Aircraft Numerical "Twin": A Time Series Regression Competition - Archive ouverte HAL Access content directly
Conference Papers Year :

Aircraft Numerical "Twin": A Time Series Regression Competition

(1) , (2, 1) , (3) , (3) , (4) , (4) , (4) , (4) , (4) , (4) , (4) , (4) , (5) , (5) , (5) , (5) , (5) , (6) , (6) , (6) , (6) , (6) , (7) , (7) , (7) , (7) , (7) , (8) , (8) , (8) , (8)
1
2
3
4
5
6
7
8
Adrien Pavao
  • Function : Author
  • PersonId : 1049181
Nachar Stéphane
Fabrice Lebeau
  • Function : Author
Alaeddine Ben Cheikh
  • Function : Author
Marc Duda
  • Function : Author
Julien Laugel
  • Function : Author
Mathieu Marauri
  • Function : Author
Mhamed Souissi
  • Function : Author
Théo Lecerf
  • Function : Author
Mehdi Elion
  • Function : Author
Sonia Tabti
  • Function : Author
Julien Budynek
  • Function : Author
Antonin Penon
  • Function : Author
Julien Ripoche
  • Function : Author
Thomas Epalle
  • Function : Author

Abstract

This paper presents the design and analysis of a data science competition on a problem of time series regression from aeronautics data. For the purpose of performing predictive maintenance, aviation companies seek to create aircraft "numerical twins", which are programs capable of accurately predicting strains at strategic positions in various body parts of the aircraft. Given a number of input parameters (sensor data) recorded in sequence during the flight, the competition participants had to predict output values (gauges), also recorded sequentially during test flights, but not recorded during regular flights. The competition data included hundreds of complete flights. It was a code submission competition with complete blind testing of algorithms. The results indicate that such a problem can be effectively solved with gradient boosted trees, after preprocessing and feature engineering. Deep learning methods did not prove as efficient.
Fichier principal
Vignette du fichier
Airplane_Numerical_Twin_HAL.pdf (2.42 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03463307 , version 1 (02-12-2021)
hal-03463307 , version 2 (16-12-2021)
hal-03463307 , version 3 (06-01-2022)

Identifiers

  • HAL Id : hal-03463307 , version 3

Cite

Adrien Pavao, Isabelle Guyon, Nachar Stéphane, Fabrice Lebeau, Martin Ghienne, et al.. Aircraft Numerical "Twin": A Time Series Regression Competition. ICMLA 2021 - 20th IEEE International Conference on Machine Learning and Applications., Dec 2021, Pasadena / Virtual, United States. ⟨hal-03463307v3⟩
269 View
170 Download

Share

Gmail Facebook Twitter LinkedIn More