Predicting compressor mass flow rate using various machine learning approaches
-
Isil Yazar
,
Yildiray Anagun
Abstract
A major focus of the present study is to construct high-fidelity models for predicting corrected mass flow rates based on the collected compressor map data. Both traditional machine learning research and modern deep learning techniques have been employed to obtain well-fitted regression models of compressor mass flow rate. As traditional machine learning methods, Multiple Linear Regression and Random Forest, are conducted on compressor maps for prediction of corrected mass flow rate. The time series-based deep learning models are able to capture the overall trend of a given input for specific map data. Therefore, a time series-based deep learning technique, namely Gated Recurrent Unit has been employed to improve regression results. Besides, the prediction capabilities of the models, results also show that the proposed models can be used for the development of dynamic aero-thermal mathematical models of gas turbine engines and mass flow rate models created for dynamic compressors in other disciplines.
Funding source: Eskisehir Osmangazi University fund of scientific research project No. FCD-2023-2882.
-
Research ethics: Not applicable.
-
Author contributions: The authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: The authors state no conflict of interest.
-
Research funding: This study was supported from Eskisehir Osmangazi University fund of scientific research project No. FCD-2023-2882.
-
Data availability: Not applicable.
References
1. Wensveen, JG. Air transportation: a management perspective, 7th ed. New York, USA: Routledge; 2018.10.4324/9781351163200Search in Google Scholar
2. Şöhret, Y, Ekici, S, Dinc, A. Investigating the green performance limits of a cargo aircraft engine during flight: a thermo-environmental evaluation. Energy Sources, Part A Recovery, Util Environ Eff 2021:1–16. https://doi.org/10.1080/15567036.2021.2017513.Search in Google Scholar
3. Alkaabi, KA, Debbage, KG. The geography of air freight: connections to U.S. metropolitan economies. J Transp Geogr 2011;19:1517–29. https://doi.org/10.1016/j.jtrangeo.2011.04.Search in Google Scholar
4. Goetz, AR, Budd, L. The geographies of air transport. Transport and mobility series. Farnham: Ashgate; 2014.Search in Google Scholar
5. Lordan, O, Sallan, JM, Simo, P, Gonzalez-Prieto, D. Robustness of the air transport network. Transp Res Part E Logist Transp Rev 2014;68:155–63. https://doi.org/10.1016/j.tre.2014.05.011.Search in Google Scholar
6. Dinc, A, Caliskan, H, Ekici, S, Sohret, Y. Thermodynamic-based environmental and enviroeconomic assessments of a turboprop engine used for freight aircrafts under different flight phases. J Therm Anal Calorim 2022;147:12693–707. https://doi.org/10.1007/s10973-022-11486-2.Search in Google Scholar
7. Tsoutsanis, E, Meskin, N, Benammar, M, Khorasani, K. A component map tuning method for performance prediction and diagnostics of gas turbine compressors. Appl Energy 2014;135:572–85. https://doi.org/10.1016/j.apenergy.2014.08.115.Search in Google Scholar
8. Shuang, S, Ze-peng, W, Xiao-peng, S, Hong-li, Z, Zhi-ping, W. An adaptive compressor characteristic map method based on the Bézier curve. Case Stud Therm Eng 2021;28:101512. https://doi.org/10.1016/j.csite.2021.101512.Search in Google Scholar
9. Kurzke, J, Riegler, C. A new compressor map scaling procedure for preliminary conceptional design of gasturbines:2000-GT-0006. New York: American Society of Mechanical Engineers; 2000.10.1115/2000-GT-0006Search in Google Scholar
10. Yazar, I, Yavuz, HS, Altın Yavuz, A. Comparison of various regression models for predicting compressor and turbine performance parameters. Energy 2017;140:1398–406, https://doi.org/10.1016/j.energy.2017.05.061.Search in Google Scholar
11. Yazar, I, Kiyak, E, Yavuz, HS. Modelling and comparison of compressor performance parameters by using ANFIS. AMR (Adv Magn Reson) 2014;1016:710–5. https://doi.org/10.4028/www.scientific.net/amr.1016.710.Search in Google Scholar
12. Yang, B, Fang, X, Zhang, L, Zhuang, F, Bi, M, Chen, C, et al.. Applicability of empirical models of isentropic efficiency and mass flow rate of dynamic compressors to jet engines. Prog Aero Sci 2019;106:32–42. https://doi.org/10.1016/j.paerosci.2019.01.007.Search in Google Scholar
13. Holmberg, H. Towards automatic and systematic compressor model selection based on measurement data [Internet] [dissertation]; 2021. Available from: http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-178104.Search in Google Scholar
14. Pakatchian, MR, Ziamolki, A, Alhuyi Nazari, M. Applications of machine learning approaches in aerodynamic aspects of axial flow compressors: a review. Front Energy Res 2023;11. https://doi.org/10.3389/fenrg.2023.1135055.Search in Google Scholar
15. Fei, J, Zhao, N, Shi, Y, Feng, Y, Wang, Z. Compressor performance prediction using a novel feed-forward neural network based on Gaussian kernel function. Adv Mech Eng 2016;8:168781401662839. https://doi.org/10.1177/1687814016628396.Search in Google Scholar
16. Sohail, MU, Hamdani, HR, Islam, A, Parvez, K, Khan, AM, Allauddin, U, et al.. Prediction of non-uniform distorted flows, effects on transonic compressor using CFD, regression analysis and artificial neural networks. Appl Sci 2021;11:3706. https://doi.org/10.3390/app11083706.Search in Google Scholar
17. Gholamrezaei, M, Ghorbanian, K. Compressor map generation using a feed-forward neural network and rig data. Proc Inst Mech Eng A 2010;224:97–108. https://doi.org/10.1243/09576509JPE792.Search in Google Scholar
18. Ghorbanian, K, Gholamrezaei, M. An artificial neural network approach to compressor performance prediction. Appl Energy 2009;86:1210–21. https://doi.org/10.1016/j.apenergy.2008.06.006.Search in Google Scholar
19. Ghorbanian, K, Gholamrezaei, M. Axial compressor performance map prediction using artificial neural network. In: Proc. ASME turbo expo (American Society of Mechanical Engineers Digital Collection), PART B; 2007, Vol. 6:1199–208 pp.10.1115/GT2007-27165Search in Google Scholar
20. Gholamrezaei, M, Ghorbanian, K. Application of integrated fuzzy logic and neural networks to the performance prediction of axial compressors. Proc Inst Mech Eng Part A J. Power Energy 2015;229:928–47. https://doi.org/10.1177/0957650915596877.Search in Google Scholar
21. Yazar, I, Kiyak, E, Yavuz, HS. Modeling and comparison of compressor performance parameters by using ANFIS. Adv Mater Res 2014;1016:710–15. https://doi.org/10.4028/www.scientific.net/AMR.1016.710.Search in Google Scholar
22. Tsoutsanis, E, Meskin, N, Benammar, M, Khorasani, K. A component map tuning method for performance prediction and diagnostics of gas turbine compressors. Appl Energy 2014;135:572–85. https://doi.org/10.1016/j.apenergy.2014.08.115.Search in Google Scholar
23. Spack, J. Linear parameter varying controller for a small turboshaft engine [MSc thesis]. Boston, Massachusetts: Electrical Engineering Dept., Northeastern University; 2011.Search in Google Scholar
24. Burlamaqui Filho, FAC, Goes, LCS, Oliveira, ABV, Bosa, RW, Fernandes, GS. Dynamic modelling nonlinear and control system for a turboshaft. In: 12th Pan-American Congress of Applied Mechanics. Port of Spain, Trinidad; 2012.Search in Google Scholar
25. Yarlagadda, S. Performance analysis of J85 turbojet engine matching thrust with reduced inlet pressure to the compressor [MSc thesis]. Boston, Massachusetts: Mechanical Dept., Graduate Faculty of University of Toledo; 2010.Search in Google Scholar
26. Ballin, MG. A high-fidelity real-time simulation of a small turboshaft engine. NASA-TM-100991; 1988.Search in Google Scholar
27. Plis, M, Rusinowski, H Mathematical modeling of an axial compressor in a gas turbine cycle. J Power Technol 2016;96:194–99.Search in Google Scholar
28. https://plotdigitizer.com/ [Accessed 5 May 2023].Search in Google Scholar
© 2024 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Computational analysis of the scramjet mode of the RBCC inlet using micro vortex generators
- Predicting compressor mass flow rate using various machine learning approaches
- Performance analysis of a gas turbine engine with intercooling and regeneration process - Part 1
- Performance analysis of pulse detonation ramjet
- Investigation on flow characteristics and its effect on heat transfer enhancement in a wedge channel with combination of circular, oblong, teardrop, and pencil pin fins
- Effect of perforated wall in controlling the separation due to SWBLI at Mach no. 5 to 9
- Research on performance seeking control of turbofan engine in minimum hot spot temperature mode
- Experimental study on flow field and combustion characteristics of V-gutter and integrated flameholders
- Probabilistic analysis of blade flutter based on particle swarm optimization-deep extremum neural network
- Numerical and experimental study on the critical geometric variation based on sensitivity analysis on a compressor rotor
- Aero-engine direct thrust control based on nonlinear model predictive control with composite predictive model
- Simple model of turbine-based combined cycle propulsion system and smooth mode transition
- Effect of inlet diameter on the flow structure and performance for aluminum-based water-jet engine
- Multi-objective optimization of the aerodynamic performance of butterfly-shaped film cooling holes in rocket thrust chamber
- Application of KH-RT model in lifting flame of methanol jet atomization
- Study of vortex throttle characteristics with adjustable resistance by rotation of the vortex chamber inlet channel
- Enhancing transonic compressor rotor efficiency by flow analysis-driven blade section modification
- Performance analysis of a planar shaped strut injector based supersonic combustion chamber
- The study of cascading effect in the integration of intake with gas turbine engine bay in subsonic cruise vehicle
Articles in the same Issue
- Frontmatter
- Computational analysis of the scramjet mode of the RBCC inlet using micro vortex generators
- Predicting compressor mass flow rate using various machine learning approaches
- Performance analysis of a gas turbine engine with intercooling and regeneration process - Part 1
- Performance analysis of pulse detonation ramjet
- Investigation on flow characteristics and its effect on heat transfer enhancement in a wedge channel with combination of circular, oblong, teardrop, and pencil pin fins
- Effect of perforated wall in controlling the separation due to SWBLI at Mach no. 5 to 9
- Research on performance seeking control of turbofan engine in minimum hot spot temperature mode
- Experimental study on flow field and combustion characteristics of V-gutter and integrated flameholders
- Probabilistic analysis of blade flutter based on particle swarm optimization-deep extremum neural network
- Numerical and experimental study on the critical geometric variation based on sensitivity analysis on a compressor rotor
- Aero-engine direct thrust control based on nonlinear model predictive control with composite predictive model
- Simple model of turbine-based combined cycle propulsion system and smooth mode transition
- Effect of inlet diameter on the flow structure and performance for aluminum-based water-jet engine
- Multi-objective optimization of the aerodynamic performance of butterfly-shaped film cooling holes in rocket thrust chamber
- Application of KH-RT model in lifting flame of methanol jet atomization
- Study of vortex throttle characteristics with adjustable resistance by rotation of the vortex chamber inlet channel
- Enhancing transonic compressor rotor efficiency by flow analysis-driven blade section modification
- Performance analysis of a planar shaped strut injector based supersonic combustion chamber
- The study of cascading effect in the integration of intake with gas turbine engine bay in subsonic cruise vehicle
