A Novel Modeling Method for Aircraft Engine Using Nonlinear Autoregressive Exogenous (NARX) Models Based on Wavelet Neural Networks
-
Bing Yu
,
Wenjun Shu
Abstract
A novel modeling method for aircraft engine using nonlinear autoregressive exogenous (NARX) models based on wavelet neural networks is proposed. The identification principle and process based on wavelet neural networks are studied, and the modeling scheme based on NARX is proposed. Then, the time series data sets from three types of aircraft engines are utilized to build the corresponding NARX models, and these NARX models are validated by the simulation. The results show that all the best NARX models can capture the original aircraft engine’s dynamic characteristic well with the high accuracy. For every type of engine, the relative identification errors of its best NARX model and the component level model are no more than 3.5 % and most of them are within 1 %.
Funding statement: This work is supported by the Natural Science Foundation of Jiangsu Province (BK20140820), the Fundamental Research Funds for the Central Universities (no. NJ20160037), Natural Science Foundation of China (no. 51406083, no. 61304113).
References
1. Jun LU, Guo YQ, Zhang SG. Research on the iteration methods in aero-engine non-linear model real-time computation. J Aerosp Power 2010;25(3): 681–686.Search in Google Scholar
2. Jaw LC, Mattingly JD. Aircraft engine controls: design, system analysis and health monitoring, Reston, VA: American Institute of Aeronautics and Astronautics, 2009.10.2514/4.867057Search in Google Scholar
3. Sjöberg J, Zhang Q, Ljung L, Benveniste A, Delyon B, Glorennec PY, et al.. Nonlinear black-box modeling in system identification: a unified overview. Automatica 1995;31(12):1691–1724.10.1016/0005-1098(95)00120-8Search in Google Scholar
4. Juditsky A, Hjalmarsson H, Benveniste A, Delyon B, Ljung L, Berg J, et al.. Nonlinear black-box models in system identification: mathematical foundations. Automatica 1995;31(12):1725–1750.10.1016/0005-1098(95)00119-1Search in Google Scholar
5. Narendra KS, Parthasarathy K. Identification and control of dynamical systems using neural networks. IEEE Trans Neural Networks 1990;1(1):4–27.10.1109/72.80202Search in Google Scholar PubMed
6. Lazzaretto A, Toffolo A. Analytical and neural network models for gas turbine design and off-design simulation. Int J Thermodyn 2001;4:4.Search in Google Scholar
7. Basso M, Giarre L, Groppi S, Zappa G. NARX models of an industrial power plant gas turbine. IEEE Trans Control Syst Technol 2005;13(4):599–604.10.1109/TCST.2004.843129Search in Google Scholar
8. Fast M, Assadi M, Sudipta D. Condition based maintenance of gas turbines using simulation data and artificial neural network: a demonstration of feasibility. ASME Turbo Expo 2008: Power for Land, Sea, and Air, 2008.Search in Google Scholar
9. Fast M, Assadi M, De S. Development and multi-utility of an ANN model for an industrial gas turbine. Appl Energy 2009;86(1):9–17.10.1016/j.apenergy.2008.03.018Search in Google Scholar
10. Palmé T, Fast M, Thern M. Gas turbine sensor validation through classification with artificial neural networks. Appl Energy 2011;88(11):3898–3904.10.1016/j.apenergy.2011.03.047Search in Google Scholar
11. Asgari H, Chen XQ, Morini M, Pinelli M, Sainudiin R, Spina PR, et al.. NARX models for simulation of the start-up operation of a single-shaft gas turbine. Appl Therm Eng 2015;93:368–376.10.1016/j.applthermaleng.2015.09.074Search in Google Scholar
12. Tang X. Wavelet neural networks based system identification. Inf Control 1998;27(4):32–35.Search in Google Scholar
13. Zheng W. A nonlinear model identification method of photovoltaic grid-connected inverters based on the NARX model. Smart Grid 2015;05(5):228–241.10.12677/SG.2015.55028Search in Google Scholar
14. Ljung L, Singh R. Version 8 of the Matlab System identification toolbox[J]. IFAC Proceedings Volumes, 2012;45(16):1826–1831.10.3182/20120711-3-BE-2027.00061Search in Google Scholar
15. Chapman JW, Lavelle TM, May RD, Litt JS, Guo T-H, “Propulsion System Simulation Using the Toolbox for the Modeling and Analysis of Thermodynamic Systems (T-MATS),” AIAA Joint Propulsion Conference, Cleveland, OH, 28–30 July, 2014.10.2514/6.2014-3929Search in Google Scholar
© 2018 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Jet Engines – The New Masters of Advanced Flight Control
- Prediction of Film Cooling Effectiveness on a Gas Turbine Blade Leading Edge Using ANN and CFD
- Sustainability Metrics of a Small Scale Turbojet Engine
- Coupling Network Computing Applications in Air-cooled Turbine Blades Optimization
- Performance Enhancement of One and Two-Shaft Industrial Turboshaft Engines Topped With Wave Rotors
- Semi-Immersive Virtual Turbine Engine Simulation System
- A Novel Modeling Method for Aircraft Engine Using Nonlinear Autoregressive Exogenous (NARX) Models Based on Wavelet Neural Networks
- Defining the Ecological Coefficient of Performance for an Aircraft Propulsion System
- Investigation on the Accuracy of Superposition Predictions of Film Cooling Effectiveness
- Computational Investigations in Rectangular Convergent and Divergent Ribbed Channels
Articles in the same Issue
- Frontmatter
- Jet Engines – The New Masters of Advanced Flight Control
- Prediction of Film Cooling Effectiveness on a Gas Turbine Blade Leading Edge Using ANN and CFD
- Sustainability Metrics of a Small Scale Turbojet Engine
- Coupling Network Computing Applications in Air-cooled Turbine Blades Optimization
- Performance Enhancement of One and Two-Shaft Industrial Turboshaft Engines Topped With Wave Rotors
- Semi-Immersive Virtual Turbine Engine Simulation System
- A Novel Modeling Method for Aircraft Engine Using Nonlinear Autoregressive Exogenous (NARX) Models Based on Wavelet Neural Networks
- Defining the Ecological Coefficient of Performance for an Aircraft Propulsion System
- Investigation on the Accuracy of Superposition Predictions of Film Cooling Effectiveness
- Computational Investigations in Rectangular Convergent and Divergent Ribbed Channels
