Modeling of aircraft vibration comfort using machine learning methods

Authors

  • Universidade Estadual do Oeste do Paraná – UNIOESTE Centro de Engenharias e Ciências Exatas
  • Universidade Estadual do Oeste do Paraná – UNIOESTE Centro de Engenharias e Ciências Exatas
  • Instituto Federal de Santa Catarina. Universidade Federal de Santa Catarina – UFSC Departamento de Engenharia Mecânica

DOI:

https://doi.org/10.5944/ribim.18.2.42584

Keywords:

Aviation, Comfort, Artificial Intelligence, Attribute Selection

Abstract

The increased competition in the aircraft market has motivated the aircraft industry to develop higher quality services for the customers. In this sense, an inter-institutional project has being developed for modeling passenger subjective responses related to adjectives (comfort, constancy, force, supportability) occasioned
by physical stimuli vibrations on aircrafts simulators. In this work, it is used Computational Intelligence methods, specifically Machine Learning, to perform feature selection and to build regression models. In the feature
selection task it was used a filter approach. Machine learning algorithms were used to build Artificial Neural
Networks, Multiple Linear Regression and Regression Trees. The experimental method proposed aims to predict passenger subjective responses only considering most important frequency bands of vibratory stimuli according to each adjective. The model evaluation was performed based on predictive quality and complexity. Is
is shown that the proposed method allowed a reduction from 86.42% to 98.15% in the amount of used frequency bands to induce models without impairing the quality of predictions. In addition, 25% of the models showed
statistically significant improvement. According to experts the built models were promising, both in terms of
complexity and predictive quality.

Downloads

Download data is not yet available.

Published

2014-10-01

How to Cite

Schaefer , R. L., Ferrero , C. A. ., & Gerges , S. N. Y. . (2014). Modeling of aircraft vibration comfort using machine learning methods. Revista Iberoamericana de Ingeniería Mecánica, 18(2), 125–136. https://doi.org/10.5944/ribim.18.2.42584

Issue

Section

Articles