Applications of generative models with a latent observation subspace in vibrodiagnostics

• Autorzy: Puchalski Andrzej , Komorska Iwona

Identyfikatory

DOI

10.29354/diag/176854

• Języki publikacji: EN

Abstrakty

EN

The vibration signal is one of the most essential diagnostic signals, the analysis of which allows for determining the dynamic state of the monitored machine set. In the era of cyber-physical industrial systems, making diagnostic decisions involves the study of large databases from previous registers and data downloaded from machines in real-time. However, the recorded signals mainly concern the operational status of the monitored object. Insufficient training data regarding failure states hinders the operation of classification algorithms. Progress in machine learning has created a new avenue for the advancement of diagnostic methods based on models. These methods now have the capability to produce signals through random sampling from a hidden space or generate fresh instances of input data from noise. The article suggests the use of a Generative Adversarial Network (GAN) model as a tool to create synthetic measurement observations for vibration monitoring. The effectiveness of the synthetic data generation algorithm was verified on the example of the vibration signal recorded during tests of the drive system of a motor vehicle.

Słowa kluczowe

EN

vibration signal; deep neural network; generative adversarial network; GAN model; synthetic subspace

PL

sygnał wibracyjny; sieć neuronowa głęboka; GAN; wibrodiagnostyka

• Wydawca: Polskie Towarzystwo Diagnostyki Technicznej
• Czasopismo: Diagnostyka
• Rocznik: 2023
• Tom: Vol. 24, No. 4
• Strony: art. no. 2023413
• Opis fizyczny: Bibliogr. 19 poz., rys., tab.

Twórcy

autor

Puchalski Andrzej

• Casimir Pulaski Radom University, Mechanical Faculty, Stasieckiego 54, 26-600 Radom, Poland

• https://orcid.org/0000-0002-5202-3410

autor

Komorska Iwona

• Casimir Pulaski Radom University, Mechanical Faculty, Stasieckiego 54, 26-600 Radom, Poland

• https://orcid.org/0000-0002-6911-0297

Bibliografia

• 1. Abdel-Jaber H, Devassy D, Al Salam A, Hidaytallah L, EL-Amir M. A review of deep learning algorithms and their applications in healthcare. Algorithms 2022; 15(2): 71. https://doi.org/10.3390/a15020071.
• 2. Alqahtani H, Kavakli-Thorne M, Kumar G. Applications of generative adversarial networks (GANs): an updated review. Archives of Computational Methods in Engineering 2021; 28(2): 525-552. https://doi.org/10.1007/s11831-019-09388-y.
• 3. Dash A, Ye J, Wang G. A review of generative adversarial networks (GANs) and its applications in a wide variety of disciplines - from medical to remote sensing. 2021. https://doi.org/10.48550/arXiv.2110.01442.
• 4. Donahue C, McAuley J, Puckette M. Adversarial audio synthesis. ICLR 2019:1-16. https://doi.org/10.48550/arXiv.1802.04208.
• 5. Goodfellow I, Bengio Y, Courville A. Deep learning. Massachusetts Institute of Technology Press 2016.
• 6. Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S. Generative adversarial networks. Communications of the ACM 2020; 63(11): 139-44. https://doi.org/10.1145/3422622.
• 7. Goodfellow I. NIPS 2016 tutorial: generative adversarial networks. 2017. https://doi.org/10.48550/arXiv.1701.00160.
• 8. Hassani H, Razavi-Far R, Saif M, Palade V. Generative adversarial network-based scheme for diagnosing faults in cyber-physical power systems. Sensors 2021;21(15):5173. https://doi.org/10.3390/s21155173.
• 9. Jang K, Hong S, Kim M, Na J, Moon I. Adversarial autoencoder based feature learning for fault detection in industrial processes. IEEE Transactions on Industrial Informatics 2022; 18(2): 827-34. https://doi.org/10.1109/TII.2021.3078414.
• 10. Kingma DP, Rezende DJ, Mohamed S, Welling M. Semi-supervised learning with deep generative models. 2014. https://doi.org/10.48550/arXiv.1406.5298.
• 11. Kingma DP, Welling M. Auto-encoding variational bayes. 2022. https://doi.org/10.48550/arXiv.1312.6114.
• 12. Kingma DP. Fast gradient-based inference with continuous latent variable models in auxiliary form. 2013. https://doi.org/10.48550/arXiv.1306.0733.
• 13. Nikolenko SI. Synthetic data for deep learning. Springer optimization and its applications 2021; 174. https://doi.org/10.1007/978-3-030-75178-4.
• 14. Puchalski A, Komorska I. Generative modelling of vibration signals in machine maintenance. Eksploatacja i Niezawodnosc - Maintenance and Reliability 2023;25(4). http://doi.org/10.17531/ein/173488.
• 15. Ramires A, Chandna P, Favory X, G'omez E, Serra X. Neural percussive synthesis parameterised by high-level timbral features. ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) 2019; 786-790.
• 16. Razghandi M, Zhou H, Erol-Kantarci M, Turgut D. Variational autoencoder generative adversarial network for synthetic data generation in smart home . 2022. https://doi.org/10.48550/arXiv.2201.07387.
• 17. Regenwetter L, Nobari AH, Ahmed F. Deep generative models in engineering design: a review. 2022. https://doi.org/10.48550/arXiv.2110.10863. 18. Salimans T, Goodfellow I, Zaremba W, Cheung V, Radford A, Chen X. Improved techniques for training GANs. 2016. https://doi.org/10.48550/arXiv.1606.03498.
• 19. Tomczak JM. Deep generative modeling. Deep Generative Modeling. Cham: Springer International Publishing 2022; 1-197.