Skip to main content Accessibility help

A neural network approach to the calibration of a flush air data system

  • W. J. Crowther (a1) and P. J. Lamont (a1)


A flush air data system uses surface pressure measurements to obtain speed and aerodynamic orientation of a flight vehicle. This paper investigates the use of a neural network to calibrate the air data system on a low-observable aircraft forebody with 22 pressure tappings. Wind tunnel data were obtained for between 0 and 25° angle of attack, 0 to 10° sideslip for speeds of 32, 37 and 45ms-1. Experimental data were used to train multilayer perceptron neural networks. A calibration accuracy of 0·322ms-1, 0·811° and 0·552° for speed, alpha and beta respectively was achieved just using the first five tappings on the nose cone. Increasing the number of tappings used as inputs to the neural network reduces the calibration error. A neural network with 22 inputs gives a best accuracy of 0·095ms-1, 0·15° and 0·085° for speed, α and β respectively. Trained networks show poor robustness to single sensor failures. Robustness is improved by preprocessing input data with an autoassociative network or by introducing sensor redundancy.



Hide All
1. Cobleioh, B. and Del Frate, J. Water tunnel flow visualisation study of a4.4% scale X-31 forebody, Oct 1994, NASA TM-104276.S
2. Siemers, P., Wolf, H. and Henry, M. Shuttle entry air data system (SEADS) — Flight verification of an advanced air data system concept, May 1988, AIAA Paper 88-2104,.
3. Whitmore, S., Davis, R. and Fife, J. In-flight demonstration of a realtime flush air data sensing system, J Aircr, 1996, 33, (5), pp. 970-977.
4. Whitmore, S., Cobleioh, B. and Haering, E. Design and calibration of the X-33 flush air data sensing system, Jan 1998, NASA TM-1998-206540.
5. Wenger, C., Devenport, W. Seven-hole pressure probe calibration method utilizing look-up error tables, AIAA J, June 1999, 37, (6), pp675679.
6. Rohloff, T. Development and Evaluation of Neural Network Flush Air Data Sensing Systems, May 1998, PhD Dissertation, Dept of Mechanical Engineering, Univ of California, Los Angeles, CA.
7. Rediniotis, O. and Vuayagopal, R. Miniature multihole pressure probes and their neural network based calibration, AIAA J, June 1999, 37, (6), pp666674.
8. Rediniotis, O. and Chrysanthakopoulos, G. Application of neural networks and fuzzy logic to the calibration of the seven-hole probe, J Fluids Engineering — Transactions of the ASME, 1998, 120, (1), pp95101.
9. Minsky, M. and Papert, S. Perceptrons-An Introduction to Computational Geometry, MIT Press, 1969, London, ISBN 0-262-630222.
10. Rumelhart, D., Hinton, G. and Williams, J. Learning internal representations by error propagation, In Parallel Distributed Processing, Explorations in the Microstructure of Cognition. (1) foundations, MIT Press, 1987, London, ISBN 0-262-18120-7.
11. Rumelhart, D.E., Widrow, B. and Lehr, M.A. The basic ideas in neural networks, Communications of the ACM, Mar 1994, 37, (3), pp8692.
12. Gurney, K. An Introduction To Neural Networks, 1997, UCL Press, London. ISBN 1-85728-503-4.
13. Bishop, C. Neural Networks for Pattern Recognition, 1996, Oxford University Press, ISBN 0-19-853849-9.
14. Masters, T. Practical Neural Network Recipes in C++, 1993, Academic Press, ISBN 0-12-479040-2.
15. Blum, E. and Li, L. Approximation theory and feed-forward networks, Neural Networks, 4:4, pp511515.
16. Whitmore, S. and Moes, , Failure detection and fault management techniques for a pneumatic high angle-of-attack flush air data system, Jan 1992, NASA TM-4335.

A neural network approach to the calibration of a flush air data system

  • W. J. Crowther (a1) and P. J. Lamont (a1)


Full text views

Total number of HTML views: 0
Total number of PDF views: 0 *
Loading metrics...

Abstract views

Total abstract views: 0 *
Loading metrics...

* Views captured on Cambridge Core between <date>. This data will be updated every 24 hours.

Usage data cannot currently be displayed