title = "Measure and optimize sample confidence of acoustic signal for fault identification in ships",
abstract = "The shortage of sufficient {"}real{"} acoustic data under fault conditions on ships has been a challenge for accurate structure diagnosis. The common solution is generating semi-artificial data while the data quality is unknown. Thus, a kernel-based confidence measure (KBCM) is proposed for evaluating the expanded acoustic data. The deviation between the expanded and real data has been deduced to establish a KBCM model for measuring confidence. Furthermore, an optimization algorithm termed as the maximum class separability is formulated for the kernel optimization. Successful applications on experimental acoustics datasets under various fault conditions have demonstrated the proposed method's effectiveness.",
author = "Linke Zhang and Na Wei and Xuhao Du",
year = "2019",
month = "9",
day = "1",
doi = "10.1121/1.5125040",
language = "English",
volume = "146",
pages = "EL198--EL204",
journal = "Journal of Acoustical Society of America",
issn = "0001-4966",
publisher = "ASA",
number = "3",

}

Measure and optimize sample confidence of acoustic signal for fault identification in ships. / Zhang, Linke; Wei, Na; Du, Xuhao.

In: Journal of the Acoustical Society of America, Vol. 146, No. 3, 01.09.2019, p. EL198-EL204.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Measure and optimize sample confidence of acoustic signal for fault identification in ships

AU - Zhang, Linke

AU - Wei, Na

AU - Du, Xuhao

PY - 2019/9/1

Y1 - 2019/9/1

N2 - The shortage of sufficient "real" acoustic data under fault conditions on ships has been a challenge for accurate structure diagnosis. The common solution is generating semi-artificial data while the data quality is unknown. Thus, a kernel-based confidence measure (KBCM) is proposed for evaluating the expanded acoustic data. The deviation between the expanded and real data has been deduced to establish a KBCM model for measuring confidence. Furthermore, an optimization algorithm termed as the maximum class separability is formulated for the kernel optimization. Successful applications on experimental acoustics datasets under various fault conditions have demonstrated the proposed method's effectiveness.

AB - The shortage of sufficient "real" acoustic data under fault conditions on ships has been a challenge for accurate structure diagnosis. The common solution is generating semi-artificial data while the data quality is unknown. Thus, a kernel-based confidence measure (KBCM) is proposed for evaluating the expanded acoustic data. The deviation between the expanded and real data has been deduced to establish a KBCM model for measuring confidence. Furthermore, an optimization algorithm termed as the maximum class separability is formulated for the kernel optimization. Successful applications on experimental acoustics datasets under various fault conditions have demonstrated the proposed method's effectiveness.

UR - http://www.scopus.com/inward/record.url?scp=85072211659&partnerID=8YFLogxK

U2 - 10.1121/1.5125040

DO - 10.1121/1.5125040

M3 - Article

VL - 146

SP - EL198-EL204

JO - Journal of Acoustical Society of America

JF - Journal of Acoustical Society of America

SN - 0001-4966

IS - 3

ER -