Classification of the gas path erosion level of the insulated stage of the axial compressor
Keywords:
axial compressor, erosive wear, numerical simulation, machine learning, technical condition, diagnosticsAbstract
Erosive wear of the parts of the gas path of an axial compressor of a gas turbine is a common reason for premature decommissioning of equipment. The creation of an advanced diagnostic system, which will allow determining the level of blade erosion according to standard parameters without the inspection or disassembly, is topical for Russian gas transmission enterprises. The paper presents preliminary results of applying machine learning methods to solve such a problem for an isolated stage of an axial compressor. The verified results of numerical simulation of the air flow in the stage were used as initial data. The degree of erosion was set as the ratio of the chord of the eroded blade to the chord of the new blade in the peripheral section. The same parameter was the target for machine learning models. Sets of local and integral parameters of the numerical calculation were used as parameters. As a result of the primary study, the random forest model showed the best results when using all available parameters and the parameters with the highest correlation. Conclusions are formulated about the applicability of machine learning methods for creating a model for assessing the degree of erosion. The development of the work is connected with the creation of a model for predicting the technical condition of the flow path of the entire compressor.
Metrics
References
ГОСТ
1. Годовой отчет ПАО «Газпром» за 2020 год [Электронный ресурс]. URL: https://www.gazprom.ru/f/posts/57/982072/gazprom-annual-report-2020-ru.pdf.
2. Burnes D., Kurz R. Performance degradation effects in modern industrial gas turbines // Proceedings of Zurich 2018 Global Power and Propulsion Forum. Том. 124. Zurich: GPPF, 2018. C. 10.
URL: https://gpps.global/wp-content/uploads/2021/01/GPPS-Zurich18-0019.pdf
3. Sallee G.P. Performance deterioration based on existing (historical) data. Cleveland: NASA Lewis Research Center, 1978. 225 с.
URL: https://ntrs.nasa.gov/api/citations/19800013837/downloads/19800013837.pdf
4. Automated Defect Detection and Decision-Support in Gas Turbine Blade Inspection / J. Aust, S. Shankland, D. Pons et al. // Aerospace. 2021. Том. 8, № 2. C. 30.
DOI: 10.3390/aerospace8020030
5. Maragoudakis M., Loukis E. Using Ensemble Random Forests for the extraction and exploitation of knowledge on gas turbine blading faults identification // OR Insight. 2012. Т. 25, № 2. С. 80–104.
DOI: 10.1057/ori.2011.15
6. Tahan M., Muhammad M., Abdul Karim Z.A. A multi-nets ANN model for real-time performance-based automatic fault diagnosis of industrial gas turbine engines // Journal of the Brazilian Society of Mechanical Sciences and Engineering. 2017. Том. 39, № 7. С. 2865–2876.
DOI: 10.1007/s40430-017-0742-8
7. A Novel Methodology for Detecting Foreign Object Damage on Compressor Blading / P. Voigt, M. Voigt, R. Mailach et al. // Turbo Expo: Power for Land, Sea, and Air. Том. 58585. Phoenix: American Society of Mechanical Engineers, 2019. C. V02DT46A005.
DOI: 10.1115/GT2019-90378
8. Water Droplet Erosion Life Prediction Method for Steam Turbine Blade Materials Based on Image Recognition and Machine Learning / Z. Zhang, T. Liu, D. Zhang, Y. Xie // J. Eng. Gas Turbine Power. 2021. Том. 143, № 3. P. 031009.
DOI: 10.1115/1.4049768
9. Predicting the Operability of Damaged Compressors Using Machine Learning / J.V. Taylor, B. Conduit, A. Dickens и др. // Turbo Expo: Power for Land, Sea, and Air. Т. 58554. Phoenix: American Society of Mechanical Engineers, 2019. С. V02AT39A027.
DOI: 10.1115/GT2019-91339
10. Reid L., Moore R.D. Design and overall performance of four highly loaded, high-speed inlet stages for an advanced high-pressure-ratio core compressor // Lewis: Research Center, 1978. 132 с.
URL: https://ntrs.nasa.gov/citations/19780025165
11. Denton J.D. Lessons from rotor 37 // Journal of Thermal Science. 1997. № 6 (1). С. 13.
DOI: 10.1007/s11630-997-0010-9
12. Cumpsty N.A. Some lessons learned // J. Turbomach. 2010. № 132(4). С. 041018.
DOI: 10.1115/1.4001222
13. CFD validation for propulsion system components. AGARD Advisory Report №355 / Ed. J. Dunham. Neuilly-Sur-Siene: AGARD, 1998. 100 с.
URL: https://apps.dtic.mil/sti/citations/ADA349027
14. Scikit-learn: Machine learning in Python / F. Pedregosa, G. Varoquaux, A. Gram-fort et al. // The Journal of machine Learning research. 2011. Т. 12. С. 2825–2830.
URL: https://jmlr.org/papers/volume12/pedregosa11a/pedregosa11a.pdf
15. Cumpsty N.A. Compressor aerodynamics. Harlow: Longman Scientific & Tech-nical, 2004. 509 c.
APA
1. PJSC Gazprom. (2020). Godovoy otchet PAO «Gazprom» za 2020 god [Annual Re-port 2020]. https://www.gazprom.ru/f/posts/57/982072/gazprom-annual-report-2020-ru.pdf
2. Burnes, D. & Kurz, R. (2018). Performance degradation effects in modern industrial gas tur-bines. In Proc. of Zurich 2018 Global Power and Propulsion Forum (p. 10). GPPF. https://gpps.global/wp-content/uploads/2021/01/GPPS-Zurich18-0019.pdf
3. Sallee, G.P. (1978). Performance deterioration based on existing (historical) data. NASA Lewis Research Center. https://ntrs.nasa.gov/citations/19800013837
4. Aust, J., Shankland, S., Pons, D., Mukundan, R., & Mitrovic, A. (2021). Automated Defect De-tection and Decision-Support in Gas Turbine Blade Inspection. Aerospace, 8(2) , 30.
https://doi.org/10.3390/aerospace8020030
5. Maragoudakis, M., & Loukis, E. (2012). Using Ensemble Random Forests for the extraction and exploitation of knowledge on gas turbine blading faults identification. OR Insight, 25(2) , 80-104. https://doi.org/10.1057/ori.2011.15
6. Tahan, M., Muhammad, M., & Abdul Karim, Z. A. (2017). A multi-nets ANN model for real-time performance-based automatic fault diagnosis of industrial gas turbine engines. Journal of the Brazilian Society of Mechanical Sciences and Engineering, 39(7) , 2865-2876.
https://doi.org/10.1007/s40430-017-0742-8
7. Voigt, P., Voigt, M., Mailach, R., Münzinger, D., Abu-Taa, K., & Lange, A. (2019). A Novel Methodology for Detecting Foreign Object Damage on Compressor Blading. In Turbo Expo: Power for Land, Sea, and Air (Vol. 58585, No V02DT46A005). American Society of Mechani-cal Engineers. https://doi.org/10.1115/GT2019-90378
8. Zhang, Z., Liu, T., Zhang, D., & Xie, Y. (2021). Water Droplet Erosion Life Prediction Method for Steam Turbine Blade Materials Based on Image Recognition and Machine Learning. Journal of Engineering for Gas Turbines and Power, 143(3). 031009. https://doi.org/10.1115/1.4049768
9. Taylor, J. V., Conduit, B., Dickens, A., Hall, C., Hillel, M., & Miller, R. J. (2019). Predicting the Operability of Damaged Compressors Using Machine Learning. In Turbo Expo: Power for Land, Sea, and Air (Vol. 58554, No V02AT39A027). American Society of Mechanical Engi-neers.
https://doi.org/10.1115/GT2019-91339
10. Reid, L. & Moore, R. D. (1978). Design and overall performance of four highly loaded, high-speed inlet stages for an advanced high-pressure-ratio core compressor. Lewis Re-search Center. https://ntrs.nasa.gov/citations/19780025165
11. Denton, J. D. (1997). Lessons from rotor 37. Journal of Thermal Science, 6 (1) , p. 13. https://doi.org/10.1007/s11630-997-0010-9
12. Cumpsty, N. A. (2010). Some lessons learned. Journal of Turbomachinery, 132(4) , 041018.
http://dx.doi.org/10.1115/1.4001222
13. Dunham, J. (Ed.). (1998). CFD validation for propulsion system components. AGARD Advisory Report № 355. AGARD. https://apps.dtic.mil/sti/citations/ADA349027
14. Pedregosa F., Varoquaux G., Gramfort A., Michel V., & Thirion, B. (2011). Machine learning in Python. The Journal of Machine Learning Research, 12, 2825-2830.
https://jmlr.org/papers/volume12/pedregosa11a/pedregosa11a.pdf
15. Cumpsty, N. A. (2004). Compressor aerodynamics. Longman Scientific & Tech-nical.
Downloads
Published
How to Cite
Issue
Section
Categories
URN
License
Copyright (c) 2022 V.L. Blinov, G.D. Deryabin, I.S. Zubkov
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
