Denoising and fuel spray droplet detection from light-scattered images using deep learning

Veeraraghava Raju Hasti; Dongyun Shin

doi:10.1016/j.egyai.2021.100130

Back

Denoising and fuel spray droplet detection from light-scattered images using deep learning

Journal article

Open access

Peer reviewed

Denoising and fuel spray droplet detection from light-scattered images using deep learning

Veeraraghava Raju Hasti and Dongyun Shin

Energy and AI, Vol.7, p.100130

01/2022

DOI: https://doi.org/10.1016/j.egyai.2021.100130

Handle:

https://hdl.handle.net/2376/118527

Appears in Aviation Sustainability Center (ASCENT)

Files and links (2)

pdf

29-j.egyai.2021.100130_pub3.18 MBDownload View

CC BY-NC-ND V4.0, Open Access

url

https://doi.org/10.1016/j.egyai.2021.100130View

Published (Version of record) Open

Abstract

Artificial intelligence

Convolutional Neural Networks

Deep learning

Droplet detection

Fuel spray

Image denoising

Mie scattering

ResNet

U-Net

A deep learning method proposed for denoising and droplets detection from light scatterd images.•Performance assessment of standard CNN, modified ResNet, and modified U-Net architectures.•Modified U-Net architecture outperformed for denoising light-scattered spray image.•Potential for real-time processing of the experimental data using the deep neural networks. A deep learning-based method for denoising and detecting the gas turbine engine spray droplets in the light-scattered image (Mie scattering) is proposed for the first time. A modified U-Net architecture is employed in the proposed method to denoise and regenerate the droplets. We have compared and validated the performance of the modified U-Net architecture with standard conventional neural networks (CNN) and modified ResNet architectures for denoising spray images from the Mie scattering experiment. The modified U-Net architecture performed better than the other two networks with significantly lower Mean Squared Error (MSE) on the validation dataset. The modified U-Net architecture also produced images with the highest Power Signal to Noise Ratio (PSNR) compared to the other two networks. This superior performance of the modified U-Net architecture is attributed to the encoder-decoder structure. During downsampling, as part of the encoder, only the most prominent features of the image are selectively retained by excluding any noise. This reconstruction of the noise-free features has produced a more accurate and better denoised image. The denoised images are then passed through a center predictor CNN to determine the location of the droplets with an average error of 1.4 pixels. The trained deep learning method for denoising and droplet center detection takes about 2.13 s on a single graphics processing unit (GPU). This study shows the promise for real-time processing of the experimental data using the well-optimized network. [Display omitted]

Metrics

2 File views/ downloads

12 Record Views

Details

Title: Denoising and fuel spray droplet detection from light-scattered images using deep learning
Creators: Veeraraghava Raju Hasti - School of Mechanical Engineering, Purdue University, West Lafayette, IN,47907 United States of America
Dongyun Shin - Purdue University West Lafayette
Publication Details: Energy and AI, Vol.7, p.100130
Academic Unit: Aviation Sustainability Center (ASCENT); Alternative Jet Fuel
Publisher: Elsevier Ltd
Grants: 13-C-AJFF-PU-011, Federal Aviation Administration (United States, Washington) - FAA
Identifiers: 99900898128301842
Language: English
Resource Type: Journal article