Unsupervised Data Analysis of Direct Numerical Simulation of a Turbulent Flame via Local Principal Component Analysis and Procustes Analysis

Giuseppe D’Alessio*, Antonio Attili, Alberto Cuoci, Heinz Pitsch, Alessandro Parente

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Direct Numerical Simulations (DNS) of reacting flows provide high-fidelity data for combustion model reduction and validation, although their interpretation is not always straightforward because of the massive amount of information and the data high-dimensionality. In this work, a completely unsupervised algorithm for data analysis is investigated on a data-set obtained from a temporally-evolving DNS simulation of a reacting n-heptane jet in air. The proposed algorithm combines the Local Principal Component Analysis (LPCA) clustering algorithm with a variables selection algorithm via dimensionality reduction and Procustes Analysis. Unlike other data-analysis algorithms, it requires null or limited user expertise as all of its steps are unsupervised and solely entrusted to mathematical objective functions, without any hyperparameter tuning step required.

Original languageEnglish
Title of host publication15th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2020
EditorsÁlvaro Herrero, Carlos Cambra, Daniel Urda, Javier Sedano, Héctor Quintián, Emilio Corchado
PublisherSpringer Science and Business Media Deutschland GmbH
Pages460-469
Number of pages10
ISBN (Electronic)978-3-030-57802-2
ISBN (Print)9783030578015
DOIs
Publication statusE-pub ahead of print - 29 Aug 2020
Event15th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2020 - Burgos, Spain
Duration: 16 Sep 202018 Sep 2020

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1268 AISC
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

Conference15th International Conference on Soft Computing Models in Industrial and Environmental Applications, SOCO 2020
Country/TerritorySpain
CityBurgos
Period16/09/2018/09/20

Keywords

  • Data analysis
  • Direct Numerical Simulation
  • Local variables selection
  • Principal Component Analysis
  • Turbulent flame

Fingerprint

Dive into the research topics of 'Unsupervised Data Analysis of Direct Numerical Simulation of a Turbulent Flame via Local Principal Component Analysis and Procustes Analysis'. Together they form a unique fingerprint.

Cite this