Investigation of intelligent classification of current technical condition of the gas turbine engine

Authors

DOI:

https://doi.org/10.15587/2312-8372.2015.38073

Keywords:

gas turbine engine, intelligent system, control reconfiguration, diagnostic system, technical condition

Abstract

The structure of diagnosing the technical condition of the gas turbine engine (GTE) is given. It is proposed a method of training the intellectual automated system of diagnostics and control reconfiguration (IASDCR) by GTE modes based on integration of fuzzy logic and neural networks. The theoretical and experimental capabilities of IASDCR classification of current condition of GTE in specific operational situations are proposed. It is designed and synthesized the structure of IASDCR GTE, based on the proposed model. The method provides the ability to customize such systems for the diagnosis and management of different types of GTE reconfiguration during their operation, thereby increasing the reliability of classification and prediction of residual life, and prevents the transition of emergency situation in catastrophic situation. The expediency of using hybrid IASDCR based on radial basis networks and fuzzy logic theory, which allowed to classify the vibrational state GTE DR-59L with a probability of 0,96 and GTE DT-71P with a probability of 0,92.

Author Biography

Микола Петрович Кравчук, National Aviation University, Komarova Ave, 1, Kyiv, Ukraine, 03058

Candidate of Technical Sciences, Assistant

Department of Automation and Energy Management 

References

  1. Epifanov, S. V., Loboda, I. I. (2004). Identifikatsiia staticheskoi i dinamicheskoi modelei protochnoi chasti kak sredstvo diagnostirovaniia GTD. Vestnik dvigatelestroeniia, № 2, 206–212.
  2. Gasidzhak, V. S., Kazak, V. N., Bel'skaia, A. A. (2008). Kombinirovannaia strategiia tehnicheskogo obsluzhivaniia GPA po narabotke s prognozirovaniem predotkaznogo sostoianiia. Materialy mizhnarodnoi konferentsii «ISDMCI’2008», (Yevpatorіia, 19-23 travnia 2008), T. 2, 100-103.
  3. Dmitriev, S. A. (1996). Diagnostirovanie protochnoi chasti GTD na ustanovivshihsia i neustanovivshihsia rezhimah raboty. K.: KMUGA, 358.
  4. Boguslaev, A. V., Dubrovin, V. I., Subbotin, S. A. (2004). Metody neiterativnogo sinteza mnogosloinyh neironnyh setei v zadachah diagnostiki aviadvigatelei. Vestnik dvigatelestroeniia, № 1, 86-93.
  5. Boguslaev, A. V., Dubrovin, V. I., Subbotin, S. A., Yatsenko, V. K. (2002). Diagnostika lopatok aviadvigatelei na osnove mnogosloinoi logicheski prozrachnoi neironnoi seti. Vestnik dvigatelestroeniia, № 1, 85-90.
  6. Yam, R. C. M., Tse, P. W., Li, L., Tu, P. (2001, February 1). Intelligent Predictive Decision Support System for Condition-Based Maintenance. The International Journal of Advanced Manufacturing Technology, Vol. 17, № 5, 383–391. doi:10.1007/s001700170173
  7. Sirotin, N. N., Korovkin, Yu. M. (1979). Tehnicheskaia diagnostika aviatsionnyh gazoturbinnyh dvigatelei. M.: Mashinostroenie, 272.
  8. Dubrovin, V. I., Subbotin, S. A., Boguslaev, A. V., Yatsenko, V. K. (2003). Intellektual'nye sredstva diagnostirovaniia i prognozirovaniia nadezhnosti aviadvigatelei. Zaporozhye: OAO «Motor–Sіch», 279.
  9. Hasydzhak, V. S., Kazak, V. M. (2007). Baiiesovskyi alhorytm rozpiznavannia peredvidmovnykh staniv hazoperekachuvalnykh ahrehativ. Visnyk tsentralnoho naukovoho tsentru TAU, Vol. 10, 77-78.
  10. Bodianskii, E. V., Rudenko, O. G. (2004). Iskusstvennye neironnye seti: arhitektura, obuchenie, primenenie. Kharkov: TELETEH, 372.

Published

2015-01-29

How to Cite

Кравчук, М. П. (2015). Investigation of intelligent classification of current technical condition of the gas turbine engine. Technology Audit and Production Reserves, 1(3(21), 53–57. https://doi.org/10.15587/2312-8372.2015.38073