Unsupervised Anomaly Detection Method for Electrical Equipment Based on Audio Latent Representation and Parallel Attention Mechanism
Source abstract
Abstract
The stable operation of electrical equipment is critical for industrial safety, yet traditional anomaly detection methods often suffer from limitations, such as high resource demands, dependency on expert knowledge, and lack of real-world capabilities. To address these challenges, this article proposes an unsupervised anomaly detection method for electrical equipment, utilizing audio latent representation and a parallel attention mechanism. The framework employs an autoencoder to extract low-dimensional features from audio signals and introduces a phase-aware parallel attention block to dynamically weight these features for an improved anomaly sensitivity. With adversarial training and a dual-encoding mechanism, the proposed method demonstrates robust performance in complex scenarios. Using public datasets (MIMII and ToyADMOS) and our collected real-world wind turbine data, it achieves high AUC scores, surpassing the best baselines, which demonstrates our framework design is suitable for industrial applications.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Technology and Security Systems
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Power China Chengdu Engineering Corporation Limited, Chengdu 610072, China
School of Communications and Information Engineering, Chongqing University of Posts and Telecommunications, Chongqing 400065, China
References (41)
Show source-provided references
1. Drill Fault Diagnosis Based on the Scalogram and Mel Spectrogram of Sound Signals Using Artificial Intelligence10.1109/ACCESS.2020.3036769 ↗
2. A periodic inspection and replacement policy for systems subject to competing failure modes due to degradation and traumatic events10.1016/j.ress.2010.12.018 ↗
3. An expert rule-based fault diagnosis strategy for variable refrigerant flow air conditioning systems10.1016/j.applthermaleng.2018.12.132 ↗
4. Smart multichannel mode extraction for enhanced bearing fault diagnosis10.1016/j.ymssp.2023.110107 ↗
5. Vibration-based anomaly detection using LSTM/SVM approaches10.1016/j.ymssp.2021.108752 ↗
6. Road Abnormality Detection Using Piezoresistive Force Sensors and Adaptive Signal Models10.1109/TIM.2022.3194900 ↗
7. Magnetic Anomaly Detection Based on Energy-Concentrated Discrete Cosine Wavelet Transform
8. Empirical mode decomposition-empowered network traffic anomaly detection for secure multipath TCP communications10.1007/s11036-022-02005-6 ↗
9. A performance-interpretable intelligent fusion of sound and vibration signals for bearing fault diagnosis via dynamic CAME10.1007/s11071-024-10157-1 ↗
10. Akcay, S., Atapour-Abarghouei, A., and Breckon, T.P. (2018, January 2–6). Ganomaly: Semi-supervised anomaly detection via adversarial training. Proceedings of the Computer Vision—ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia. Revised Selected Papers, Part III 14.
11. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
12. The Doppler Effect based acoustic source separation for a wayside train bearing monitoring system10.1016/j.jsv.2015.09.038 ↗
13. Kumar, J., Sharma, S., and Bharti, A.K. (2021, January 9–10). Fault detection and classification in automobile engine based on its audio signature using support vector machine. In Proceedings of the ICCCE 2021: 4th International Conference on Communications and Cyber Physical Engineering, Hyderabad, India.
14. Fault diagnosis of automobile power seat with acoustic analysis and retrained SVM based on smartphone10.1016/j.measurement.2022.111699 ↗
15. A local knit pattern-based automated fault classification method for the cooling system of the data center10.1016/j.apacoust.2020.107888 ↗
16. Support vector machines10.1109/5254.708428 ↗
17. Zhu, W., Liu, H., Zhou, Y., Gan, L., and Ma, Y. (2021, January 17–20). Wind turbine blade fault detection by acoustic analysis: Preliminary results. Proceedings of the 2021 IEEE International Conference on Signal Processing, Communications and Computing (ICSPCC), Xi’an, China.10.1109/ICSPCC52875.2021.9564938 ↗
18. Zhang, J., Liu, W., Lan, J., Hu, Y., and Zhang, F. (2021, January 4–6). Audio Fault Analysis for Industrial Equipment Based on Feature Metric Engineering with CNNs. Proceedings of the 2021 4th International Conference on Robotics, Control and Automation Engineering (RCAE), Wuhan, China.10.1109/RCAE53607.2021.9638896 ↗
19. A machine learning-based multiclass classification model for bee colony anomaly identification using an IoT-based audio monitoring system with an edge computing framework10.1016/j.eswa.2024.124898 ↗
20. Peng, B., Wang, K., and Abdulla, W. (2025). Robust Classification of Urban Sounds in Noisy Environments: A Novel Approach Using SPWVD-MFCC and Dual-Stream Classifier. Acoust. Aust.10.1007/s40857-025-00350-6 ↗
21. Peng, B., Li, D., Wang, K.I.K., and Abdulla, W.H. (2025). Acoustic-Based Industrial Diagnostics: A Scalable Noise-Robust Multiclass Framework for Anomaly Detection. Processes, 13.10.3390/pr13020544 ↗
22. Yan, H., Zhan, X., Wu, Z., Cheng, J., Wen, L., and Jia, X. (2024). Unsupervised anomalous sound detection method based on Gammatone spectrogram and adversarial autoencoder with attention mechanism. Proc. Inst. Mech. Eng. Part E J. Process Mech. Eng., 09544089241258027.10.1177/09544089241258027 ↗
23. Anomaly Detection in Sound Activity with Generative Adversarial Network Models10.5753/jisa.2024.3897 ↗
24. Radford, A., Metz, L., and Chintala, S. (2015). Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv.
25. Hojjati, H., and Armanfard, N. (2022, January 23–27). Self-supervised acoustic anomaly detection via contrastive learning. Proceedings of the ICASSP 2022—2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore.10.1109/ICASSP43922.2022.9746207 ↗
26. Guan, J., Xiao, F., Liu, Y., Zhu, Q., and Wang, W. (2023, January 4–10). Anomalous sound detection using audio representation with machine ID based contrastive learning pretraining. Proceedings of the ICASSP 2023—2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Rhodes Island, Greece.10.1109/ICASSP49357.2023.10096054 ↗
27. Gu, A., and Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. arXiv.
28. SSDPT: Self-supervised dual-path transformer for anomalous sound detection10.1016/j.dsp.2023.103939 ↗
29. Shams, S., Dindar, S.S., Jiang, X., and Mesgarani, N. (2024, January 2–5). SSAMBA: Self-Supervised Audio Representation Learning With Mamba State Space Model. Proceedings of the 2024 IEEE Spoken Language Technology Workshop (SLT), Macau, China.10.1109/SLT61566.2024.10832304 ↗
30. Qu, X., Liu, Z., Wu, C.Q., Hou, A., Yin, X., and Chen, Z. (2024). MFGAN: Multimodal Fusion for Industrial Anomaly Detection Using Attention-Based Autoencoder and Generative Adversarial Network. Sensors, 24.10.3390/s24020637 ↗
31. Variational bayesian clustering algorithm for unsupervised anomalous sound detection incorporating VH-BCL+10.1007/s11042-023-17006-0 ↗
32. Khan, M., Negi, A., Kulkarni, A., Phutke, S.S., Vipparthi, S.K., and Murala, S. (2024). Phaseformer: Phase-based Attention Mechanism for Underwater Image Restoration and Beyond. arXiv.10.1109/WACV61041.2025.00931 ↗
33. Purohit, H., Tanabe, R., Ichige, T., Endo, T., Nikaido, Y., Suefusa, K., and Kawaguchi, Y. (2019, January 25–26). MIMII Dataset: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection. Proceedings of the Detection and Classification of Acoustic Scenes and Events 2019 Workshop (DCASE2019), New York, NY, USA.10.33682/m76f-d618 ↗
34. Koizumi, Y., Saito, S., Uematsu, H., Harada, N., and Imoto, K. (2019, January 20–23). ToyADMOS: A Dataset of Miniature-Machine Operating Sounds for Anomalous Sound Detection. Proceedings of the 2019 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA.10.1109/WASPAA.2019.8937164 ↗
35. Ono, N., Harada, N., Kawaguchi, Y., Mesaros, A., Imoto, K., Koizumi, Y., and Komatsu, T. (2020). Proceedings of the Fifth Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE 2020), Zenodo.
36. Nonintrusive wind blade fault detection using a deep learning approach by exploring acoustic informationa)10.1121/10.0016998 ↗
37. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
38. Zenati, H., Foo, C.S., Lecouat, B., Manek, G., and Chandrasekhar, V.R. (2018). Efficient gan-based anomaly detection. arXiv.
39. Suefusa, K., Nishida, T., Purohit, H., Tanabe, R., Endo, T., and Kawaguchi, Y. (2020, January 4–8). Anomalous Sound Detection Based on Interpolation Deep Neural Network. Proceedings of the ICASSP 2020—2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain.10.1109/ICASSP40776.2020.9054344 ↗
40. Wichern, G., Chakrabarty, A., Wang, Z.Q., and Roux, J.L. (2021, January 17–20). Anomalous Sound Detection Using Attentive Neural Processes. Proceedings of the 2021 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), New Paltz, NY, USA.10.1109/WASPAA52581.2021.9632762 ↗
41. Zhenhua, L., Ling, Z., Gao, J., Yu, K., and Jia, J. (2022, January 15–18). Predictive AutoEncoders Are Context-Aware Unsupervised Anomalous Sound Detectors. Proceedings of the Man-Machine Speech Communication, Hefei, China.