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

Notani, Kota; Hayashi, Takahiro; Mori, Naoki

doi:https://doi.org/10.2320/matertrans.MT-I2022001

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

アクセス数:368件（2025-07-15 13:26 集計）

固定URL: https://hdl.handle.net/11094/89937

閲覧可能ファイル

ファイル	フォーマット	利用条件	サイズ	閲覧回数	利用開始日	説明	information
MaterTrans_63_12_1622	pdf	なし	3.86 MB	116	2023.01.23

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

タイトル	Abnormal Sound Detection in Pipes Using a Wireless Microphone and Machine Learning
著者	著者名 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 著者名 Hayashi, Takahiro
	NRID 1000000802092 1000000802092 researchmap permalink 7000020478 7000020478 Scopus Author ID 55614094500 55614094500 ORCID 0000-0002-0707-3443 0000-0002-0707-3443 著者名 Mori, Naoki
キーワード等	nondestructive inspection
	pipes
	abnormal sound detection
	machine learning
	wireless microphone
内容	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.
抄録	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.
出版者	The Japan Institute of Metals and Materials
収録物名	Materials Transactions
巻(号)	63(12)
ページ	1622-1630
刊行年月	2022-12-01
言語	英語
ハンドルURL	https://hdl.handle.net/11094/89937
PISSN	13459678
NCID	AA1151294X
関連情報 (isIdenticalTo)	DOI (出版社版) https://doi.org/10.2320/matertrans.MT-I2022001
アクセス権	open access
権利情報	© 2022 The Japanese Society for Non-Destructive Inspection
出版タイプ	Version of Record
カテゴリ	学術雑誌論文 Journal Article

資源タイプ	学術雑誌論文
ローカル資源タイプ	学術雑誌論文
DCMI資源タイプ	text
DCTERMS.bibliographicCitation	Materials Transactions. 2022, 63(12), p. 1622-1630
DC.title	Abnormal Sound Detection in Pipes Using a Wireless Microphone and Machine Learning
DC.creator	Notani, Kota
	Hayashi, Takahiro
	Mori, Naoki
DC.publisher	The Japan Institute of Metals and Materials
DC.language' scheme='DCTERMS.RFC1766	英語
DC.type' scheme='DCTERMS.DCMIType	text
DCTERMS.issued' scheme='DCTERMS.W3CDTF	2022-12-01
DC.identifier	https://doi.org/10.2320/matertrans.MT-I2022001
DC.subject	nondestructive inspection
	pipes
	abnormal sound detection
	machine learning
	wireless microphone
DC.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.
DCTERMS.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.
DC.rights	© 2022 The Japanese Society for Non-Destructive Inspection
DC.format	89937
citation_title	Abnormal Sound Detection in Pipes Using a Wireless Microphone and Machine Learning
citation_author	Notani, Kota
	Hayashi, Takahiro
	Mori, Naoki
citation_publisher	The Japan Institute of Metals and Materials
citation_language	英語
citation_date	2022-12-01
citation_journal_title	Materials Transactions
citation_volume	63
citation_issue	12
citation_firstpage	1622
citation_lastpage	1630
citation_doi	https://doi.org/10.2320/matertrans.MT-I2022001
citation_public_url	https://hdl.handle.net/11094/89937

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

閲覧可能ファイル

論文情報

論文詳細を表示