Detection and classification of aircraft icing using neural networks

E. A. Schuchard, J. W. Melody, T. Başar, W. R. Perkins, P. Voulgaris

Research output: Contribution to conferencePaper

Abstract

This work introduces a neural network system that detects and classifies aircraft ice accretion in order to improve flight performance and safety. Neural networks are developed for use within an ice management system that monitors icing and its effects upon performance, stability and control. The ice management system would be used to automatically operate ice protection systems, to provide aircraft envelope protection and, when necessary, to adapt flight controls. A simplified longitudinal model of the DH-6 Twin Otter is used to study tailplane ice accumulation. An H parameter identification technique is applied to this model and relevant parameter estimates are used to characterize icing during a maneuver. Parameter estimates are used as inputs to a neural network system that both detects the presence of icing and classifies its severity. Extensive simulation results are presented that indicate the accuracy of the neural network detection and classification, even for modest levels of input.

Original languageEnglish (US)
StatePublished - Dec 1 2000
Event38th Aerospace Sciences Meeting and Exhibit 2000 - Reno, NV, United States
Duration: Jan 10 2000Jan 13 2000

Other

Other38th Aerospace Sciences Meeting and Exhibit 2000
CountryUnited States
CityReno, NV
Period1/10/001/13/00

Fingerprint

aircraft icing
Ice
aircraft
ice
ice formation
Aircraft
Neural networks
management systems
flight safety
flight
flight characteristics
flight control
parameter identification
Flight dynamics
maneuvers
estimates
monitors
Identification (control systems)
envelopes
accretion

ASJC Scopus subject areas

  • Space and Planetary Science
  • Aerospace Engineering

Cite this

Schuchard, E. A., Melody, J. W., Başar, T., Perkins, W. R., & Voulgaris, P. (2000). Detection and classification of aircraft icing using neural networks. Paper presented at 38th Aerospace Sciences Meeting and Exhibit 2000, Reno, NV, United States.

Detection and classification of aircraft icing using neural networks. / Schuchard, E. A.; Melody, J. W.; Başar, T.; Perkins, W. R.; Voulgaris, P.

2000. Paper presented at 38th Aerospace Sciences Meeting and Exhibit 2000, Reno, NV, United States.

Research output: Contribution to conferencePaper

Schuchard, EA, Melody, JW, Başar, T, Perkins, WR & Voulgaris, P 2000, 'Detection and classification of aircraft icing using neural networks', Paper presented at 38th Aerospace Sciences Meeting and Exhibit 2000, Reno, NV, United States, 1/10/00 - 1/13/00.
Schuchard EA, Melody JW, Başar T, Perkins WR, Voulgaris P. Detection and classification of aircraft icing using neural networks. 2000. Paper presented at 38th Aerospace Sciences Meeting and Exhibit 2000, Reno, NV, United States.
Schuchard, E. A. ; Melody, J. W. ; Başar, T. ; Perkins, W. R. ; Voulgaris, P. / Detection and classification of aircraft icing using neural networks. Paper presented at 38th Aerospace Sciences Meeting and Exhibit 2000, Reno, NV, United States.
@conference{4c5a45acada44921b707400d508186bd,
title = "Detection and classification of aircraft icing using neural networks",
abstract = "This work introduces a neural network system that detects and classifies aircraft ice accretion in order to improve flight performance and safety. Neural networks are developed for use within an ice management system that monitors icing and its effects upon performance, stability and control. The ice management system would be used to automatically operate ice protection systems, to provide aircraft envelope protection and, when necessary, to adapt flight controls. A simplified longitudinal model of the DH-6 Twin Otter is used to study tailplane ice accumulation. An H∞ parameter identification technique is applied to this model and relevant parameter estimates are used to characterize icing during a maneuver. Parameter estimates are used as inputs to a neural network system that both detects the presence of icing and classifies its severity. Extensive simulation results are presented that indicate the accuracy of the neural network detection and classification, even for modest levels of input.",
author = "Schuchard, {E. A.} and Melody, {J. W.} and T. Başar and Perkins, {W. R.} and P. Voulgaris",
year = "2000",
month = "12",
day = "1",
language = "English (US)",
note = "38th Aerospace Sciences Meeting and Exhibit 2000 ; Conference date: 10-01-2000 Through 13-01-2000",

}

TY - CONF

T1 - Detection and classification of aircraft icing using neural networks

AU - Schuchard, E. A.

AU - Melody, J. W.

AU - Başar, T.

AU - Perkins, W. R.

AU - Voulgaris, P.

PY - 2000/12/1

Y1 - 2000/12/1

N2 - This work introduces a neural network system that detects and classifies aircraft ice accretion in order to improve flight performance and safety. Neural networks are developed for use within an ice management system that monitors icing and its effects upon performance, stability and control. The ice management system would be used to automatically operate ice protection systems, to provide aircraft envelope protection and, when necessary, to adapt flight controls. A simplified longitudinal model of the DH-6 Twin Otter is used to study tailplane ice accumulation. An H∞ parameter identification technique is applied to this model and relevant parameter estimates are used to characterize icing during a maneuver. Parameter estimates are used as inputs to a neural network system that both detects the presence of icing and classifies its severity. Extensive simulation results are presented that indicate the accuracy of the neural network detection and classification, even for modest levels of input.

AB - This work introduces a neural network system that detects and classifies aircraft ice accretion in order to improve flight performance and safety. Neural networks are developed for use within an ice management system that monitors icing and its effects upon performance, stability and control. The ice management system would be used to automatically operate ice protection systems, to provide aircraft envelope protection and, when necessary, to adapt flight controls. A simplified longitudinal model of the DH-6 Twin Otter is used to study tailplane ice accumulation. An H∞ parameter identification technique is applied to this model and relevant parameter estimates are used to characterize icing during a maneuver. Parameter estimates are used as inputs to a neural network system that both detects the presence of icing and classifies its severity. Extensive simulation results are presented that indicate the accuracy of the neural network detection and classification, even for modest levels of input.

UR - http://www.scopus.com/inward/record.url?scp=84894366658&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84894366658&partnerID=8YFLogxK

M3 - Paper

AN - SCOPUS:84894366658

ER -