DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Fast Evaluation of Aircraft Icing Severity Using Machine Learning Based on XGBoost

Abstract

Aircraft icing represents a serious hazard in aviation which has caused a number of fatal accidents over the years. In addition, it can lead to substantial increase in drag and weight, thus reducing the aerodynamics performance of the airplane. The process of ice accretion on a solid surface is a complex interaction of aerodynamic and environmental variables. The complex relationship makes machine learning-based methods an attractive alternative to traditional numerical simulation-based approaches. In this study, we introduce a purely data-driven approach to find the complex pattern between different flight conditions and aircraft icing severity prediction. The supervised learning algorithm Extreme Gradient Boosting (XGBoost) is applied to establish the prediction framework which makes prediction based on any set of observations. The input flight conditions for the proposed prediction framework are liquid water content, droplet diameter and exposure time. The proposed approach is demonstrated in three cases: maximum ice thickness prediction, icing area prediction and icing severity level evaluation. Performance comparison studies and error analysis are also conducted to verify the effectiveness and performance of the proposed method. Results show that the proposed method has reasonable capability in evaluating aircraft icing severity.

Authors:
ORCiD logo; ; ; ORCiD logo
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1607827
Grant/Contract Number:  
#ANL 4J-30361-0030A
Resource Type:
Published Article
Journal Name:
Aerospace
Additional Journal Information:
Journal Name: Aerospace Journal Volume: 7 Journal Issue: 4; Journal ID: ISSN 2226-4310
Publisher:
MDPI AG
Country of Publication:
Switzerland
Language:
English

Citation Formats

Li, Sibo, Qin, Jingkun, He, Miao, and Paoli, Roberto. Fast Evaluation of Aircraft Icing Severity Using Machine Learning Based on XGBoost. Switzerland: N. p., 2020. Web. doi:10.3390/aerospace7040036.
Li, Sibo, Qin, Jingkun, He, Miao, & Paoli, Roberto. Fast Evaluation of Aircraft Icing Severity Using Machine Learning Based on XGBoost. Switzerland. https://doi.org/10.3390/aerospace7040036
Li, Sibo, Qin, Jingkun, He, Miao, and Paoli, Roberto. Tue . "Fast Evaluation of Aircraft Icing Severity Using Machine Learning Based on XGBoost". Switzerland. https://doi.org/10.3390/aerospace7040036.
@article{osti_1607827,
title = {Fast Evaluation of Aircraft Icing Severity Using Machine Learning Based on XGBoost},
author = {Li, Sibo and Qin, Jingkun and He, Miao and Paoli, Roberto},
abstractNote = {Aircraft icing represents a serious hazard in aviation which has caused a number of fatal accidents over the years. In addition, it can lead to substantial increase in drag and weight, thus reducing the aerodynamics performance of the airplane. The process of ice accretion on a solid surface is a complex interaction of aerodynamic and environmental variables. The complex relationship makes machine learning-based methods an attractive alternative to traditional numerical simulation-based approaches. In this study, we introduce a purely data-driven approach to find the complex pattern between different flight conditions and aircraft icing severity prediction. The supervised learning algorithm Extreme Gradient Boosting (XGBoost) is applied to establish the prediction framework which makes prediction based on any set of observations. The input flight conditions for the proposed prediction framework are liquid water content, droplet diameter and exposure time. The proposed approach is demonstrated in three cases: maximum ice thickness prediction, icing area prediction and icing severity level evaluation. Performance comparison studies and error analysis are also conducted to verify the effectiveness and performance of the proposed method. Results show that the proposed method has reasonable capability in evaluating aircraft icing severity.},
doi = {10.3390/aerospace7040036},
journal = {Aerospace},
number = 4,
volume = 7,
place = {Switzerland},
year = {2020},
month = {3}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.3390/aerospace7040036

Save / Share:

Works referenced in this record:

A Data-Driven Design for Fault Detection of Wind Turbines Using Random Forests and XGboost
journal, January 2018


Scalability of OpenFOAM Density-Based Solver with Runge–Kutta Temporal Discretization Scheme
journal, March 2020

  • Li, Sibo; Paoli, Roberto; D’Mello, Michael
  • Scientific Programming, Vol. 2020
  • DOI: 10.1155/2020/9083620

Aircraft ice accretion prediction using neural network and wavelet packet transform
journal, January 2016

  • Chang, Shinan; Leng, Mengyao; Wu, Hongwei
  • Aircraft Engineering and Aerospace Technology, Vol. 88, Issue 1
  • DOI: 10.1108/AEAT-05-2014-0057

Fast evaluation of well placements in heterogeneous reservoir models using machine learning
journal, April 2018

  • Nwachukwu, Azor; Jeong, Hoonyoung; Pyrcz, Michael
  • Journal of Petroleum Science and Engineering, Vol. 163
  • DOI: 10.1016/j.petrol.2018.01.019

ONERA three-dimensional icing model
journal, June 1995

  • Hedde, T.; Guffond, D.
  • AIAA Journal, Vol. 33, Issue 6
  • DOI: 10.2514/3.12795

NNICE – a neural network aircraft icing algorithm
journal, October 2005


Prediction of Icing Effects on the Dynamic Response of Light Airplanes
journal, May 2007

  • Lampton, Amanda; Valasek, John
  • Journal of Guidance, Control, and Dynamics, Vol. 30, Issue 3
  • DOI: 10.2514/1.25687

Numerical simulation of three-dimensional ice accretion on an aircraft wing
journal, January 2016


Iced-airfoil aerodynamics
journal, July 2005


Aircraft icing: An ongoing threat to aviation safety
journal, April 2018


A tensorial approach to computational continuum mechanics using object-oriented techniques
journal, January 1998

  • Weller, H. G.; Tabor, G.; Jasak, H.
  • Computers in Physics, Vol. 12, Issue 6
  • DOI: 10.1063/1.168744

Turbulence Intensity Measurement Technique for Use in Icing Wind Tunnels
journal, May 1999

  • Henze, Chad M.; Bragg, Michael B.
  • Journal of Aircraft, Vol. 36, Issue 3
  • DOI: 10.2514/2.2473

Numerical simulation of ice accretions on an aircraft wing
journal, December 2012


Multiparameter Analysis of Aero-Icing Problems Using Proper Orthogonal Decomposition and Multidimensional Interpolation
journal, April 2013

  • Fossati, Marco; Habashi, Wagdi G.
  • AIAA Journal, Vol. 51, Issue 4
  • DOI: 10.2514/1.J051877

Effects of ice geometry on airfoil performance using neural networks prediction
journal, September 2011

  • Cao, Yihua; Yuan, Kungang; Li, Guozhi
  • Aircraft Engineering and Aerospace Technology, Vol. 83, Issue 5
  • DOI: 10.1108/00022661111159870

PoliMIce: A simulation framework for three-dimensional ice accretion
journal, September 2015


A New Flux Splitting Scheme
journal, July 1993

  • Liou, Meng-Sing; Steffen, Christopher J.
  • Journal of Computational Physics, Vol. 107, Issue 1
  • DOI: 10.1006/jcph.1993.1122

Equilibrium Temperature of an Unheated Icing Surface as a Function of Air Speed
journal, January 1953

  • Messinger, Bernard L.
  • Journal of the Aeronautical Sciences, Vol. 20, Issue 1
  • DOI: 10.2514/8.2520

Extension to the Messinger Model for Aircraft Icing
journal, February 2001


Modeling of Ice Accretion over Aircraft Wings Using a Compressible OpenFOAM Solver
journal, June 2019

  • Li, Sibo; Paoli, Roberto
  • International Journal of Aerospace Engineering, Vol. 2019
  • DOI: 10.1155/2019/4864927

Aircraft Ice Accretion Prediction Based on Neural Networks
journal, January 2006

  • Ogretim, E.; Huebsch, W.; Shinn, A.
  • Journal of Aircraft, Vol. 43, Issue 1
  • DOI: 10.2514/1.16241

machine.
journal, October 2001


A New Version of Detached-eddy Simulation, Resistant to Ambiguous Grid Densities
journal, May 2006

  • Spalart, P. R.; Deck, S.; Shur, M. L.
  • Theoretical and Computational Fluid Dynamics, Vol. 20, Issue 3
  • DOI: 10.1007/s00162-006-0015-0

Real-Time Regional Jet Comprehensive Aeroicing Analysis via Reduced-Order Modeling
journal, December 2016

  • Zhan, Zhao; Habashi, Wagdi G.; Fossati, Marco
  • AIAA Journal, Vol. 54, Issue 12
  • DOI: 10.2514/1.J055013

A single step ice accretion model using Level-Set method
journal, August 2016