Method of gas turbine malfunction diagnostics using hybrid intellectual systems

Abstract


Methods of improving the safety and efficiency of gas turbines are analyzed. The existing diagnostic methodologies and software for compression stations are reviewed. Lists of significant diagnostics parameters, typical faults and their causes are compiled. A model of a hybrid intellectual system of gas turbine fault diagnosis based on artificial neural network and fuzzy inference is introduced. The fuzzy inference method which allows processing an arbitrary number of intermediate variables and transitive relations is described. Moreover, the method makes it possible to take into account the inaccuracies in expert knowledge not only in describing the facts of an application domain but also in cause-and-effect relations between them. The implementation of the proposed model and the method in the system of taking decisions that makes it possible to reveal both the presence and character of the faults and their possible causes is described. The proposed system makes it possible to improve the accuracy and completeness of gas turbine diagnostics, which, in its turn, will increase the labor safety for the compression station staff as well as the promptness of repair and maintenance. Thus, the application of the system may have a positive effect on the service life and economic feasibility of gas turbines.


About the authors

P. G. Antropov

Yury Gagarin State Technical University of Saratov

Author for correspondence.
Email: apg.sstu@yandex.ru

Russian Federation

Candidate of Science (Engineering), Associate Professor

Dean of the Power Engineering Faculty, Head of the Department of Heat and Power Engineering

O. N. Dolinina

Yury Gagarin State Technical University of Saratov

Email: olga@sstu.ru

Russian Federation

Candidate of Science (Engineering), Associate Professor

Dean of International Faculty of Applied Information Technologies

A. Y. Shvarts

Yury Gagarin State Technical University of Saratov

Email: shvartsaleksandr@gmail.com

Russian Federation

Postgraduate student of the Applied Information Technologies Department

References

  1. Grachev V.A., Zaritsky S.P., Detkov A.Yu., Mokrousov S.N. Predictive maintenance of pipe fittings at OJSC "Gazprom" subsidiaries // Bezopasnost' truda v promyshlennosti, 2006. No. 12, P. 54-59. (In Russ.)
  2. Kokorev E.N., Ivanov A.P., Serebryansky A.Ya., Ivanov V.A. Program system for modeling the operation mode of gas networks in cities and localities // Bezopasnost' truda v promyshlennosti. 2001. No. 4. P. 34-35. (In Russ.)
  3. Ostreykovsky V.A., Silin Ya.V. Application of catastrophe theory methods to the assessment of oilfield pipeline reliability // Automatization, telemechanization and telecommunication in oil industry. 2011. No. 11. P. 29-33. (In Russ.)
  4. Larin E.A. Probabilistic model of calculating reliability parameters for district heating steam-gas units in heat and power supply systems // Izvestiya vysshikh uchebnykh zavedeniy. Problemy energetiki. 2010. No. 9-10. P. 111-122. (In Russ.)
  5. Semenov A.A. Kompleksnyy analiz rabotosposobnosti gazoperekachivayushchikh agregatov na osnove prognoza ostatochnogo resursa. Diss. kand. tekhn. nauk [Complex analysis of gas turbine performance based on residual service life estimation: PhD thesis]. Moscow, 2004. 134 p.
  6. Strebkov A., Basmanov M., Menshikov S., Morozov I. Gas turbine parametric diagnostics system: modern approach // Business Russia: industry, transport, social life. 2011. No. 7. P. 42-43. (In Russ.)
  7. Dolinina O.N., Karimov R.N. Methods of processing multi-dimensional data from numeric and non-numeric objects // Vestnik of Samara St. Tech. Univ. 2006. No. 2(12). P. 100-110. (In Russ.)
  8. Safonov V.S., Leontiev E.V., Schurovsky V.A. Standards for technological design of main gas pipelines. OJSC «Gazprom», 2005. (In Russ.)
  9. Antropov P.G., Zamotorin V.N., Zakharov V.N. et al. Manual for training and retraining of workers and specialists at gas compressor station. YugTransgaz, Petrovsk, 2000. 145 p. (In Russ.)

Statistics

Views

Abstract - 55

PDF (Russian) - 28

Article Metrics

Metrics Loading ...

PlumX

Dimensions

Refbacks

  • There are currently no refbacks.

Copyright (c) 2015 VESTNIK of the Samara State Aerospace University

This website uses cookies

You consent to our cookies if you continue to use our website.

About Cookies