Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learning
Two-phase flow may almost exist in every branch of the energy industry. For the corresponding engineering design, it is very essential and crucial to monitor flow patterns and their transitions accurately. With the high-speed development and success of deep learning based on convolutional neural net...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2022-12-01
|
Series: | Nuclear Engineering and Technology |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S1738573322003485 |
_version_ | 1811184391672561664 |
---|---|
author | Hong Xu Tao Tang |
author_facet | Hong Xu Tao Tang |
author_sort | Hong Xu |
collection | DOAJ |
description | Two-phase flow may almost exist in every branch of the energy industry. For the corresponding engineering design, it is very essential and crucial to monitor flow patterns and their transitions accurately. With the high-speed development and success of deep learning based on convolutional neural network (CNN), the study of flow pattern identification recently almost focused on this methodology. Additionally, the photographing technique has attractive implementation features as well, since it is normally considerably less expensive than other techniques. The development of such a two-phase flow pattern online monitoring system is the objective of this work, which seldom studied before. The ongoing preliminary engineering design (including hardware and software) of the system are introduced. The flow pattern identification method based on CNNs and transfer learning was discussed in detail. Several potential CNN candidates such as ALexNet, VggNet16 and ResNets were introduced and compared with each other based on a flow pattern dataset. According to the results, ResNet50 is the most promising CNN network for the system owing to its high precision, fast classification and strong robustness. This work can be a reference for the online monitoring system design in the energy system. |
first_indexed | 2024-04-11T13:12:29Z |
format | Article |
id | doaj.art-4f1c323bc4ce4e1ba3aa35a91116ec7a |
institution | Directory Open Access Journal |
issn | 1738-5733 |
language | English |
last_indexed | 2024-04-11T13:12:29Z |
publishDate | 2022-12-01 |
publisher | Elsevier |
record_format | Article |
series | Nuclear Engineering and Technology |
spelling | doaj.art-4f1c323bc4ce4e1ba3aa35a91116ec7a2022-12-22T04:22:33ZengElsevierNuclear Engineering and Technology1738-57332022-12-01541247514758Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learningHong Xu0Tao Tang1Sino-French Institute of Nuclear Engineering and Technology, Sun Yat-sen University, Zhuhai, China; Corresponding author.School of Microelectronics and Communication Engineering, Chongqing University, Chongqing, China; Energy Technology R&D Division, Jinyuyun Energy Technology Co., Ltd., Chongqing, ChinaTwo-phase flow may almost exist in every branch of the energy industry. For the corresponding engineering design, it is very essential and crucial to monitor flow patterns and their transitions accurately. With the high-speed development and success of deep learning based on convolutional neural network (CNN), the study of flow pattern identification recently almost focused on this methodology. Additionally, the photographing technique has attractive implementation features as well, since it is normally considerably less expensive than other techniques. The development of such a two-phase flow pattern online monitoring system is the objective of this work, which seldom studied before. The ongoing preliminary engineering design (including hardware and software) of the system are introduced. The flow pattern identification method based on CNNs and transfer learning was discussed in detail. Several potential CNN candidates such as ALexNet, VggNet16 and ResNets were introduced and compared with each other based on a flow pattern dataset. According to the results, ResNet50 is the most promising CNN network for the system owing to its high precision, fast classification and strong robustness. This work can be a reference for the online monitoring system design in the energy system.http://www.sciencedirect.com/science/article/pii/S1738573322003485Flow patternOnline monitoring systemArtificial neural network (ANN)Convolutional neural network (CNN)Transfer learningResNet50 |
spellingShingle | Hong Xu Tao Tang Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learning Nuclear Engineering and Technology Flow pattern Online monitoring system Artificial neural network (ANN) Convolutional neural network (CNN) Transfer learning ResNet50 |
title | Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learning |
title_full | Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learning |
title_fullStr | Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learning |
title_full_unstemmed | Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learning |
title_short | Two-phase flow pattern online monitoring system based on convolutional neural network and transfer learning |
title_sort | two phase flow pattern online monitoring system based on convolutional neural network and transfer learning |
topic | Flow pattern Online monitoring system Artificial neural network (ANN) Convolutional neural network (CNN) Transfer learning ResNet50 |
url | http://www.sciencedirect.com/science/article/pii/S1738573322003485 |
work_keys_str_mv | AT hongxu twophaseflowpatternonlinemonitoringsystembasedonconvolutionalneuralnetworkandtransferlearning AT taotang twophaseflowpatternonlinemonitoringsystembasedonconvolutionalneuralnetworkandtransferlearning |