An improved compact propulsion system model based on batch normalize deep neural network
-
Juan Fang
,
Haibo Zhang
Abstract
Aero-engine on-board steady state model is an important part of many advanced engine control algorithms. In order to build a high accuracy and real-time steady-state onboard model in a large envelope, an ICPSM (improved compact propulsion system model) based on batch normalize neural network is proposed in this paper. Compared with piecewise linearization model and support vector machine model, conventional CPSM which is mainly composed of baseline model and nonlinear sub model has the advantages of high real-time performance and small data storage. However, as the similarity conversion error increases with the distance from the design point, the cumulative error of the conventional baseline model also increases, which makes the model unable to maintain high accuracy in the full envelope. Thus, a high accuracy baseline model in full envelope based on batch normalize neural network is proposed in this paper. The simulation result shows that compared with the conventional compact propulsion system model, the percentage error of parameters of the improved compact propulsion system model based on the batch neural network is reduced by two times, the single step operation time is reduced by 18%, and the data storage of the onboard model is reduced as well.
Funding source: National Natural Science Foundation of China
Award Identifier / Grant number: 51906102
Funding source: National Science and Technology Major Project
Award Identifier / Grant number: 2017-V-0004-0054
Funding source: Research on the Basic Problem of Intelligent Aero-engine
Award Identifier / Grant number: 2017-JCJQ-ZD-047-21
Funding source: Fundamental Research Funds for the Central Universities
Award Identifier / Grant number: NZ2020002
-
Author contributions: All the authors have accepted responsibility for the entire content of this submitted manuscript and approved submission.
-
Research funding: This study was supported in part by National Natural Science Foundation of China under Grant 51906102, in part by National Science and Technology Major Project under Grant 2017-V-0004-0054, in part by Research on the Basic Problem of Intelligent Aero-engine under Grant 2017-JCJQ-ZD-047-21, in part by the Fundamental Research Funds for the Central Universities under Grant NZ2020002.
-
Conflict of interest statement: The authors declare no conflicts of interest regarding this article.
References
1. Sun Jianguo, VV, Ilyasov, B. Advanced multivariable control system of aeroengines. Beijing: Beijing University of Aeronautics and Astronautics Press; 2005.Search in Google Scholar
2. Jianguo, S. Prospects of the aeroengine control development in the early time of the 21st century. J Aero Power 2001;16:97–102.10.1093/ndt/16.suppl_6.97Search in Google Scholar PubMed
3. Orme, JS, Gilyard, GB. Preliminary supersonic flight test evaluation of performance seeking control. In: AIAA-93-1821. Monterey, CA, USA: AIAA; 1993. https://doi.org/10.2514/6.1993-1821.Search in Google Scholar
4. Chisholm, J. In-flight optimization of the total propulsion system. In: AIAA/SAE/ASME/ASEE 28th joint propulsion conference and exhibit. Nashville, TN; 1992. https://doi.org/10.2514/6.1992-3744.Search in Google Scholar
5. Nobbs, S, Jacobs, S, Donahue, D. Development of the full-envelope performance seeking control algorithm. In: Joint propulsion conference & exhibit, Nashville, TN, USA; 1992. https://doi.org/10.2514/6.1992-3748.Search in Google Scholar
6. Stewart, JF. Integrated flight propulsion control research result using the NASA F-15 HIDEC flight research facility. In: AIAA-92-4106. Edwards, CA, USA: AIAA Journal; 1992. https://doi.org/10.2514/6.1992-4106.Search in Google Scholar
7. Gilyard, GB, Orme, JS. Subsonic flight test evaluation of a performance seeking control algorithm on an F-15 airplane. In: NASA technical memorandum 4400. US: NASA; 1992. https://doi.org/10.2514/6.1992-3743.Search in Google Scholar
8. Orme, JS, Conners, TR. Supersonic flight test result of a performance seeking control algorithm on a NASA F-15 aircraft. In: 30th AIAA/ASME/SAE/ASEE joint propulsion conference: California: Edwards; 1994. https://doi.org/10.2514/6.1994-3210.Search in Google Scholar
9. Siqi, F. Aircraft engine control. Xi’an: Northwest University of Technology Press; 2008.Search in Google Scholar
10. Zhang, SG, Guo, YQ, Lu, J. Research on aircraft engine component-level models based on GasTurb/MATLAB. J Aerosp Power 2012;27:2850–6.Search in Google Scholar
11. Lichtsinder, M, Levy, Y. Jet engine model for control and real-time simulations. J Eng Gas Turbines Power 2006;128:745–53.10.1115/1.1915391Search in Google Scholar
12. Reed, JA, Afjeh, AA. Computational simulation of gas turbines: part 1—foundations of component-based models. J Eng Gas Turbines Power 2000;122:V001T01A009. https://doi.org/10.1115/1.1287490.Search in Google Scholar
13. Bolender, MA, Doman, DB. Non-linear control allocation using piecewise linear functions. In: AIAA guidance, navigation, and control conference and exhibit. Elsevier B.V.; 2003. https://doi.org/10.1109/med.2006.328751.Search in Google Scholar
14. Kevenaar, TAM, Leenaerts, DMW. A comparison of piecewise-linear model descriptions. IEEE Trans Circ Syst I: Fund Theor Appl 1992;39:996–1004. https://doi.org/10.1109/81.207720.Search in Google Scholar
15. Li, JW, Guo, YQ, Yuan, XC. Turbofan engine modeling of piecewise linear model. Comput Simulat 2007;24:37–40.Search in Google Scholar
16. Crowther, WJ, Edge, KA, Burrows, CR, Atkinson, RM, Woollons, DJ. Fault diagnosis of a hydraulic actuator circuit using neural networks—an output vector space classification approach. Proc Inst Mech Eng, Part I: J Syst Contr Eng 2005;212:57–68.10.1243/0959651981539299Search in Google Scholar
17. Carneiro, JF, Almeida, FGD. Pneumatic servo valve models based on artificial neural networks. Proc IME J Syst Contr Eng 2011;225:393–411.10.1177/2041304110394498Search in Google Scholar
18. Xu Liang, HJ. Dynamic identification of aeroengine BP network model suitable for all envelope. J Nanjing Univ Aeronaut Astronaut 2001;4:32–5.Search in Google Scholar
19. Haykin, S. Neural networks – a comprehensive foundation. Amsterdam: Neurocomputing; 1994.Search in Google Scholar
20. Hao, X, Zhang, G, Ma, S. Deep learning. Int J Semantic Comput (IJSC) 2016;10:417–39. https://doi.org/10.1142/s1793351x16500045.Search in Google Scholar
21. Drucker, H, Burges, CJ, Kaufman, L, Smola, A, Vapnik, V. Support vector regression machines, 7th ed. Advances in Neural Information Processing Systems; 1997, vol 28:779–84 pp.Search in Google Scholar
22. Gérard Bloch, L, F, Colin, G, Chamaillard, Y. Support vector regression from simulation data and few experimental samples. Inf Sci 2008;178:3813–27. https://doi.org/10.1016/j.ins.2008.05.016.Search in Google Scholar
23. Yu, XK, Li, YH, Wang, J, Zhang, Pu, Lu, J. A novel aero-engine identification model based on support vector machines. J Aero Power 2004;19:684–8.Search in Google Scholar
24. Luh, GC, Wu, CY. Non-linear system identification using genetic algorithms. Proc IME J Syst Contr Eng 1999;213:105–18. https://doi.org/10.1243/0959651991540421.Search in Google Scholar
25. Gilyard, GB, Orme, JS. Performance seeking control: program overview and future directions. In: AIAA-93-3765-CP. Edwards, California: Dryden Flight Research Facility; 1993. https://doi.org/10.2514/6.1993-3765.Search in Google Scholar
26. Yi, S. Aviation gas turbine engine. Bei Jing: Aviation Industry Press; 1995.Search in Google Scholar
27. Zheng, Q, Fang, J, Hu, Z, Zhang, H. Aero-engine on-board model based on batch normalize deep neural network. IEEE Access 2019;7:54855–62.10.1109/ACCESS.2018.2885199Search in Google Scholar
28. Zhang, S, Choromanska, A, Lecun, Y. Deep learning with elastic averaging SGD. MIT Press; 2014.Search in Google Scholar
29. Liu Yingchao, ZJ. Gradient descent method. J Nanjing Univ Sci Technol (Nat Sci): Soc Sci 1993:12–6.Search in Google Scholar
© 2021 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Natural frequency analysis of a functionally graded rotor-bearing system with a slant crack subjected to thermal gradients
- Evaluation of exit pattern factors of an annular aero gas turbine combustor at altitude off-design conditions
- Research on quasi-one-dimensional modeling and performance analysis of RBCC propulsion system
- Performance characteristics of flow in annular diffuser using CFD
- Control-oriented quasi-one dimensional modeling method for scramjet
- Effect of rotor–stator rim cavity flow on the turbine
- An improved aerodynamic performance optimization method of 3-D low Reynolds number rotor blade
- Hot gas ingestion in chute rim seal clearance of gas turbine
- An improved compact propulsion system model based on batch normalize deep neural network
- Study of the vortex chamber and its application for the development of novel measurement and control devices
- Effect of equivalence ratio on the detonation noise characteristics of pulse detonation engine
- Simulation and analysis of hot plume infrared signature based on SNB model
Articles in the same Issue
- Frontmatter
- Natural frequency analysis of a functionally graded rotor-bearing system with a slant crack subjected to thermal gradients
- Evaluation of exit pattern factors of an annular aero gas turbine combustor at altitude off-design conditions
- Research on quasi-one-dimensional modeling and performance analysis of RBCC propulsion system
- Performance characteristics of flow in annular diffuser using CFD
- Control-oriented quasi-one dimensional modeling method for scramjet
- Effect of rotor–stator rim cavity flow on the turbine
- An improved aerodynamic performance optimization method of 3-D low Reynolds number rotor blade
- Hot gas ingestion in chute rim seal clearance of gas turbine
- An improved compact propulsion system model based on batch normalize deep neural network
- Study of the vortex chamber and its application for the development of novel measurement and control devices
- Effect of equivalence ratio on the detonation noise characteristics of pulse detonation engine
- Simulation and analysis of hot plume infrared signature based on SNB model
