Applying ensemble neural networks to analyze industrial maintenance: Influence of Saharan dust transport on gas turbine axial compressor fouling

  1. D. Gonzalez Calvo 1
  2. R.M. Aguilar 1
  3. C. Criado Hernandez 1
  4. Luis Antonio González Mendoza 1
  1. 1 Universidad de La Laguna

    Universidad de La Laguna

    San Cristobal de La Laguna, España


Inteligencia artificial: Revista Iberoamericana de Inteligencia Artificial

ISSN: 1137-3601

Year of publication: 2021

Volume: 24

Issue: 68

Pages: 53-71

Type: Article

DOI: 10.4114/INTARTIF.VOL24ISS68PP53-71 DIALNET GOOGLE SCHOLAR lock_openOpen access editor

More publications in: Inteligencia artificial: Revista Iberoamericana de Inteligencia Artificial


Cited by

  • Scopus Cited by: 0 (03-05-2023)
  • Web of Science Cited by: 0 (26-05-2023)
  • Dimensions Cited by: 0 (18-04-2023)

SCImago Journal Rank

  • Year 2021
  • SJR Journal Impact: 0.247
  • Best Quartile: Q4
  • Area: Artificial Intelligence Quartile: Q4 Rank in area: 198/253
  • Area: Software Quartile: Q4 Rank in area: 336/404

Scopus CiteScore

  • Year 2021
  • CiteScore of the Journal : 1.5
  • Area: Artificial Intelligence Percentile: 22
  • Area: Software Percentile: 20

Journal Citation Indicator (JCI)

  • Year 2021
  • Journal Citation Indicator (JCI): 0.13
  • Best Quartile: Q4
  • Area: COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Quartile: Q4 Rank in area: 177/190


(Data updated as of 18-04-2023)
  • Total citations: 0
  • Recent citations: 0
  • Field Citation Ratio (FCR): 0.0


The planning of industrial maintenance associated with the production of electricity is vital, as it yields a current and future snapshot of an industrial component in order to optimize the human, technical and economic resources of the installation. This study focuses on the degradation due to fouling of a gas turbine in the Canary Islands, and analyzes fouling levels over time based on the operating regime and local meteorological variables. In particular, we study the relationship between degradation and the suspended dust that originates in the Sahara Desert. To this end, we use a computational procedure that relies on a set of artificial neural networks to build an ensemble, using a cross-validated committees approach, to yield the compressor efficiency. The use of trained models makes it possible to know in advance how the local fouling of an industrial rotating component will evolve, which is useful for maintenance planning.