Home Journals Articles Updates About
CN
image
收藏切换
An Anomalous Sound Detection Algorithm Based on Attention and Domain Generalization
收藏切换
PDF
Xuan ZHANG1, Zheng-kang ZHOU2, Jia-shan TANG1, *
Science Technology and Engineering | 2025, 25(15) : 6310 - 6317
Less
收藏切换
Science Technology and Engineering | 2025, 25(15): 6310-6317
• Papers·Mechanical and Instrumental Industry •
An Anomalous Sound Detection Algorithm Based on Attention and Domain Generalization
Full
Xuan ZHANG1, Zheng-kang ZHOU2, Jia-shan TANG1, *
Affiliations
  • 1 College of Science, Nanjing University of Posts and Telecommunications, Nanjing 210023
  • 2 Nanjing Urban Construction Tunnel & Bridge Intelligent Management Co., Ltd., Nanjing 211800, China
Published: 2025-05-28 doi: 10.12404/j.issn.1671-1815.2405433
Outline
收藏切换

A new anomaly sound detection algorithm was studied that combines attention mechanisms and domain generalization techniques to more accurately identify normal and abnormal sounds in mechanical equipment. Specifically, two neural networks were jointly trained using a sub-cluster Adacos loss function, with features modeled by a Gaussian mixture model (GMM). Anomaly scores were calculated using negative log-likelihood values, and a 90th percentile threshold was set for detection. The algorithm demonstrated strong performance across seven types of machines, including fans and bearings, achieving harmonic mean AUC(area under curve) and pAUC values of 76.69% and 87.99%, with the highest performance observed on valve data. Compared to two baseline systems, the algorithm improved AUC and pAUC by 24.08% and 20.68%, respectively. Ablation studies further confirmed the positive impact of the GMM, attention mechanism, and Scadacos loss function. When tested against eight other algorithms on the same dataset, the proposed method showed a 4.16% improvement in the harmonic mean of AUC and pAUC, highlighting its significant advantage in anomaly sound detection tasks.

anomaly sound detection  /  unsupervised learning  /  domain generalization  /  attention mechanism  /  deep learning
Xuan ZHANG, Zheng-kang ZHOU, Jia-shan TANG. An Anomalous Sound Detection Algorithm Based on Attention and Domain Generalization[J]. Science Technology and Engineering, 2025 , 25 (15) : 6310 -6317 . DOI: 10.12404/j.issn.1671-1815.2405433
Appendix
Less
Year 2025 volume 25 Issue 15
PDF
352
137
Cite this Article
BibTeX
Article Info
doi: 10.12404/j.issn.1671-1815.2405433
  • Receive Date：2024-07-19
  • Online Date：2025-07-09
  • Published：2025-05-28
Article Data
Affiliations
History
  • Received：2024-07-19
  • Revised：2024-11-24
Funding
Affiliations
    1 College of Science, Nanjing University of Posts and Telecommunications, Nanjing 210023
    2 Nanjing Urban Construction Tunnel & Bridge Intelligent Management Co., Ltd., Nanjing 211800, China
References
Share
https://castjournals.cast.org.cn/joweb/kxjsygc/EN/10.12404/j.issn.1671-1815.2405433
Share to
QR

Scan QR to access full text

Cite this article
BibTeX
Citations
表12种不同金属材料的力学参数
科
Family		 属数
Number of
genus		 种数
Number of
species		 占总种数比例
Percentage of
total species (%)		 属
Genus		 种数
Number of
species		 占总种数比例
Percentage of total
species (%)
鹅膏菌科Amanitaceae 2 11 5.26 鹅膏菌属 Amanita 10 4.78
小菇科 Mycenaceae 2 12 5.74 丝盖伞属 Inocybe 5 2.39
多孔菌科 Polyporaceae 8 14 6.70 蜡蘑属 Laccaria 5 2.39
红菇科 Russulaceae 3 23 11.00 小皮伞属 Marasmius 6 2.87
小菇属 Mycena 11 5.26
光柄菇属 Pluteus 5 2.39
红菇属 Russula 17 8.13
栓菌属 Trametes 5 2.39
关闭全屏
  • BibTeX
  • EndNote
  • RefWorks
  • TxT
Links
Articles
Latest Articles
Most Read
Collections
Updates
Events
News
Multimedia
About
About Us
Contact
No. 86 Xueyuan South Road, Haidian District, Beijing
100081
010-62199257
qkjq@cast.org.cn

Copyright © 2025 China Association for Science and Technology. All rights reserved. For all open access content, the relevant licensing terms apply.
Sponsored by the Office of the Leading Group for Cybersecurity and Informatization of CAST, and supported by Science and Technology Review Publishing House