The Application of Neural Networks for Spin Avoidance and Recovery 1999-01-5612
This paper presents a method by which artificial neural networks can be trained and used to identify a possible spin entry, differentiate between an incipient spin and a stabilized spin, and predict required recovery controls. These were then implemented into a simulation and tested using data from actual flight tests conducted by NASA Langley Research Center, to verify that artificial neural networks can successfully be used for this application. The spin avoidance and recovery system functioned properly. In addition, a weighting system was developed to predict possible spin characteristics of aircraft, depending on the relative magnitude of the three principal moments of inertia.
Citation: Lay,, L., Nagati, M., and Steck, J., "The Application of Neural Networks for Spin Avoidance and Recovery," SAE Technical Paper 1999-01-5612, 1999, https://doi.org/10.4271/1999-01-5612. Download Citation
Author(s):
Lawrence W. Lay,, M. Gawad Nagati, James E. Steck
Affiliated:
Wichita State University
Pages: 13
Event:
World Aviation Congress & Exposition
ISSN:
0148-7191
e-ISSN:
2688-3627
Related Topics:
Neural networks
Flight tests
Test procedures
Aircraft
Simulation and modeling
SAE MOBILUS
Subscribers can view annotate, and download all of SAE's content.
Learn More »
