 |
M. V. Shlyakhov, E. О. Petrenko, V. E. Pyatetsky, N. N. Bakhtadze Digital Predictive Identification Models for Operational Parameter Dynamics of Thermal Power Generation Equipment |
 |
|
Abstract.
The paper presents a method for predicting the health of thermal power plant equipment, such as energy boilers coupled with steam turbines. The models are developed, which indicate the condition of steam superheaters of an energy boiler for a specified control action. Based on realtime prediction, a solution is offered to the problem of boiler efficiency maintenance during design operation as well as repair activities planning over a specified time period.
Keywords:
power generation equipment, prediction methods, identification models, associative search.
DOI 10.14357/20718632250310
EDN QRDNKD
PP. 113-122.
References
1. Electricity generation in the Russian Federation increased by 2.4% in 2024, reaching 1.209 trillion kWh (Rosstat, 2024). Available from: http://energocis.ru/news/vyrabotka_elektroene1739277992/ [Accessed 11 March 2025]. 2. Power generation in Russia – survey. Available from: https://energoseti.ru/articles/energetika-rossii?ysclid=ma14k6nvfs428229681 [Accessed 11 March 2025]. 3. Sumanta Basu, Sushil Cherian, Jisna Johnson. Design of MultiInput Multi-Output Non-linear Model Predictive Control for Main Steam Temperature of Super Critical Boiler. International Journal of Mechanical Engineering and Applications. 2024;12(1):18-31. doi: 10.11648/j.ijmea.20241201.13. 4. P. R. Dolzhanskiy, Specifics of residual life assessment for steam pipeline tubes operating beyond design service life, Central Repair and Mechanical Plant, PJSC Mosenergo. 2005;8:35-39. ISSN: 0040-3636 5. Power characteristics of TGM-96B steam boiler Available from: https://kotel-modul.ru/boiler-equipment/boilers/steam/tgm96?ysclid=m7nkpqc9p6903133846 [Accessed 26 March 2025]. 6. RD 10-577-03 (2003). Standard Instruction for Metal Monitoring and Lifetime Extension of Critical Components of Boilers, Turbines, and Pipelines in Thermal Power Plants. Moscow: State Unitary Enterprise "Scientific and Technical Center for Industrial Safety of the Russian Federal Mining and Industrial Inspectorate". 2003. 128 p. 7. N. N. Bakhtadze, V. A. Lototskiy, E. A. Sakrutina. Identification analysis of non-linear non-stationary objects. In: X International. Proceedings of the 10th International Conference on System Identification and Control Problems (SICPRO), Moscow, Russia, Jan. 26-29, 2015; 2015. 1484 p. 8. MSE criterion in sklearn library Available from: https://scikit-learn.org/stable /modules/generated/sklearn.metrics.mean_squared_error.html [Accessed 6 March 2025]. 9. MAPE criterion in sklearn library Available from: https://scikit-learn.org/stable /modules/generated/ sklearn.metrics.mean_squared_error.html [Accessed 6 March 2025]. 10. R^2criterion in sklearn library Available from: https://scikitlearn.org/stable /modules/generated/ sklearn.metrics.mean_squared_error.html [Accessed 6 March 2025].
|
