Direct Thrust Inverse Control of Aero-Engine Based on Deep Neural Network
-
Qiangang Zheng
,
Ziyan Du
Abstract
A novel thrust control method based on inverse control is proposed to improve engine response ability. The On Line Sliding Window Deep Neural Network (OL SW DNN) is proposed and adopted as inverse mapping model modeling method of inverse control. The OL SW DNN has deeper layer structure, which makes the inverse mapping model have stronger fitting capacity for nonlinear object than traditional NN. Moreover, due to adopt on-line learning modeling method, the proposed adaptive control method can obtain desired thrust whether engine degrades or not. The comparison simulations of the traditional control method based on PID and the proposed control method are carried out. Compared with the traditional control method, the proposed control method can obtain desired thrust when the engine degradation occurs, but also has fast response ability (the acceleration times for engine thrust increase to 95 % thrust of acceleration object decreases by 1.35 seconds).
Funding statement: This was supported in part by the National Natural Science Foundation of China under Grant 51576096, in part by Q. Lan and the 333 Project, in part by the Research Funds for Central Universities under Grant NF2018003, in part by Six Talents Peak Project of Jiangsu Province.
Nomenclature
- Symbol
-
Explanation
- H
-
Height
- Ma
-
Mach number
- PLA
-
Power level angle
- Wfb
-
Fuel flow
- F
-
Engine thrust
- T41
-
High pressure turbine inlet temperature
- Nf
-
Fan rotor speed
- Nc
-
Compressor rotor speed
- Smf
-
Fan surge margin
- Smc
-
Compressor surge marge
- Ps3
-
Combustor inlet pressure
- RU
-
Ratio Unit (Wfb /Ps3 )
References
1. Jaw L C, Mattingly JD. Aircraft engine controls: design, system analysis, and health monitoring. American Institute of Aeronautics and Astronautics, 2009.10.2514/4.867057Search in Google Scholar
2. Csank J, May R, Litt J, Ten-Huei G. Control design for a generic commercial aircraft engine[C].46th AIAA/ASME/SAE/ASEE Joint Propulsion Conference & Exhibit. 2010;6629:25–8.10.2514/6.2010-6629Search in Google Scholar
3. Zheng Q, Zhang H. A global optimization control for turbo-fan engine acceleration schedule design. Proc Inst Mech Eng, Part G: J Aerosp Eng. 2018;232:308–16.10.1177/0954410016683412Search in Google Scholar
4. Lu F, Huang J, Lv Y. Gas path health monitoring for a turbofan engine based on a nonlinear filtering approach[J]. Energies, 2013;6(1):492–513.10.3390/en6010492Search in Google Scholar
5. Zheng Q, Zhang H, Miao L, Sun F. On-board real-time optimization control for turbo-fan engine life extending[J]. Int J Turbo Jet-Engines. 2017;34(4):321–32.10.1515/tjj-2016-0015Search in Google Scholar
6. KrishnaKumar K, Hachisako Y, Huang Y. Jet engine performance estimation using intelligent system technologies. AIAA Aerospace Sciences Meeting and Exhibit, Reno, NV, 2001, 8(11).10.2514/6.2001-1122Search in Google Scholar
7. Chen T, Sun J. Direct Control of Aeroengine Thrust Based on Correlation Analysis and Neural Networks. J Nanjing Univ Aeronaut Astronaut. 2005;37:183–7.Search in Google Scholar
8. Simon DL, Armstrong JB, Garg S. Application of an Optimal Tuner Selection Approach for On-Board Self-Tuning Engine Models. ASME 2011 Turbo Expo: Turbine Technical Con-ference and Exposition. 2012:361–73.10.1115/1.4004178Search in Google Scholar
9. Csank JT, Connolly JW. Enhanced engine performance during emergency operation using a model-based engine control architecture. 51st AIAA/SAE/ASEE Joint Propulsion Confer-ence, 2015.10.2514/6.2015-3991Search in Google Scholar
10. Connolly JW, Csank J, Chicatelli A. Advanced Control Considerations for Turbofan Engine Design. Aiaa/sae/asee Joint Propulsion Conference, 2016.10.2514/6.2016-4653Search in Google Scholar
11. Csank J, Connolly JW. Model-Based Engine Control Architecture with an Extended Kalman Filter. AIAA Guidance, Navigation, and Control Conference, 2016.10.2514/6.2016-1623Search in Google Scholar
12. Gruenbacher E, Luigi DR. Robust inverse control for combustion engine test benches. American Control Conference, 2008. IEEE, 2008.10.1109/ACC.2008.4586926Search in Google Scholar
13. Srinathkumar S. Appendix C: BO-105 helicopter state variable models. Eigenstructure Control Algorithms: Applications to aircraft/rotorcraft handling qualities design. IET Digital Library, 2011.10.1049/PBCE074E_appendixcSearch in Google Scholar
14. Simplício P, Pavel M D, Van Kampen E, Chu Q. An acceleration measurements-based approach for helicopter nonlinear flight control using incremental nonlinear dynamic inversion[J]. Control Engineering Practice, 2013;21(8):1065–77.10.1016/j.conengprac.2013.03.009Search in Google Scholar
15. Zheng Q, Zhang H, Li Y, Hu Z. Aero-engine On-board Dynamic Adaptive MGD Neural Network Model within a Large Flight Envelope. IEEE Access. 2018;6:45755–61.10.1109/ACCESS.2018.2789935Search in Google Scholar
16. Schmidhuber J. Deep Learning in Neural Networks: an Overview . Neural Networks. 2015;61:85–117.10.1016/j.neunet.2014.09.003Search in Google Scholar PubMed
17. Goodfellow I, Bengio Y, Courville A, Bengio Y. Deep learning. Cambridge: MIT press; 2016.Search in Google Scholar
© 2019 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Review
- Assessment of Exit Temperature Pattern Factors in an Annular Gas Turbine Combustor: An Overview
- Original Research Articles
- Optimization of Trenched Film Cooling Using RSM Coupled CFD
- Modeling of Relative Exergy Destruction for Turboprop Engine Components Using Deep Learning Artificial Neural Networks
- Direct Thrust Inverse Control of Aero-Engine Based on Deep Neural Network
- Entropy, Energy and Exergy for Measuring PW4000 Turbofan Sustainability
- A Centrifugal Compressor Performance Map Empirical Prediction Method for Automotive Turbochargers
- Unsteady Numerical Simulation in a Supersonic Compressor Cascade with a Strong Shock Wave
- CFD Study of Combined Impingement and Film Cooling Flow on the Internal Surface Temperature Distribution of a Vane
- CFD Analysis of Flow and Performance Characteristics of a 90°curved Rectangular Diffuser: Effects of Aspect Ratio and Reynolds Number
- Effects of the Recess Length of the Pilot Stage on the Lean Blowout Limits for the Multipoint Lean Direct Injection Combustors
- Stress and Vibration Analysis of a PDC (Pulse Detonation Chamber)
- Transverse Injection Experiments within an Axisymmetric Scramjet Combustor
Articles in the same Issue
- Frontmatter
- Review
- Assessment of Exit Temperature Pattern Factors in an Annular Gas Turbine Combustor: An Overview
- Original Research Articles
- Optimization of Trenched Film Cooling Using RSM Coupled CFD
- Modeling of Relative Exergy Destruction for Turboprop Engine Components Using Deep Learning Artificial Neural Networks
- Direct Thrust Inverse Control of Aero-Engine Based on Deep Neural Network
- Entropy, Energy and Exergy for Measuring PW4000 Turbofan Sustainability
- A Centrifugal Compressor Performance Map Empirical Prediction Method for Automotive Turbochargers
- Unsteady Numerical Simulation in a Supersonic Compressor Cascade with a Strong Shock Wave
- CFD Study of Combined Impingement and Film Cooling Flow on the Internal Surface Temperature Distribution of a Vane
- CFD Analysis of Flow and Performance Characteristics of a 90°curved Rectangular Diffuser: Effects of Aspect Ratio and Reynolds Number
- Effects of the Recess Length of the Pilot Stage on the Lean Blowout Limits for the Multipoint Lean Direct Injection Combustors
- Stress and Vibration Analysis of a PDC (Pulse Detonation Chamber)
- Transverse Injection Experiments within an Axisymmetric Scramjet Combustor
