Data-Driven Detection of Pilot-Induced Oscillations using Principal Component Analysis
André L. A. PALADINI, Raghu Chaitanya MUNJULURY, Daniel DREWIACKI, Petter KRUS, Jorge Henrique BIDINOTTO
Abstract. This study proposes a PIO detection algorithm based on a convolutional/fully connected regression neural network that processes PCA-reduced flight data from wavelet-transformed signals. The model achieved a correlation of 0.88, according to the modified Pearson Correlation Coefficient, with Principal Component Analysis enabling a two-order-of-magnitude dataset reduction and improved training efficiency.
Keywords
Pilot-Induced Oscillations, Principal Component Analysis, Convolutional Neural Network, Wavelet Transform, Flight Simulators
Published online 7/20/2026, 6 pages
Copyright © 2026 by the author(s)
Published under license by Materials Research Forum LLC., Millersville PA, USA
Citation: André L. A. PALADINI, Raghu Chaitanya MUNJULURY, Daniel DREWIACKI, Petter KRUS, Jorge Henrique BIDINOTTO, Data-Driven Detection of Pilot-Induced Oscillations using Principal Component Analysis, Materials Research Proceedings, Vol. 69, pp 1460-1465, 2026
DOI: https://doi.org/10.21741/9781644904251-256
The article was published as article 256 of the book CEAS – AIDAA Conference 2025
Content from this work may be used under the terms of the Creative Commons Attribution 3.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI.
References
[1] J. Hodgkinson, Aircraft Handling Qualities, 1st. Reston, VA: AIAA Education Series, 1999, p. 517.
[2] A. L. A. Paladini, D. Drewiacki, and J. H. Bidinotto, “Aeroelastic effects in PIO occurrences: A dual approach on flight simulator tests”, Aerospace Science and Technology, p. 109337, 2024. https://doi.org/10.1016/j.ast.2024.109337
[3] D. Mitchell, A. Arencibia, and S. Munoz, “Real-time detection of pilot-induced oscillations”, in AIAA Atmospheric Flight Mechanics Conference and Exhibit, 2004, p. 4700.
[4] A. L. A. Paladini, D. Drewiacki, R. Munjulury, et al., “Convolutional neural network for detection and quantification of pilot-induced oscillations”, in Swedish Aerospace Conference, FT2025, vol. 215, 2025. https://doi.org/10.3384/wcc215.1194
[5] G. James, D. Witten, T. Hastie, R. Tibshirani, et al., An introduction to statistical learning. Springer, 2013, vol. 112.
[6] E. Bachelder, E. Bjorkman, and B. Aponso, “PIO and handling qualities prediction using the USAFTPS Bjorkman PIO data set”, in Vertical Flight Society’s 80th Annual Forum & Technology Display, Montreal, Canada, 2024.
