Abstract
This work evaluates the accuracy and reliability of PIO test classification using the PIO Rating Scale and proposes using an automatic tool for this evaluation based on test data to eliminate the subjectivity inherent to the application of rating scales. Two test procedures (discrete synthetic task and pitch capture) are executed in a flight simulator, using aircraft dynamic models with different PIO proneness and experienced flight test pilots. The results show a significant effect of subjectivity in pilot rating and various reliability for different test procedures. This data is used to build an artificial neural network (ANN) proposed to classify the executions using the PIO Rating Scale. The ANN presented low computational cost and 97.1% accuracy when using data extracted from the pitch capture test procedure.
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig1_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig2_HTML.jpg)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig3_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig4_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig5_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig6_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig7_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig8_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig9_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig10_HTML.png)
![](http://media.springernature.com/m312/springer-static/image/art%3A10.1007%2Fs40430-024-05070-y/MediaObjects/40430_2024_5070_Fig11_HTML.png)
References
Celere AL 2008 “Método para Avaliação do Ganho Empregado Pelo Piloto para Ensaios de PIO” (in Portuguese) Ph.D. Dissertation, São Carlos School of Engineering. University of São Paulo, São Carlos
Mitchell DG, Hoh RH, 1999. “Development of methods and devices to predict and prevent Pilot-Induced Oscillations.”, Hoh Aeronautics Inc.
Anderson MR (1998) Pilot-induced oscillations involving multiple nonlinearities. J Guid Control Dyn 21(5):786–792. https://doi.org/10.2514/2.4307
Bidinotto JH, Almeida SP (2021) “A historical review of pilot induced oscillation (PIO) Occurrence”, 26th International Congress of Mechanical Engineering, COBEM. Virtual Congress. https://doi.org/10.26678/ABCM.COBEM2021.COB2021-0307
Hess RA, Kalteis RM (1991) Technique for predicting longitudinal pilot-induced oscillations. J Guid Control Dyn 14(1):198–204. https://doi.org/10.2514/3.20622
Cooper, G., and Harper, R., “The use of pilot rating in the evaluation of aircraft handling qualities,” NASA TN D-5153, 1969.
Department of Defense Interface Standard, “Flying Qualities of Piloted Airplanes,” Mil Standard MIL1797A, 1990.
Weingarten NC, Chalk CR (1984) In-flight investigation of large airplane flying qualities for approach and landing. J Guidance, Control, Dyn 7(1):92–98
Federal Aviation Administration, Code of Federal Regulations, “Flight test Guide for Transport Category,” Airplanes Advisory Circular AC25–7D, 2018.
Suzuki S, Sakamoto Y, Sanematsu Y, Takahara H (2006) Analysis of human pilot control inputs using neural network. J Aircr 43(3):793–796. https://doi.org/10.2514/1.16898
Mori R, Suzuki S, Masui K, Tomita H (2008) Neural network analysis of pilot landing control in real flight. J Mech Syss Transp Logist 1(1):14–21. https://doi.org/10.1299/jmtl.1.14
Mori R, Suzuki S (2009) Neural network modeling of lateral pilot landing control. J Aircr 46(5):1721–1726. https://doi.org/10.2514/1.42576
Tan W, Wu Y, Qu X, Efremov AV. 2014. “A method for predicting aircraft flying qualities using neural networks pilot model.” 2nd International Conference on Systems and Informatics, ICSAI.
Turetta FMS, Ayala HVH, Trabasso LG, Coelho LS Alfredson J. 2018. “Data-Driven Pilot Behavior Modeling Applied to an Aircraft Offset Landing Task.” International Conference on Applied Human Factors and Ergonomics AHFE.
Turetta FMS, Ayala HVH, Trabasso LG, Alfredson J (2016) “Data-driven pilot behavior modeling applied to a VMCG determination flight test task”, aerospace technology congress, FTF. Stockholm, Sweden
Oliveira MM, Mayor GS, Macedo JP, Bidinotto JH (2022) Neural networks to classify atmospheric turbulence from flight test data: an optimization of input parameters for a generic model. J Braz Soc Mech Sci Eng 44(3):82. https://doi.org/10.1007/s40430-022-03386-1
Efremov AV, Rodchenko VV, and Boris S, 1996. “Investigation of pilot induced oscillation tendency and prediction criteria development.” Moscow aviation institute report WL-TR-96–3109
Bidinotto J H, Moura H C, Neves G D A, 2022. Universidade de São Paulo, São Carlos, SP, Brazil. Patent Application for a SynTask – Software de Tarefas Sintéticas Aeronáuticas No BR512022002377–6, filed 06 Sep.
Neves GDA, Bruschi AG, Bidinotto JH (2021) “Development of a tool for pilot induced oscillations (PIO) testing in flight simulator”, 26th international congress of mechanical engineering, COBEM. Virtual Congress. https://doi.org/10.26678/ABCM.COBEM2021.COB2021-0036
Etkin B, Reid LD (1996) Dynamics of flight: stability and control, 3rd edn. Wiley, New York
Moura HC, Alegre GSP, Bidinotto JH, Belo EM (2018) “PIO susceptibility in fly-by-wire systems”, 31st congress of the international council of the aeronautical sciences. ICAS, Belo Horizonte
Silva IN, Spatti DH, Flauzino RA (2016) Redes Neurais Artificiais para Engenharia e Ciências Aplicadas, 2nd edn. Artliber, São Paulo, Brazil
Chen E, Zhang M, David Wang D (2021) Effects of sample size on neural network training for image classification tasks. IEEE Transactions on Neural Networks and Learning Systems 32(5):2000–2012. https://doi.org/10.1109/TNNLS.2020.3014668
Garcia M, Martinez J, Diaz L (2019) The Impact of sample size on subjective ratings of user experience in human-computer interaction studies. Int J Human-Comput Interaction 35(4):378–392. https://doi.org/10.1080/10447318.2018.1526472
Mello, Ricardo S, David H. Klyde, and David G. Mitchell. “Aircraft Accident Investigation Using Wavelet Scalogram-Based Metric to Identify Possible PIO Signature.” AIAA SCITECH 2023 Forum. 2023
Acknowledgements
The authors thanks EMBRAER S.A. to make available some of the flight test pilots to perform the tests for this work.
Funding
This research received no specific grant from any funding agency in the public, commercial, or not for-profit sectors.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declared no potential conflicts of interest with respect to the research, authorship, and/or publication of this article.
Additional information
Technical Editor: Flávio Silvestre.
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bruschi, A.G., Drewiacki, D. & Bidinotto, J.H. Artificial neural networks for PIO events classification comparing different data collection procedures. J Braz. Soc. Mech. Sci. Eng. 46, 496 (2024). https://doi.org/10.1007/s40430-024-05070-y
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s40430-024-05070-y