Abstract
Acoustic Industrial Anomaly Detection (AIAD) has received a great deal of attention as a technique to discover faults or malicious activity, allowing for preventive measures to be more effectively targeted. The essence of AIAD is to learn the compact distribution of normal acoustic data and detect outliers as anomalies during testing. However, recent AIAD work does not capture the dependencies and dynamics of Acoustic Industrial Data (AID). To address this issue, we propose a novel Contrastive Learning Framework (CLF) for AIAD, known as CLF-AIAD. Our method introduces a multi-grained contrastive learning-based framework to extract robust normal AID representations. Specifically, we first employ a projection layer and a novel context-based contrast method to learn robust temporal vectors. Building upon this, we then introduce a sample-wise contrasting-based module to capture local invariant characteristics, improving the discriminative capabilities of the model. Finally, a transformation classifier is introduced to bolster the performance of the primary task under a self-supervised learning framework. Extensive experiments on two typical industrial datasets, MIMII and ToyADMOS, demonstrate that our proposed CLF-AIAD effectively detects various real-world defects and improves upon the state-of-the-art in unsupervised industrial anomaly detection.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bigoni, C., Hesthaven, J.S.: Simulation-based anomaly detection and damage localization: an application to structural health monitoring. Comput. Methods Appl. Mech. Eng. 363, 112896 (2020)
Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning, pp. 1597–1607. PMLR (2020)
Cui, Y., Liu, Z., Lian, S.: A survey on unsupervised industrial anomaly detection algorithms. arXiv preprint: 2204.11161 (2022)
Defard, T., Setkov, A., Loesch, A., Audigier, R.: Padim: a patch distribution modeling framework for anomaly detection and localization. In: Pattern Recognition, pp. 475–489 (2021)
Dohi, K., Endo, T., Purohit, H., Tanabe, R., Kawaguchi, Y.: Flow-based self-supervised density estimation for anomalous sound detection. In: Proceedings of ICASSP, pp. 336–340 (2021)
Dohi, K., Imoto, K., et al.: Description and discussion on dcase 2022 challenge task 2: Unsupervised anomalous sound detection for machine condition monitoring applying domain generalization techniques. arXiv preprint: 2206.05876 (2022)
Eldele, E., Ragab, M., Chen, Z., Wu, M., et al.: Time-series representation learning via temporal and contextual contrasting, pp. 2352–2359, August 2021
Eltouny, K., Gomaa, M., Liang, X.: Unsupervised learning methods for data-driven vibration-based structural health monitoring: a review. Sensors 23(6), 3290 (2023)
Gong, D., Liu, L., Le, V., Saha, B., Mansour, M.R., et al.: Memorizing normality to detect anomaly: Memory-augmented deep autoencoder for unsupervised anomaly detection. In: Proceedings of ICCV, pp. 1705–1714 (2019)
He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of CVPR, pp. 9729–9738 (2020)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of CVPR, pp. 770–778 (2016)
Hojjati, H., Armanfard, N.: Dasvdd: Deep autoencoding support vector data descriptor for anomaly detection. arXiv preprint: 2106.05410 (2021)
Hojjati, H., Armanfard, N.: Self-supervised acoustic anomaly detection via contrastive learning. In: Proceedings of ICASSP, pp. 3253–3257 (2022)
Jiang, A., Zhang, W.Q., et al.: Unsupervised anomaly detection and localization of machine audio: a gan-based approach. In: Proceedings of ICASSP, pp. 1–5 (2023)
Kawaguchi, Y., Imoto, K., et al.: Description and discussion on dcase 2021 challenge task 2: Unsupervised anomalous sound detection for machine condition monitoring under domain shifted conditions. arXiv preprint: 2106.04492 (2021)
Kim, M.S., Yun, J.P., Lee, S., Park, P.: Unsupervised anomaly detection of lm guide using variational autoencoder. In: Proceedings of ATEE, pp. 1–5 (2019)
Koizumi, Y., Saito, S., Uematsu, H., Harada, N.: Optimizing acoustic feature extractor for anomalous sound detection based on neyman-pearson lemma. In: Proceedings of EUSIPCO, pp. 698–702 (2017)
Koizumi, Y., Saito, S., Uematsu, H., Harada, N., Imoto, K.: Toyadmos: a dataset of miniature-machine operating sounds for anomalous sound detection. In: Proceedings of WASPAA, pp. 313–317 (2019)
Liu, Y., Garg, S., Nie, J., Zhang, Y., et al.: Deep anomaly detection for time-series data in industrial IoT: a communication-efficient on-device federated learning approach. IEEE Internet Things J. 8(8), 6348–6358 (2020)
Liu, Z., Tang, H., Michiels, S., Joosen, W., Hughes, D.: Unsupervised acoustic anomaly detection systems based on gaussian mixture density neural network. In: Proceedings of EUSIPCO, pp. 259–263 (2022)
Lu, H., Fu, Y., Qin, H., Huang, S., et al.: Anomalous sounds detection using autoencoder and classification methods. Technival report, DCASE2021 Challenge (2021)
McLachlan, G.J.: Mahalanobis distance. Resonance 4(6), 20–26 (1999)
Patcha, A.: An overview of anomaly detection techniques: existing solutions and latest technological trends. Comput. Netw. 51(12), 3448–3470 (2007)
Purohit, H., Tanabe, R., et al.: Mimii dataset: sound dataset for malfunctioning industrial machine investigation and inspection. arXiv preprint: 1909.09347 (2019)
Ruff, L., et al.: A unifying review of deep and shallow anomaly detection. Proc. IEEE 109(5), 756–795 (2021)
Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. Advances in neural information processing systems 29 (2016)
Suefusa, K., Nishida, T., Purohit, H., et al.: Anomalous sound detection based on interpolation deep neural network. In: Proceedings of ICASSP, pp. 271–275 (2020)
Taheri, H., Koester, L.W., et al.: In situ additive manufacturing process monitoring with an acoustic technique: clustering performance evaluation using k-means algorithm. J. Manuf. Sci. Eng. 141(4) (2019)
Trapp, M., Chen, F.: Automotive buzz, squeak and rattle: mechanisms, analysis, evaluation and prevention. Elsevier (2011)
Tuli, S., Casale, G., et al.: Tranad: Deep transformer networks for anomaly detection in multivariate time series data. arXiv preprint: 2201.07284 (2022)
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)
Yue, Z., Wang, Y., Duan, J., Yang, T., et al.: Ts2vec: Towards universal representation of time series. In: Proceedings of AAAI, vol. 36, pp. 8980–8987 (2022)
Yun, H., Kim, H., Jeong, Y.H., Jun, M.B.: Autoencoder-based anomaly detection of industrial robot arm using stethoscope based internal sound sensor. J. Intell. Manuf. 34(3), 1427–1444 (2023)
Zhang, W., Yang, D., Peng, H., Wu, W., et al.: Deep reinforcement learning based resource management for dnn inference in industrial iot. IEEE Trans. Veh. Technol. 70(8), 7605–7618 (2021)
Zhang, Z., Zhao, Z., Zhang, X., et al.: Industrial anomaly detection with domain shift: a real-world dataset and masked multi-scale reconstruction. arXiv preprint: 2304.02216 (2023)
Acknowledgements
Research Fund KU Leuven in the context of the ReSOS project (C3/20/014) and by Ford Motor Company in the context of the Ford-KU Leuven Research Alliance project Automated S &R (KUL0134).
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Liu, Z. et al. (2024). CLF-AIAD: A Contrastive Learning Framework for Acoustic Industrial Anomaly Detection. In: Luo, B., Cheng, L., Wu, ZG., Li, H., Li, C. (eds) Neural Information Processing. ICONIP 2023. Communications in Computer and Information Science, vol 1961. Springer, Singapore. https://doi.org/10.1007/978-981-99-8126-7_10
Download citation
DOI: https://doi.org/10.1007/978-981-99-8126-7_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-8125-0
Online ISBN: 978-981-99-8126-7
eBook Packages: Computer ScienceComputer Science (R0)