The primary goal of a power plant is to ensure a reliable and uninterrupted supply of electrical and thermal energy to consumers. To ensure an operational state, as well as reducing costs associated with repairs or unscheduled shutdowns of equipment, many generating companies use predictive and remote monitoring systems to preemptively resolve up to 90% of anomalies. In order to increase the efficiency of such systems, developments are underway to automate the recognition of equipment anomalies. Solving this problem will significantly streamline the work of specialist technicians by automatically generating notifications about detected anomalies and providing recommendations on their elimination. The article analyzes the use of big data in the power industry to monitor the technical condition of power equipment. The basic operation principles of the “ROTEÑ” company’s PRANA software-hardware complex for prognostics and remote monitoring are considered in terms of the need to classify anomalies. Typical problems and their possible solution given a lack of data on the equipment operation during classifier creation are described. In addition, various approaches to the creation of an anomaly classifier based on power equipment operation data collected from several companies are compared. The approach of the PRANA complex in solving this problem is described in more detail. The article lists the various types of anomalies and characteristics of common operating models used for the same type of equipment. The main approaches to the analysis of operation data accumulated by power equipment are also described: the analysis of sequences and their changes, the use of a priori information. The study led to the creation of a classifier for simple anomalies based on the data obtained from a GTE-160 unit.
Similar content being viewed by others
References
M. A. Lipatov, “First complex of predictive analytics for power equipment in Russia”, Ékspositsiya, Neft’. Gas, No. 3(49), 82 – 83 (2016).
C. Lynch, “Big data: how do your data grow?” Nature, 455(7209), 28 – 29 (2008).
S. A. Naumov, A. V. Krymsky, M. A. Lipatov, and D. N. Skrabatun, “Experience of using remote access and predictive analytics of the state of power equipment,” Teploénergetika, No. 4, 21 – 33 (2018).
US Pat. 9250625(B2), J. P. Herzog.
US Pat. 2017236064(A1), A. G. Cassantec.
US Pat. 2017236065(A1), A. G. Cassantec.
J. D. Williams, W. H. Woodlan, J. B. Birch, and J. H. Sullivan, “On the distribution of hotelling’s t2 statistic based on the successive differences covariance matrix estimator,” J. Qual. Technol., 38(3), 217 – 229 (2006).
M. Basseville, A. Benveniste, et al., Detection of Abrupt Changes in Signals and Dynamical Systems [Russian translation], Moscow, Mir (1980).
Author information
Authors and Affiliations
Corresponding author
Additional information
Translated from Élektricheskie Stantsii, No. 1, January 2022, pp. 49 – 56. https://doi.org/10.34831/EP.2022.1086.1.006
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Nemirovich-Skrabatun, D.N., Persyaev, A.A. Experience in Creating a System for Automatic Anomaly Recognition in Power Equipment Operation. Power Technol Eng 56, 254–260 (2022). https://doi.org/10.1007/s10749-023-01503-1
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10749-023-01503-1