Abnormal Sound Detection in Pipes Using a Wireless Microphone and Machine Learning

Notani, Kota; Hayashi, Takahiro; Mori, Naoki

Materials Transactions, 2022, 63(12), 1622-1630

Number of Access:447（2025-11-20 07:16 Counts）

Identifier to cite or link to this item: https://hdl.handle.net/11094/89937

Link to primary information 

File Format Terms of use Size Views Date.Available Description information
MaterTrans_63_12_1622 pdf None 3.86 MB 133 2023.01.23  

Item Information

Output File Export EndNote Basic Export Mendeley

Title
Abnormal Sound Detection in Pipes Using a Wireless Microphone and Machine Learning
Creator
CreatorName
Notani, Kota
NRID
1000030324479 1000030324479
ORCID
0000-0001-6064-4658 0000-0001-6064-4658
researchmap permalink
takahiro_hayashi takahiro_hayashi
Scopus Author ID
37064150200 37064150200
CreatorName
Hayashi, Takahiro
NRID
1000000802092 1000000802092
researchmap permalink
7000020478 7000020478
Scopus Author ID
55614094500 55614094500
ORCID
0000-0002-0707-3443 0000-0002-0707-3443
CreatorName
Mori, Naoki
Subject
nondestructive inspection
pipes
abnormal sound detection
machine learning
wireless microphone
Description
Kota Notani, Takahiro Hayashi, Naoki Mori, Abnormal Sound Detection in Pipes Using a Wireless Microphone and Machine Learning, MATERIALS TRANSACTIONS, 2022, Volume 63, Issue 12, Pages 1622-1630, 2022, https://doi.org/10.2320/matertrans.MT-I2022001.
Abstract
Abnormal sound detection using a one-class support vector machine (OCSVM) and a principal component analysis (PCA) is proposed aiming to stable and objective inspection without skilled plant inspectors. For measurement of acoustic signals, we developed a compact microphone unit that can work in sound detection, signal transmission, and power supply, wirelessly. Six signal parameters were extracted as features from filtered and segmented acoustic signals. Using the features standardized and reduced in dimensionality by PCA, an anomaly detection model using OCSVM is built to detect abnormal sounds. The proposed method is verified by acoustic diagnosis of sound waves leaking from pipeworks with running water. Diagnostic accuracies were evaluated for artificial abnormal sounds with different types of burst waves output from a piezoelectric element attached to the pipe and Pencil Lead Break sound in water flowing background noise. Burst wave changes could be detected in almost all patterns, and the diagnostic accuracy was 100% for the Pencil Lead Break sound.
Publisher
The Japan Institute of Metals and Materials
Source Title
Materials Transactions
Volume (Issue)
63(12)
Page
1622-1630
Date of Issued
2022-12-01
Language
English
Handle URL
https://hdl.handle.net/11094/89937
PISSN
13459678
NCID
AA1151294X
Relation.isIdenticalTo
DOI (Publisher Version)
https://doi.org/10.2320/matertrans.MT-I2022001
Access Rights
open access
CopyRight
© 2022 The Japanese Society for Non-Destructive Inspection
oaire:version
Version of Record
Category
学術雑誌論文 Journal Article