Detection of Clips Failures in Manufacturing using Audio Signals

Sabri Suer; Ilknur Koseoglu; Rahim Oner; Gokhan Ince

doi:10.1109/HORA58378.2023.10156765

Detection of Clips Failures in Manufacturing using Audio Signals

Sabri Suer, Ilknur Koseoglu, Rahim Oner, Gokhan Ince

Department of Computer Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

1 Citation (Scopus)

Abstract

In industrial manufacturing processes, such as plugging small connectors in, where visual verification is difficult, workers may experience difficulties in detecting failures. Artificial intelligence algorithms can be used to detect and identify the sound of these connectors and mitigate human error. In this work, sound samples of correctly plugged-in connectors and ordinary background noise of the workplace were collected using a recording setup fastened to workers' hand. In order to discriminate anomalies that represent failures, autoencoder models were trained and tested in an unsupervised manner. Experiments with different deep learning architectures for anomaly detection are conducted. Our CNNAE-FT model achieved best results and yielded a ROC-AUC score of 0.85.

Original language	English
Title of host publication	HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9798350337525
DOIs	https://doi.org/10.1109/HORA58378.2023.10156765
Publication status	Published - 2023
Event	5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023 - Istanbul, Turkey Duration: 8 Jun 2023 → 10 Jun 2023

Publication series

Name	HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings

Conference

Conference	5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023
Country/Territory	Turkey
City	Istanbul
Period	8/06/23 → 10/06/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Funding

This project is funded by TIM Akilli Kiyafetleri A.S. and TÜBITAK with the grant number 3220472.

Funders	Funder number
Türkiye Bilimsel ve Teknolojik Araştırma Kurumu	3220472

Keywords

anomaly detection
machine learning
sound detection

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/HORA58378.2023.10156765

Cite this

Suer, S., Koseoglu, I., Oner, R., & Ince, G. (2023). Detection of Clips Failures in Manufacturing using Audio Signals. In HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings (HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/HORA58378.2023.10156765

Suer, Sabri ; Koseoglu, Ilknur ; Oner, Rahim et al. / Detection of Clips Failures in Manufacturing using Audio Signals. HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings).

@inproceedings{65b2ba6de9cf401dba7c444832060bc4,

title = "Detection of Clips Failures in Manufacturing using Audio Signals",

abstract = "In industrial manufacturing processes, such as plugging small connectors in, where visual verification is difficult, workers may experience difficulties in detecting failures. Artificial intelligence algorithms can be used to detect and identify the sound of these connectors and mitigate human error. In this work, sound samples of correctly plugged-in connectors and ordinary background noise of the workplace were collected using a recording setup fastened to workers' hand. In order to discriminate anomalies that represent failures, autoencoder models were trained and tested in an unsupervised manner. Experiments with different deep learning architectures for anomaly detection are conducted. Our CNNAE-FT model achieved best results and yielded a ROC-AUC score of 0.85.",

keywords = "anomaly detection, machine learning, sound detection",

author = "Sabri Suer and Ilknur Koseoglu and Rahim Oner and Gokhan Ince",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023 ; Conference date: 08-06-2023 Through 10-06-2023",

year = "2023",

doi = "10.1109/HORA58378.2023.10156765",

language = "English",

series = "HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings",

address = "United States",

}

Suer, S, Koseoglu, I, Oner, R & Ince, G 2023, Detection of Clips Failures in Manufacturing using Audio Signals. in HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings. HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings, Institute of Electrical and Electronics Engineers Inc., 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023, Istanbul, Turkey, 8/06/23. https://doi.org/10.1109/HORA58378.2023.10156765

Detection of Clips Failures in Manufacturing using Audio Signals. / Suer, Sabri; Koseoglu, Ilknur; Oner, Rahim et al.
HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2023. (HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Detection of Clips Failures in Manufacturing using Audio Signals

AU - Suer, Sabri

AU - Koseoglu, Ilknur

AU - Oner, Rahim

AU - Ince, Gokhan

PY - 2023

Y1 - 2023

N2 - In industrial manufacturing processes, such as plugging small connectors in, where visual verification is difficult, workers may experience difficulties in detecting failures. Artificial intelligence algorithms can be used to detect and identify the sound of these connectors and mitigate human error. In this work, sound samples of correctly plugged-in connectors and ordinary background noise of the workplace were collected using a recording setup fastened to workers' hand. In order to discriminate anomalies that represent failures, autoencoder models were trained and tested in an unsupervised manner. Experiments with different deep learning architectures for anomaly detection are conducted. Our CNNAE-FT model achieved best results and yielded a ROC-AUC score of 0.85.

AB - In industrial manufacturing processes, such as plugging small connectors in, where visual verification is difficult, workers may experience difficulties in detecting failures. Artificial intelligence algorithms can be used to detect and identify the sound of these connectors and mitigate human error. In this work, sound samples of correctly plugged-in connectors and ordinary background noise of the workplace were collected using a recording setup fastened to workers' hand. In order to discriminate anomalies that represent failures, autoencoder models were trained and tested in an unsupervised manner. Experiments with different deep learning architectures for anomaly detection are conducted. Our CNNAE-FT model achieved best results and yielded a ROC-AUC score of 0.85.

KW - anomaly detection

KW - machine learning

KW - sound detection

UR - https://www.scopus.com/pages/publications/85165689395

U2 - 10.1109/HORA58378.2023.10156765

DO - 10.1109/HORA58378.2023.10156765

M3 - Conference contribution

AN - SCOPUS:85165689395

T3 - HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings

BT - HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023

Y2 - 8 June 2023 through 10 June 2023

ER -

Suer S, Koseoglu I, Oner R, Ince G. Detection of Clips Failures in Manufacturing using Audio Signals. In HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings. Institute of Electrical and Electronics Engineers Inc. 2023. (HORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings). doi: 10.1109/HORA58378.2023.10156765

Detection of Clips Failures in Manufacturing using Audio Signals

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this