Journal
COMBUSTION AND FLAME
Volume 191, Issue -, Pages 226-238Publisher
ELSEVIER SCIENCE INC
DOI: 10.1016/j.combustflame.2018.01.014
Keywords
Combustion data analysis; Complex chemistry post-processing; Stochastic embedding; Machine learning
Categories
Funding
- Swedish Energy Agency (Energimyndigheten)
Ask authors/readers for more resources
This paper introduces a novel post-processing technique for analyzing high dimensional combustion data. In this technique, t-Distributed Stochastic Neighbor Embedding (t-SNE) is used to reduce the dimensionality of the combustion data with no prior knowledge while preserving the similarity of the original data. Multidimensional combustion datasets are from premixed and non-premixed laminar flame simulations and measurements of a series of well documented piloted flames with inhomogeneous inlets. The resulting reduced manifold is visualized by scatter plots to reveal the global and local structure of the data (manual labeling). Unsupervised clustering algorithms are then utilized for post-processing the t-SNE manifold in order to develop an automatic labeling process. (C) 2018 The Combustion Institute. Published by Elsevier Inc. All rights reserved.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available