Testing of the equipment monitoring system based on acoustic noise diagnostics using neural networks
UDC: 681.5
DOI: 10.33285/2782-604X-2022-6(587)-32-40
Authors:
TORINA ELENA M.
1,
KISELEV ALEXANDER V.2,
FORRAT NIKOLAI A.3,
MIKHAILOV DMITRY M.4,
DVORYANKIN SERGEI V.5
1 National Research University "MPEI", Moscow, Russia
2 ZETA, Cheboksary, Russia
3 I-EXP, Moscow, Russia
4 China Branch of BRICS Institute for the Study of Future Networks, Shenzhen, China
5 National University of Oil and Gas "Gubkin University", Moscow, Russia
Keywords: equipment condition monitoring, equipment repair and down time, acoustic noise diagnostics, neural networks
Annotation:
In the processes that require minimization of equipment repair and down time, constant monitoring of the equipment state is required to timely detect deviations from normal operation. Promising and cost-effective for these purposes are the systems for equipment automatic monitoring based on acoustic noise diagnostics. However, there are many variables in the noise pattern that can warn about the occurrence of an anomalous regime. Analyzing such a volume of data by a man is a complex and time-consuming task. The article proposes a method for analyzing the acoustic noise pattern of the operating equipment based on two neural networks that allow quickly processing a large amount of data. The system developed on the basis of this method was successfully tested when operating a power boiler at a thermal power plant. The test results and prospects for further development of the project are also presented in the article.
Bibliography:
1. Karel J., Monhart F. Noise measurement diagnostics for large electric machines // INTER-NOISE and NOISE-CON Congress and Conference Proceedings. – Institute of Noise Control Engineering, 2019. – T. 259, No. 9. – P. 840–849.
2. Terekhov A.L., Mayants Yu.A., Pishchukhin V.M. Metodologicheskie osnovy shumovoy diagnostiki tekhnologicheskogo oborudovaniya neftegazovoy otrasli // Gazovaya prom-st'. – 2020. – № 5(800). – S. 92–99.
3. Matyushkova O.Yu., Tetter V.Yu. Sovremennye metody vibroakusticheskogo diagnostirovaniya // Omskiy nauch. vestn. – 2013. – № 3(123) – S. 294–299.
4. Mitrofanov S.V., Stashkevich A.S. Vibrodiagnostika energe-ticheskogo oborudovaniya. Perspektivy razvitiya i optimizatsiya vibrodiagnosticheskikh tekhnologiy // Universitetskiy kompleks kak regional'nyy tsentr obrazovaniya, nauki i kul'tury: materialy Vseros. nauch.-metod. konf. (s mezhdunar. uchastiem), Orenburg, 30 yanv. – 01 fevr. – Izd.-poligraf. kompleks "Universitet", 2013. – S. 301–304.
5. Dong Yul Oh, Il Dong Yun. Residual Error Based Anomaly Detection Using Auto-Encoder in SMD Machine Sound // Sensors. – 2018. – Vol. 18, Issue 5. – DOI: 10.3390/s18051308
Back to issue