Abnormal Sound Source Detection and Localization by Spatial Mapping of Normal Sounds for Robotic Inspection in Oil Refineries
International Journal of Automation Technology · 05.05.2025 · 19 (3) · 192-203
DOI: 10.20965/ijat.2025.p0192 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Automation Technology, online erschienen am 05.05.2025. Verfasst von Jun Younes Louhi Kasahara und 15 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 15 Literaturangaben.
Abstract (Originalsprache)
In this paper, we propose a novel approach to detection and localization of abnormal sound sources for robotic inspection in oil refineries. Such environments are difficult environments with high noise from multiple machines and where swift detection of anomalies is critical. The rarity of anomalies hinders the gathering of a balanced training dataset for the common supervised learning approach. Our previous work, based on autoencoders, bypassed this issue but lacked the ability to locate the abnormal sound source. Our proposed method first learns a spatial map of the normal sounds, allowing to predict what sound should be present at each robot position. This enables a detection based on a comparison between the predicted and observed sound. Localization can then be conducted based on this comparison using optimization. Experiments conducted in laboratory conditions showed the effectiveness of the proposed method. Additionally, experiments in field conditions in an actual oil refinery further showed the potential of the proposed method.
Zitieren
APA
Kasahara, J. Y. L., Tanaka, K., Shoda, K., Kinoshita, M., Kasahara, S., Ito, H., Koda, R., Tamura, S., Tanaka, H., Kato, T., Nonaka, F., Kanda, S., Nagatani, K., Asama, H., An, Q., & Yamashita, A. (2025). Abnormal Sound Source Detection and Localization by Spatial Mapping of Normal Sounds for Robotic Inspection in Oil Refineries. International Journal of Automation Technology, 19(3), 192-203. https://doi.org/10.20965/ijat.2025.p0192
Vancouver
Kasahara JYL, Tanaka K, Shoda K, Kinoshita M, Kasahara S, Ito H, et al. Abnormal Sound Source Detection and Localization by Spatial Mapping of Normal Sounds for Robotic Inspection in Oil Refineries. International Journal of Automation Technology. 2025;19(3):192-203. doi:10.20965/ijat.2025.p0192
BibTeX
@article{Kasahara2025,
author = {Kasahara, Jun Younes Louhi and Tanaka, Kentaro and Shoda, Koki and Kinoshita, Masayoshi and Kasahara, Seiji and Ito, Hiroyuki and Koda, Risa and Tamura, Sunao and Tanaka, Hirokazu and Kato, Toshiya and Nonaka, Fumihiko and Kanda, Shinji and Nagatani, Keiji and Asama, Hajime and An, Qi and Yamashita, Atsushi},
title = {Abnormal Sound Source Detection and Localization by Spatial Mapping of Normal Sounds for Robotic Inspection in Oil Refineries},
journal = {International Journal of Automation Technology},
year = {2025},
volume = {19},
number = {3},
pages = {192--203},
doi = {10.20965/ijat.2025.p0192}
}
EUVIMED