Neural network-based dynamic model and gust identification system for the jetstream G-NFLA

Abstract

Artificial neural networks are an established technique for constructing non-linear models of multi-input–multi-output systems based on sets of observations. In terms of aerospace vehicle modeling, however, these are currently restricted to either unmanned applications or simulations, despite the fact that large amounts of flight data are typically recorded and kept for reasons of safety and maintenance. In this paper, a methodology for constructing practical models of aerospace vehicles based on available flight data recordings from the vehicles’ operational use is proposed and applied on the Jetstream G-NFLA aircraft. This includes a data analysis procedure to assess the suitability of the available flight databases and a neural network-based approach for modeling. In this context, a database of recorded landings of the Jetstream G-NFLA, normally kept as part of a routine maintenance procedure, is used to form training datasets for two separate applications. A neural network-based longitudinal dynamic model and gust identification system are constructed and tested against real flight data. Results indicate that in both cases, the resulting models’ predictions achieve a level of accuracy that allows them to be used as a basis for practical real-world applications.

Keywords

Artificial neural networks flight testing system identification gust identification hybrid identification

Get full access to this article

View all access options for this article.

References

Kosmatopoulos

Polycarpou

Christodoulou

. High-order neural network structures for identification of dynamical systems. IEEE Transact Neural Network 1995; 6: 422–431.

Shin Y. Neural network based adaptive control for nonlinear dynamic regimes. PhD Thesis, Georgia Institute of Technology, 2005.

Haga R, Matsuura A, Suzuki S, et al. Neural network based adaptive flight control using feedback error learning. In: AIAA guidance, navigation and control conference, Keystone, Colorado, 21–24 August 2006.

Krüger T, Mößner M, Axmann J, et al. Adaptive flight control for unmanned aircraft using a stable neural network observer. In: AIAA Infotech@Aerospace, Atlanta, Georgia, 20–22 April 2010.

Stastny T, Lykins R and Keshmiri S. Nonlinear parameter estimation of unmanned aerial vehicle in wind shear using artificial neural networks. In: Guidance, navigation and control and co-located conferences, Boston, MA, 19–22 August 2013.

Puttige

Anavatti

. Real-time system identification of unmanned aerial vehicles: a multi-network approach. J Comput 2008; 3: 31–38.

Williams-Hayes P. Selected flight test results for online learning neural network-based flight control system. NASA Technical Report TR-2004-212857, 2004.

Nie R, Weiguo Z, Guangwen L, et al. A neural gust load alleviator for aircraft model using active. In: IEEE international conference on intelligent computing and intelligent systems, Shanghai, 2009.

Pashilkar A, Sundararajan N and Saratchadran P. Neuro controller for aircraft auto landing under severe winds and control surface failures. In: Aerospace sciences meeting and exhibit, Reno, Nevada, 2005.

10.

Nie R, Zhang W, Guangwen L, et al. Application of model-following adaptive neural network control theory in gust load alleviation. In: IEEE international conference on automation and logistics, Shenyang, China, 2009.

11.

National Flying Laboratory Centre. Introduction to the Aircraft: G-NFLA, Cranfield: Cranfield University, 2012.

12.

Powel M. Radial basis functions for multivariable interpolation: a review. In: IMA conference on Algorithms for the approximation of functions and data, July 1985. RMCS Shrivenham.

13.

Broomhead

Lowe

. Radial basis functions, multi-variable functional interpolation and adaptive networks, London: Royal Signals & Radar Establishment, 1988.

14.

Haykin

. Neural networks: a comprehensive foundation, Upper Saddle River, NJ: Prentice Hall, 1999.

15.

Hertz

Krogh

Palmer

. Introduction to the theory of neural computation, Boston, MA: Addison Wesley, 1991.

16.

Micchelli

. Interpolation of scattered data: distance matrices and conditionally positive definite functions. Construct Approx 1986; 2: 11–22.

17.

Mahalanobis

. On the generalised distance in statistics. Proc National Inst Sci India 1936; 2: 49–55.

18.

Lloyd

. Least squares quantization in PCM. IEEE Transact Inform Theor 1982; 28: 129–137.

19.

Zapranis A and Livanis E. Prediction intervals for neural networks. In: 9th WSEAS international conference in computers, Wisconsin, USA, 14–16 July 2005.

20.

Mazloumi

Rose

Currie

. Prediction intervals to account for uncertainties in neural network predictions: methodology and application in bus travel time prediction. Eng Appl Artificial Intell 2011; 24: 534–542.

21.

Zio

. A study of the Bootstrap Method for estimating the accuracy of artificial neural networks in predicting nuclear transient processes. IEEE Transact Nucl Sci 2006; 53: 1460–1478.

22.

Carney J and Cunningham P. Confidence and prediction intervals for neural network ensembles. In: International joint conference on neural networks, Washington, DC, 1999.

23.

Pearson

. On lines and planes of closest fit to systems of points in space. Philos Magazine 1901; 2: 559–572.

24.

Jolliffe

. Principal component analysis, New York, NY: Springer Science+Business Media, 1986.

25.

Hastie

Tibshirani

Friedman

. The elements of statisticcal learning: data mining, inference and prediction, New York: Springer Science+Business Media LLC, 2009.

26.

Kyriacou

Asouti

Giannakoglou

. Efficient PCA-driven EAs and metamodel-assisted EAs, with applications in turbomachinery. Eng Optimiz 2014; 46: 895–911.

27.

Cooke

. Simulation model of the NFLC Jetstream 31, Cranfield: Cranfield College of Aeronautics, 2006.