基于深度学习的舰船姿态预估的可视化研究

Zhanyang Chen; Zhenyu Wang; Haixin Cui; Sheng Li

doi:10.13245/j.hust.250504

基于深度学习的舰船姿态预估的可视化研究

Translated title of the contribution: Visualization research on prediction of ship attitude based on deep learning

Zhanyang Chen
, Zhenyu Wang
, Haixin Cui
, Sheng Li

School of Ocean Engineering, Harbin Institute of Technology Weihai
Dalian University of Technology
Shanghai Jiao Tong University
Marine Design & Research Institute of China

Research output: Contribution to journal › Article › peer-review

1 Scopus citations

Abstract

Aiming at the problem that the drastic change of motion attitude would greatly reduce the safety of carrier-based aircraft when the ship was sailing in the actual sea conditions，a composite prediction model was formed by introducing long short-term memory neural network (LSTM) and K-means clustering algorithm (K-Means) into the modular neural network (MNN)． First，the model was trained and the best parameters were saved based on the simulation values generated by Fortran software． Then，the parameters were invoked and the attitude was predicted based on the experimental data of ship model．The minimum predicted loss value could reach 1×10^-5 order of magnitude，and the maximum fitting coefficient could reach 0.98．

Translated title of the contribution	Visualization research on prediction of ship attitude based on deep learning
Original language	Chinese (Traditional)
Pages (from-to)	132-137
Number of pages	6
Journal	Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)
Volume	53
Issue number	4
DOIs	https://doi.org/10.13245/j.hust.250504
State	Published - Apr 2025
Externally published	Yes

Access to Document

10.13245/j.hust.250504

Cite this

@article{9639aacb7a0c4faa9c4d25f6c7f2e9b5,

title = "基于深度学习的舰船姿态预估的可视化研究",

abstract = "Aiming at the problem that the drastic change of motion attitude would greatly reduce the safety of carrier-based aircraft when the ship was sailing in the actual sea conditions，a composite prediction model was formed by introducing long short-term memory neural network (LSTM) and K-means clustering algorithm (K-Means) into the modular neural network (MNN)． First，the model was trained and the best parameters were saved based on the simulation values generated by Fortran software． Then，the parameters were invoked and the attitude was predicted based on the experimental data of ship model．The minimum predicted loss value could reach 1×10-5 order of magnitude，and the maximum fitting coefficient could reach 0.98．",

keywords = "PyQt third-party library, long short-term memory neural network, modular neural network, on-line computation, ship motion",

author = "Zhanyang Chen and Zhenyu Wang and Haixin Cui and Sheng Li",

year = "2025",

month = apr,

doi = "10.13245/j.hust.250504",

language = "繁体中文",

volume = "53",

pages = "132--137",

journal = "Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)",

issn = "1671-4512",

publisher = "Huazhong University of Science and Technology",

number = "4",

}

TY - JOUR

T1 - 基于深度学习的舰船姿态预估的可视化研究

AU - Chen, Zhanyang

AU - Wang, Zhenyu

AU - Cui, Haixin

AU - Li, Sheng

PY - 2025/4

Y1 - 2025/4

N2 - Aiming at the problem that the drastic change of motion attitude would greatly reduce the safety of carrier-based aircraft when the ship was sailing in the actual sea conditions，a composite prediction model was formed by introducing long short-term memory neural network (LSTM) and K-means clustering algorithm (K-Means) into the modular neural network (MNN)． First，the model was trained and the best parameters were saved based on the simulation values generated by Fortran software． Then，the parameters were invoked and the attitude was predicted based on the experimental data of ship model．The minimum predicted loss value could reach 1×10-5 order of magnitude，and the maximum fitting coefficient could reach 0.98．

AB - Aiming at the problem that the drastic change of motion attitude would greatly reduce the safety of carrier-based aircraft when the ship was sailing in the actual sea conditions，a composite prediction model was formed by introducing long short-term memory neural network (LSTM) and K-means clustering algorithm (K-Means) into the modular neural network (MNN)． First，the model was trained and the best parameters were saved based on the simulation values generated by Fortran software． Then，the parameters were invoked and the attitude was predicted based on the experimental data of ship model．The minimum predicted loss value could reach 1×10-5 order of magnitude，and the maximum fitting coefficient could reach 0.98．

KW - PyQt third-party library

KW - long short-term memory neural network

KW - modular neural network

KW - on-line computation

KW - ship motion

UR - https://www.scopus.com/pages/publications/105002760118

U2 - 10.13245/j.hust.250504

DO - 10.13245/j.hust.250504

M3 - 文章

AN - SCOPUS:105002760118

SN - 1671-4512

VL - 53

SP - 132

EP - 137

JO - Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)

JF - Huazhong Keji Daxue Xuebao (Ziran Kexue Ban)/Journal of Huazhong University of Science and Technology (Natural Science Edition)

IS - 4

ER -

基于深度学习的舰船姿态预估的可视化研究

Abstract

Access to Document

Other files and links

Fingerprint

Cite this