Advertisement

Acoustic Anomaly Detection Using Convolutional Autoencoders in Industrial Processes

  • Taha Berkay DumanEmail author
  • Barış Bayram
  • Gökhan İnce
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 950)

Abstract

In the industrial plants, detection of abnormal events during the processes is a difficult task for human operators who need to monitor the production. In this work, the main aim is to detect anomalies in the industrial processes by an intelligent audio based solution for the new generation of factories. Therefore, this paper presents a Convolutional Autoencoder (CAE) based end-to-end unsupervised Acoustic Anomaly Detection (AAD) system to be used in the context of industrial plants and processes. In this research, a new industrial acoustic dataset has been created by gathering the audio data obtained from a number of videos of industrial processes, recorded in factories involving industrial tools and processes. Due to the fact that the anomalous events in real life are rather rare and the creation of these events is highly costly, anomaly event sounds are superimposed to regular factory soundscape by using different Signal-to-Noise Ratio (SNR) values. To show the effectiveness of the proposed system, the performances of the feature extraction and the AAD are evaluated. The comparison has been made between CAE, One-Class Support Vector Machine (OCSVM), and a hybrid approach of them (CAE-OCSVM) under various SNRs for different anomaly and process sounds. The results showed that CAE with the end-to-end strategy outperforms OCSVM while the respective results are close to the results of hybrid approach.

Keywords

Anomaly detection Industrial processes Convolutional autoencoders One-Class Support Vector Machine Signal-to-Noise Ratio Audio feature extraction 

References

  1. 1.
    Salamon, J., Bello, J.P.: Deep convolutional neural networks and data augmentation for environmental sound classification. IEEE Signal Process. Lett. 24(3), 279–283 (2017).  https://doi.org/10.1109/LSP.2017.2657381CrossRefGoogle Scholar
  2. 2.
    Chou, P.H., Wu, M.J., Chen, K.K.: Integrating support vector machine and genetic algorithm to implement dynamic wafer quality prediction system. Expert Syst. Appl. 37(6), 4413–4424 (2010).  https://doi.org/10.1016/j.eswa.2009.11.087CrossRefGoogle Scholar
  3. 3.
    Cariño-Corrales, J.A., Saucedo-Dorantes, J.J., Zurita-Millán, D., Delgado-Prieto, M., Ortega-Redondo, J.A., Alfredo Osornio-Rios, R., de Jesus Romero-Troncoso, R.: Vibration-based adaptive novelty detection method for monitoring faults in a kinematic chain. Shock Vibr. 2016, 1–12 (2016).  https://doi.org/10.1155/2016/2417856CrossRefGoogle Scholar
  4. 4.
    Carino, J.A., Delgado-Prieto, M., Zurita, D., Millan, M., Redondo, J.A.O., Romero-Troncoso, R.: Enhanced industrial machinery condition monitoring methodology based on novelty detection and multi-modal analysis. IEEE Access 4, 7594–7604 (2016).  https://doi.org/10.1109/ACCESS.2016.2619382CrossRefGoogle Scholar
  5. 5.
    Narayanan, V., Bobba, R.B.: Learning based anomaly detection for industrial arm applications. In: Proceedings of the 2018 Workshop on Cyber-Physical Systems Security and PrivaCy, pp. 13–23. ACM (2018).  https://doi.org/10.1145/3264888.3264894
  6. 6.
    Jia, X., Zhao, M., Di, Y., Yang, Q., Lee, J.: Assessment of data suitability for machine prognosis using maximum mean discrepancy. IEEE Trans. Industr. Electron. 65(7), 5872–5881 (2018).  https://doi.org/10.1109/TIE.2017.2777383CrossRefGoogle Scholar
  7. 7.
    Diez-Olivan, A., Del Ser, J., Galar, D., Sierra, B.: Data fusion and machine learning for industrial prognosis: trends and perspectives towards industry 4.0. Inf. Fusion 50, 92–111 (2019).  https://doi.org/10.1016/j.inffus.2018.10.005CrossRefGoogle Scholar
  8. 8.
    Aurino, F., Folla, M., Gargiulo, F., Moscato, V., Picariello, A., Sansone, C.: One-class SVM based approach for detecting anomalous audio events. In: 2014 International Conference on Intelligent Networking and Collaborative Systems, pp. 145–151. IEEE (2014).  https://doi.org/10.1109/INCoS.2014.59
  9. 9.
    Popescu, M., Mahnot, A.: Acoustic fall detection using one-class classifiers. In: 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 3505–3508. IEEE (2009)Google Scholar
  10. 10.
    Erfani, S.M., Rajasegarar, S., Karunasekera, S., Leckie, C.: High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning. Pattern Recogn. 58, 121–134 (2016).  https://doi.org/10.1016/j.patcog.2016.03.028CrossRefGoogle Scholar
  11. 11.
    Marchi, E., Vesperini, F., Eyben, F., Squartini, S., Schuller, B.: A novel approach for automatic acoustic novelty detection using a denoising autoencoder with bidirectional LSTM neural networks. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1996–2000. IEEE (2015).  https://doi.org/10.1109/ICASSP.2015.7178320
  12. 12.
    Marchi, E., Vesperini, F., Squartini, S., Schuller, B.: Deep recurrent neural network-based autoencoders for acoustic novelty detection. Comput. Intell. Neurosci. vol. 2017, (2017).  https://doi.org/10.1155/2017/4694860CrossRefGoogle Scholar
  13. 13.
    Principi, E., Vesperini, F., Squartini, S., Piazza, F.: Acoustic novelty detection with adversarial autoencoders. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 3324–3330. IEEE (2017).  https://doi.org/10.1109/IJCNN.2017.7966273
  14. 14.
    Droghini, D., Ferretti, D., Principi, E., Squartini, S., Piazza, F.: An end-to-end unsupervised approach employing convolutional neural network autoencoders for human fall detection. In: Italian Workshop on Neural Nets, pp. 185–196. Springer (2017).  https://doi.org/10.1007/978-3-319-95095-2_18Google Scholar
  15. 15.
    Hartman, D.A.: Real-time detection of processing flaws during inertia friction welding of critical components. In: ASME Turbo Expo 2012: Turbine Technical Conference and Exposition, pp. 1–10. American Society of Mechanical Engineers (2012).  https://doi.org/10.1115/GT2012-68014
  16. 16.
    Piczak, K.J.: Environmental sound classification with convolutional neural networks. In: 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP), pp. 1–6. IEEE (2015).  https://doi.org/10.1109/MLSP.2015.7324337
  17. 17.
    Youden, W.J.: Index for rating diagnostic tests. Cancer 3(1), 32–35 (1950)CrossRefGoogle Scholar
  18. 18.
    Fonseca, E., Plakal, M., Ellis, D.P., Font, F., Favory, X., Serra, X.: Learning sound event classifiers from web audio with noisy labels. arXiv preprint arXiv:1901.01189 (2019)

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Taha Berkay Duman
    • 1
    Email author
  • Barış Bayram
    • 1
  • Gökhan İnce
    • 1
  1. 1.Faculty of Computer and Informatics EngineeringIstanbul Technical UniversityIstanbulTurkey

Personalised recommendations