Eliciting a human understandable model of ice adhesion strength for rotor blade leading edge materials from uncertain experimental data

Ana M. Palacios, Jose Palacios, Luciano Sánchez

Research output: Contribution to journalArticle

10 Citations (Scopus)

Abstract

The published ice adhesion performance data of novel "ice-phobic" coatings varies significantly, and there are not reliable models of the properties of the different coatings that help the designer to choose the most appropriate material. In this paper it is proposed not to use analytical models but to learn instead a rule-based system from experimental data. The presented methodology increases the level of post-processing interpretation accuracy of experimental data obtained during the evaluation of ice-phobic materials for rotorcraft applications. Key to the success of this model is a possibilistic representation of the uncertainty in the data, combined with a fuzzy fitness-based genetic algorithm that is capable to elicit a suitable set of rules on the basis of incomplete and imprecise information.

Original languageEnglish (US)
Pages (from-to)10212-10225
Number of pages14
JournalExpert Systems With Applications
Volume39
Issue number11
DOIs
StatePublished - Sep 1 2012

Fingerprint

Bond strength (materials)
Turbomachine blades
Ice
Rotors
Coatings
Knowledge based systems
Analytical models
Adhesion
Genetic algorithms
Processing

All Science Journal Classification (ASJC) codes

  • Engineering(all)
  • Computer Science Applications
  • Artificial Intelligence

Cite this

@article{9bef07c3a4ab4efea41c108a090c203c,
title = "Eliciting a human understandable model of ice adhesion strength for rotor blade leading edge materials from uncertain experimental data",
abstract = "The published ice adhesion performance data of novel {"}ice-phobic{"} coatings varies significantly, and there are not reliable models of the properties of the different coatings that help the designer to choose the most appropriate material. In this paper it is proposed not to use analytical models but to learn instead a rule-based system from experimental data. The presented methodology increases the level of post-processing interpretation accuracy of experimental data obtained during the evaluation of ice-phobic materials for rotorcraft applications. Key to the success of this model is a possibilistic representation of the uncertainty in the data, combined with a fuzzy fitness-based genetic algorithm that is capable to elicit a suitable set of rules on the basis of incomplete and imprecise information.",
author = "Palacios, {Ana M.} and Jose Palacios and Luciano S{\'a}nchez",
year = "2012",
month = "9",
day = "1",
doi = "10.1016/j.eswa.2012.02.155",
language = "English (US)",
volume = "39",
pages = "10212--10225",
journal = "Expert Systems with Applications",
issn = "0957-4174",
publisher = "Elsevier Limited",
number = "11",

}

Eliciting a human understandable model of ice adhesion strength for rotor blade leading edge materials from uncertain experimental data. / Palacios, Ana M.; Palacios, Jose; Sánchez, Luciano.

In: Expert Systems With Applications, Vol. 39, No. 11, 01.09.2012, p. 10212-10225.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Eliciting a human understandable model of ice adhesion strength for rotor blade leading edge materials from uncertain experimental data

AU - Palacios, Ana M.

AU - Palacios, Jose

AU - Sánchez, Luciano

PY - 2012/9/1

Y1 - 2012/9/1

N2 - The published ice adhesion performance data of novel "ice-phobic" coatings varies significantly, and there are not reliable models of the properties of the different coatings that help the designer to choose the most appropriate material. In this paper it is proposed not to use analytical models but to learn instead a rule-based system from experimental data. The presented methodology increases the level of post-processing interpretation accuracy of experimental data obtained during the evaluation of ice-phobic materials for rotorcraft applications. Key to the success of this model is a possibilistic representation of the uncertainty in the data, combined with a fuzzy fitness-based genetic algorithm that is capable to elicit a suitable set of rules on the basis of incomplete and imprecise information.

AB - The published ice adhesion performance data of novel "ice-phobic" coatings varies significantly, and there are not reliable models of the properties of the different coatings that help the designer to choose the most appropriate material. In this paper it is proposed not to use analytical models but to learn instead a rule-based system from experimental data. The presented methodology increases the level of post-processing interpretation accuracy of experimental data obtained during the evaluation of ice-phobic materials for rotorcraft applications. Key to the success of this model is a possibilistic representation of the uncertainty in the data, combined with a fuzzy fitness-based genetic algorithm that is capable to elicit a suitable set of rules on the basis of incomplete and imprecise information.

UR - http://www.scopus.com/inward/record.url?scp=84859428831&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859428831&partnerID=8YFLogxK

U2 - 10.1016/j.eswa.2012.02.155

DO - 10.1016/j.eswa.2012.02.155

M3 - Article

AN - SCOPUS:84859428831

VL - 39

SP - 10212

EP - 10225

JO - Expert Systems with Applications

JF - Expert Systems with Applications

SN - 0957-4174

IS - 11

ER -