Identification of temporal anomalies of spectrograms of vibration measurements of a turbine generator rotor using a recurrent neural network autoencoder

A method is proposed for recognizing pre-emergency conditions of rotary installations based on the use of the Hamming window and advanced Deep Learning techniques in retrospective analysis of the results of accounting for the factors of operation of a turbine generator, diagnostics and control under critical impacts. A program of experimental studies on the model of a turbine plant with simulation of faults and receiving vibration signals has been developed. An experiment based on the homostatic method of checking the signal with Hamming windows, in the frequency, time and modulation domains and common initial data, allows one to determine the most promising signal characteristics for identification. A method has been developed for monitoring the state of turbine generators in an automatic mode for timely notification of the CHPP personnel about the appearance of signs of pre-emergency situations, as well as about the nature of faults by the method of predicting the state of a pre-emergency situation using convolutional neural networks implemented in the form of a recurrent autoencoder. Clustering is applied and clusters are identified that correspond to the spectrograms of pre-emergency situations. The effectiveness of the use of the homostatic method in combination with correlation analysis is based on the decision-making model described in more detail in other works.

1. Sobra J., Vaimann T., Belahcen A. Mechanical vibration analysis of induction machine under dynamic rotor eccentricity. In: Proceedings of 17th International Scientific Conference on Electric Power Engineering (EPE). Prague, Czech Republic, 2016, p. 1−4. https://doi.org/10.1109/EPE.2016.7521732

2. Boudiaf A., Djebala A., Bendjma H., Balaska A., Dahane A. A summary of vibration analysis techniques for fault detection and diagnosis in bearing. In: Proceedings of 8th International Conference on Modelling, Identification and Control (ICMIC). Algiers, Algeria, 2016, p. 37−42. https://doi.org/10.1109/ICMIC.2016.7804187

3. Wei Li, Mingquan Qiu, Zhencai Zhu, Bo Wu, Gongbo Zhou. Bearing fault diagnosis based on spectrum images of vibration signals. Meas. Sci. Technol.2016;27(3): Article ID 035005. https://doi.org/10.1088/0957-0233/27/3/035005

4. Serdukova L., Kuske R., Yurchenko D. Post-grazing dynamics of a vibro-impacting energy generator. J. Sound and Vibration. 2020;492: Article ID 115811. https://doi.org/10.1016/j.jsv.2020.115811

5. Okhtilev M.Yu., Sokolov B.V., Yusupov R.M. Intellektual’nye tekhnologii monitoringa i upravleniya strukturnoi dinamikoi slozhnykh tekhnicheskikh ob’’ektov (Intelligent monitoring and control technology of the structural dynamics of complex technical objects). Moscow: Nauka; 2006. 410 p. (in Russ.). ISBN 5-02-033789-7]

6. Budadin O.N., Kaledin V.O., Kulkov A.A., Pichugin A.N., Nagaitseva N.V. Theoretical and experimental study of thermal control applicability to a 3-D polymer composite structure under uniaxial power loading. Kontrol’. Diagnostika = Testing. Diagnostics. 2014;5(191):72−81 (in Russ.). https://doi.org/10.14489/td.2014.05.pp.072-080

7. Akimov D.A., Rabotkin V.D., Terekhin I.V., Redkin O.K. Knowledge representation in distributed information systems industry. Promyshlennye ASU i kontrollery= Industrial Automatic Control Systems and Controllers. 2013;1:33−38 (in Russ.).]

8. Ostroukh A., Nikonov V., Ivanova I., Sumkin K., Akimov D. Development of the contactless integrated interface of complex production lines. Journal of Artificial Intelligence (JAIR). 2014;7(1):1−12. https://dx.doi.org/10.3923/jai.2014.1.12

9. Akimov D., Krug P., Ostroukh A., Ivchenko V., Morozova T., Sadykov I. The Simulation Model of theAutonomous Truck Caravan in the Extreme and Non-Stationary Environment. Int. J. App. Eng. Res. 2016;11(9):6435−6440.

10. Kulagin V.P., Ivanov A.I., Kuznetsov Y.M., Chulkova G.M. Multidimensional mutual ordering of patterns using a set of pre-trained artificial neural networks. J. Phys.: Conf. Ser. 2017;803(1): Article ID 012083. https://doi.org/10.1088/1742-6596/803/1/012083

11. Kulagin V., Akimov D., Pavelyev S., Potapov D. Automated Identification of Critical Malfunctions of Aircraft Engines Based on Modified Wavelet Transform and Deep Neural Network Clustering. IOP Conf. Ser.: Materials Science and Engineering. 2020;714(1): Article ID 012014. https://doi.org/10.1088/1757-899X/714/1/012014

12. Hashish E., Miller K., Finley W., Kreitzer S. Vibration Diagnostic Challenges: Case Studies in Electric Motor Applications. IEEE Industry Applications Magazine.2017;23(4):22−34. https://doi.org/10.1109/MIAS.2016.2600718

13. Zhou S., Qian S., Chang W., Xiao Y., Cheng Y. A Novel Bearing Multi-Fault Diagnosis Approach Based on Weighted Permutation Entropy and an Improved SVM Ensemble Classifier. Sensors. 2018;18(6):1934. https://doi.org/10.3390/s18061934

14. Arun P., Madhukumar S., Careena P. A Method for the Investigation of Bearing Vibration Based on Spectrogram Image Comparison. IOP Conf. Ser.: Materials Science and Engineering. 2017;396(1): Article ID 012044. https://doi.org/10.1088/1757-899X/396/1/012044

15. Wen L., Gao L., Li X., Wang L., Zhu J. A Jointed Signal Analysis and Convolutional Neural Network Method for Fault Diagnosis. Procedia CIRP. 2018;72:1084−1087. https://doi.org/10.1016/j.procir.2018.03.117

16. Jayakumar K., Thangavel S. Industrial drive fault diagnosis through vibration analysis using wavelet transform. J. Vib. Control. 2017;23(12):2003−2013. https://doi.org/10.1177%2F1077546315606602