KIT | KIT-Bibliothek | Impressum | Datenschutz

Towards DeepSpray: Using Convolutional Neural Network to post-process Shadowgraphy Images of Liquid Atomization

Chaussonnet, Geoffroy; Lieber, Christian; Yikang, Yan; Gu, Wenda; Bartschat, Andreas; Reischl, Markus; Koch, Rainer; Mikut, Ralf; Bauer, Hans-Jörg

Abstract:
This technical report investigates the potential of Convolutional Neural Networks to post-process images from primary atomization. Three tasks are investigated. First, the detection and segmentation of liquid droplets in degraded optical conditions. Second, the detection of overlapping ellipses and the prediction of their geometrical characteristics. This task corresponds to extrapolate the hidden contour of an ellipse with reduced visual information. Third, several features of the liquid surface during primary breakup (ligaments, bags, rims) are manually annotated on 15 experimental images. The detector is trained on this minimal database using simple data augmentation and then applied to other images from numerical simulation and from other experiment.
In these three tasks, models from the literature based on Convolutional Neural Networks showed very promising results, thus demonstrating the high potential of Deep Learning to post-process liquid atomization. The next step is to embed these models into a unified framework DeepSpray.

Open Access Logo


Volltext (Version 3) §
DOI: 10.5445/IR/1000097897/v3
Veröffentlicht am 11.10.2019
Volltext (Version 2) §
DOI: 10.5445/IR/1000097897/v2
Veröffentlicht am 09.09.2019
Volltext (Version 1) §
DOI: 10.5445/IR/1000097897
Veröffentlicht am 03.09.2019
Cover der Publikation
Zugehörige Institution(en) am KIT Institut für Thermische Strömungsmaschinen (ITS)
Institut für Automation und angewandte Informatik (IAI)
Publikationstyp Forschungsbericht/Preprint
Publikationsjahr 2019
Sprache Englisch
Identifikator KITopen-ID: 1000097897
HGF-Programm 34.14.02 (POF III, LK 01)
Vergasung
Umfang 22 S.
Schlagwörter deep learning, liquid atomization
KIT – Die Forschungsuniversität in der Helmholtz-Gemeinschaft
KITopen Landing Page