Transformer and Graph Convolution-Based Unsupervised Detection of Machine Anomalous Sound Under Domain Shifts

Thanks to the development of deep learning, machine abnormal sound detection (MASD) based on unsupervised learning has exhibited excellent performance. However, in the task of unsupervised MASD, there are discrepancies between the acoustic characteristics of the test set and the training set under t...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on emerging topics in computational intelligence Vol. 8; no. 4; pp. 2827 - 2842
Main Authors: Yan, Jingke, Cheng, Yao, Wang, Qin, Liu, Lei, Zhang, Weihua, Jin, Bo
Format: Journal Article
Language:English
Published: Piscataway IEEE 01.08.2024
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Artificial neural networks
Computational modeling
Convolution
Data mining
Data models
Deep learning
domain shift
Feature extraction
machine anomalous sound detection
Machine learning
Physical properties
Sound
Task analysis
Time-frequency analysis
Transformers
Unsupervised learning
ISSN:2471-285X, 2471-285X
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Thanks to the development of deep learning, machine abnormal sound detection (MASD) based on unsupervised learning has exhibited excellent performance. However, in the task of unsupervised MASD, there are discrepancies between the acoustic characteristics of the test set and the training set under the physical parameter changes (domain shifts) of the same machine's operating conditions. Existing methods not only struggle to stably learn the sound signal features under various domain shifts but also inevitably increase computational overhead. To address these issues, we propose an unsupervised machine abnormal sound detection model based on Transformer and Dynamic Graph Convolution (Unsuper-TDGCN) in this paper. Firstly, we design a network that models time-frequency domain features to capture both global and local spatial and time-frequency interactions, thus improving the model's stability under domain shifts. Then, we introduce a Dynamic Graph Convolutional Network (DyGCN) to model the dependencies between features under domain shifts, enhancing the model's ability to perceive changes in domain features. Finally, a Domain Self-adaptive Network (DSN) is employed to compensate for the performance decline caused by domain shifts, thereby improving the model's adaptive ability for detecting anomalous sounds in MASD tasks under domain shifts. The effectiveness of our proposed model has been validated on multiple datasets.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2471-285X
2471-285X
DOI:10.1109/TETCI.2024.3377728