Flow Field Reconstruction and Prediction of Powder Fuel Transport Based on Scattering Images and Deep Learning

This paper presents the flow field reconstruction and prediction of powder fuel transport systems based on representative feature extraction from scattering images using deep learning techniques. A laboratory-built powder fuel supply system was used to conduct scattering spectroscopy experiments on...

Full description

Saved in:
Bibliographic Details
Main Authors: Hongyuan Du, Zhen Cao, Yingjie Song, Jiangbo Peng, Chaobo Yang, Xin Yu
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/15/4613
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849765967699116032
author Hongyuan Du
Zhen Cao
Yingjie Song
Jiangbo Peng
Chaobo Yang
Xin Yu
author_facet Hongyuan Du
Zhen Cao
Yingjie Song
Jiangbo Peng
Chaobo Yang
Xin Yu
author_sort Hongyuan Du
collection DOAJ
description This paper presents the flow field reconstruction and prediction of powder fuel transport systems based on representative feature extraction from scattering images using deep learning techniques. A laboratory-built powder fuel supply system was used to conduct scattering spectroscopy experiments on boron-based fuel under various flow rate conditions. Based on the acquired scattering images, a prediction and reconstruction method was developed using a deep network framework composed of a Stacked Autoencoder (SAE), a Backpropagation Neural Network (BP), and a Long Short-Term Memory (LSTM) model. The proposed framework enables accurate classification and prediction of the dynamic evolution of flow structures based on learned representations from scattering images. Experimental results show that the feature vectors extracted by the SAE form clearly separable clusters in the latent space, leading to high classification accuracy under varying flow conditions. In the prediction task, the feature vectors predicted by the LSTM exhibit strong agreement with ground truth, with average mean square error, mean absolute error, and r-square values of 0.0027, 0.0398, and 0.9897, respectively. Furthermore, the reconstructed images offer a visual representation of the changing flow field, validating the model’s effectiveness in structure-level recovery. These results suggest that the proposed method provides reliable support for future real-time prediction of powder fuel mass flow rates based on optical sensing and imaging techniques.
format Article
id doaj-art-a0532b23c20e4bfc9c350fc3d997a0d1
institution DOAJ
issn 1424-8220
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-a0532b23c20e4bfc9c350fc3d997a0d12025-08-20T03:04:43ZengMDPI AGSensors1424-82202025-07-012515461310.3390/s25154613Flow Field Reconstruction and Prediction of Powder Fuel Transport Based on Scattering Images and Deep LearningHongyuan Du0Zhen Cao1Yingjie Song2Jiangbo Peng3Chaobo Yang4Xin Yu5National Key Laboratory of Laser Spatial Information, Harbin Institute of Technology, Harbin 150001, ChinaNational Key Laboratory of Laser Spatial Information, Harbin Institute of Technology, Harbin 150001, ChinaNational Key Laboratory of Laser Spatial Information, Harbin Institute of Technology, Harbin 150001, ChinaNational Key Laboratory of Laser Spatial Information, Harbin Institute of Technology, Harbin 150001, ChinaNational Key Laboratory of Laser Spatial Information, Harbin Institute of Technology, Harbin 150001, ChinaNational Key Laboratory of Laser Spatial Information, Harbin Institute of Technology, Harbin 150001, ChinaThis paper presents the flow field reconstruction and prediction of powder fuel transport systems based on representative feature extraction from scattering images using deep learning techniques. A laboratory-built powder fuel supply system was used to conduct scattering spectroscopy experiments on boron-based fuel under various flow rate conditions. Based on the acquired scattering images, a prediction and reconstruction method was developed using a deep network framework composed of a Stacked Autoencoder (SAE), a Backpropagation Neural Network (BP), and a Long Short-Term Memory (LSTM) model. The proposed framework enables accurate classification and prediction of the dynamic evolution of flow structures based on learned representations from scattering images. Experimental results show that the feature vectors extracted by the SAE form clearly separable clusters in the latent space, leading to high classification accuracy under varying flow conditions. In the prediction task, the feature vectors predicted by the LSTM exhibit strong agreement with ground truth, with average mean square error, mean absolute error, and r-square values of 0.0027, 0.0398, and 0.9897, respectively. Furthermore, the reconstructed images offer a visual representation of the changing flow field, validating the model’s effectiveness in structure-level recovery. These results suggest that the proposed method provides reliable support for future real-time prediction of powder fuel mass flow rates based on optical sensing and imaging techniques.https://www.mdpi.com/1424-8220/25/15/4613scattering imagefeature extractiontemporal predictionstacked autoencoderLSTM network
spellingShingle Hongyuan Du
Zhen Cao
Yingjie Song
Jiangbo Peng
Chaobo Yang
Xin Yu
Flow Field Reconstruction and Prediction of Powder Fuel Transport Based on Scattering Images and Deep Learning
Sensors
scattering image
feature extraction
temporal prediction
stacked autoencoder
LSTM network
title Flow Field Reconstruction and Prediction of Powder Fuel Transport Based on Scattering Images and Deep Learning
title_full Flow Field Reconstruction and Prediction of Powder Fuel Transport Based on Scattering Images and Deep Learning
title_fullStr Flow Field Reconstruction and Prediction of Powder Fuel Transport Based on Scattering Images and Deep Learning
title_full_unstemmed Flow Field Reconstruction and Prediction of Powder Fuel Transport Based on Scattering Images and Deep Learning
title_short Flow Field Reconstruction and Prediction of Powder Fuel Transport Based on Scattering Images and Deep Learning
title_sort flow field reconstruction and prediction of powder fuel transport based on scattering images and deep learning
topic scattering image
feature extraction
temporal prediction
stacked autoencoder
LSTM network
url https://www.mdpi.com/1424-8220/25/15/4613
work_keys_str_mv AT hongyuandu flowfieldreconstructionandpredictionofpowderfueltransportbasedonscatteringimagesanddeeplearning
AT zhencao flowfieldreconstructionandpredictionofpowderfueltransportbasedonscatteringimagesanddeeplearning
AT yingjiesong flowfieldreconstructionandpredictionofpowderfueltransportbasedonscatteringimagesanddeeplearning
AT jiangbopeng flowfieldreconstructionandpredictionofpowderfueltransportbasedonscatteringimagesanddeeplearning
AT chaoboyang flowfieldreconstructionandpredictionofpowderfueltransportbasedonscatteringimagesanddeeplearning
AT xinyu flowfieldreconstructionandpredictionofpowderfueltransportbasedonscatteringimagesanddeeplearning