Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle

The accurate and rapid prediction of hydrodynamic characteristics greatly affects the monitoring of the manoeuvring performance of unidentified underwater vehicles. This work proposes a novel SEConv1D framework for the hydrodynamics prediction of the unidentified underwater vehicle. Firstly, a novel...

Full description

Saved in:
Bibliographic Details
Main Authors: Hou, Yuqing, Li, Hui, Chen, Hong, Shen, Shengnan, Duan, Fei, Wei, Wei, Wang, Jiayue, Huang, Yicang, Guan, Xiawei, Liao, Yinghao
Other Authors: School of Mechanical and Aerospace Engineering
Format: Article
Language:English
Published: 2023
Subjects:
Online Access:https://hdl.handle.net/10356/172033
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-172033
record_format dspace
spelling sg-ntu-dr.10356-1720332023-11-20T02:30:36Z Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle Hou, Yuqing Li, Hui Chen, Hong Shen, Shengnan Duan, Fei Wei, Wei Wang, Jiayue Huang, Yicang Guan, Xiawei Liao, Yinghao School of Mechanical and Aerospace Engineering Engineering::Mechanical engineering Computational Fluid Dynamics Resistance Coefficient The accurate and rapid prediction of hydrodynamic characteristics greatly affects the monitoring of the manoeuvring performance of unidentified underwater vehicles. This work proposes a novel SEConv1D framework for the hydrodynamics prediction of the unidentified underwater vehicle. Firstly, a novel framework integrated with one-dimensional convolutional neural networks (Conv1D) and a squeeze-and-excitation network (SENet) is proposed. Secondly, a hydrodynamic dataset based on computational fluid dynamics (CFD) is constructed and verified by experiments. Finally, the proposed framework is applied to predict the total resistance coefficient (Cd) of REMUS UUV and SUBOFF AFF-1. The predicted results agree well with experimental results, and the error of Cd between the experimental data and predicted results for REMUS UUV and SUBOFF AFF-1 is less than 3.39% and 1.97%, respectively, which proved that the proposed framework is effective. Compared with those of the most popular networks (i.e., support vector machine, multilayer perceptron, artificial neural network and Conv1D), the mean error of the Cd and friction resistance coefficient (Cf) between the CFD and predicted results is small at only 0.19%, depicting reductions of 91.5%, 85.9%, 66.7% and 40.6%, respectively. The per inference time of the proposed framework is only 0.164 s form the real-time prediction. This work was supported by the Fundamental Research Funds for the Central Universities (Grant No. 2042022gf0017 ), China; China Scholarship Council (Grant No. 202206270158 ), China. 2023-11-20T02:30:36Z 2023-11-20T02:30:36Z 2023 Journal Article Hou, Y., Li, H., Chen, H., Shen, S., Duan, F., Wei, W., Wang, J., Huang, Y., Guan, X. & Liao, Y. (2023). Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle. Ocean Engineering, 277, 114296-. https://dx.doi.org/10.1016/j.oceaneng.2023.114296 0029-8018 https://hdl.handle.net/10356/172033 10.1016/j.oceaneng.2023.114296 2-s2.0-85151488959 277 114296 en Ocean Engineering © 2023 Elsevier Ltd. All rights reserved.
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Mechanical engineering
Computational Fluid Dynamics
Resistance Coefficient
spellingShingle Engineering::Mechanical engineering
Computational Fluid Dynamics
Resistance Coefficient
Hou, Yuqing
Li, Hui
Chen, Hong
Shen, Shengnan
Duan, Fei
Wei, Wei
Wang, Jiayue
Huang, Yicang
Guan, Xiawei
Liao, Yinghao
Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle
description The accurate and rapid prediction of hydrodynamic characteristics greatly affects the monitoring of the manoeuvring performance of unidentified underwater vehicles. This work proposes a novel SEConv1D framework for the hydrodynamics prediction of the unidentified underwater vehicle. Firstly, a novel framework integrated with one-dimensional convolutional neural networks (Conv1D) and a squeeze-and-excitation network (SENet) is proposed. Secondly, a hydrodynamic dataset based on computational fluid dynamics (CFD) is constructed and verified by experiments. Finally, the proposed framework is applied to predict the total resistance coefficient (Cd) of REMUS UUV and SUBOFF AFF-1. The predicted results agree well with experimental results, and the error of Cd between the experimental data and predicted results for REMUS UUV and SUBOFF AFF-1 is less than 3.39% and 1.97%, respectively, which proved that the proposed framework is effective. Compared with those of the most popular networks (i.e., support vector machine, multilayer perceptron, artificial neural network and Conv1D), the mean error of the Cd and friction resistance coefficient (Cf) between the CFD and predicted results is small at only 0.19%, depicting reductions of 91.5%, 85.9%, 66.7% and 40.6%, respectively. The per inference time of the proposed framework is only 0.164 s form the real-time prediction.
author2 School of Mechanical and Aerospace Engineering
author_facet School of Mechanical and Aerospace Engineering
Hou, Yuqing
Li, Hui
Chen, Hong
Shen, Shengnan
Duan, Fei
Wei, Wei
Wang, Jiayue
Huang, Yicang
Guan, Xiawei
Liao, Yinghao
format Article
author Hou, Yuqing
Li, Hui
Chen, Hong
Shen, Shengnan
Duan, Fei
Wei, Wei
Wang, Jiayue
Huang, Yicang
Guan, Xiawei
Liao, Yinghao
author_sort Hou, Yuqing
title Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle
title_short Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle
title_full Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle
title_fullStr Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle
title_full_unstemmed Novel SEConv1D framework for real-time hydrodynamics prediction of the unidentified underwater vehicle
title_sort novel seconv1d framework for real-time hydrodynamics prediction of the unidentified underwater vehicle
publishDate 2023
url https://hdl.handle.net/10356/172033
_version_ 1783955553753497600