Detection of Clips Failures in Manufacturing using Audio Signals

Sabri Suer, Ilknur Koseoglu, Rahim Oner, Gokhan Ince

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

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 languageEnglish
Title of host publicationHORA 2023 - 2023 5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9798350337525
DOIs
Publication statusPublished - 2023
Event5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023 - Istanbul, Turkey
Duration: 8 Jun 202310 Jun 2023

Publication series

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

Conference

Conference5th International Congress on Human-Computer Interaction, Optimization and Robotic Applications, HORA 2023
Country/TerritoryTurkey
CityIstanbul
Period8/06/2310/06/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

  • anomaly detection
  • machine learning
  • sound detection

Fingerprint

Dive into the research topics of 'Detection of Clips Failures in Manufacturing using Audio Signals'. Together they form a unique fingerprint.

Cite this