Ship Attitude Prediction Based on Input Delay Neural Network and Measurements of Gyroscopes

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

2 Citationer (Scopus)

Resumé

Due to the uncertainty and random nature of ocean waves, the accurate prediction of ship attitude is hard to be achieved, especially in high sea states. A ship attitude prediction method using Input Delay Neural Network (IDNN) is proposed in this paper. One of the advantages of this method is that it takes the measurements of Microelectromechanical Systems (MEMS) gyrosocpes, besides ship Euler angles, as the inputs of IDNN, which can greatly increase the prediction precision of ship attitude with little increase in system cost. The effectiveness of proposed method is validated through a data set sampled in a ship simulation hardware system. Moreover, the factors that affect the prediction performance are also explored through a set of experiments. The prediction method proposed can achieve high precision, that is, the root-mean-square prediction errors for roll, pitch and yaw, are 0.26 deg, 0.12 deg and 0.26 deg, respectively, when the prediction time is 2 sec. This precision is high enough for most attitude stabilization control systems.
OriginalsprogEngelsk
TitelProceedings of 2017 American Control Conference (ACC)
Antal sider7
ForlagIEEE Press
Publikationsdatomaj 2017
Sider4901-4907
ISBN (Elektronisk)978-1-5090-5992-8
DOI
StatusUdgivet - maj 2017
Begivenhed2017 American Control Conference: 2017 American Control Conference - Sheraton Seattle Hotel, Seattle, USA
Varighed: 24 maj 201726 maj 2017
http://acc2017.a2c2.org/
http://acc2017.a2c2.org/

Konference

Konference2017 American Control Conference
LokationSheraton Seattle Hotel,
LandUSA
BySeattle
Periode24/05/201726/05/2017
Internetadresse

Fingerprint

Gyroscopes
Ships
Neural networks
Water waves
MEMS
Stabilization
Hardware
Control systems
Costs

Citer dette

Wang, Yunlong ; N. Soltani, Mohsen ; Hussain, Dil muhammed Akbar. / Ship Attitude Prediction Based on Input Delay Neural Network and Measurements of Gyroscopes. Proceedings of 2017 American Control Conference (ACC). IEEE Press, 2017. s. 4901-4907
@inproceedings{76146c9b2d564730a3df6c9fa7be3fa7,
title = "Ship Attitude Prediction Based on Input Delay Neural Network and Measurements of Gyroscopes",
abstract = "Due to the uncertainty and random nature of ocean waves, the accurate prediction of ship attitude is hard to be achieved, especially in high sea states. A ship attitude prediction method using Input Delay Neural Network (IDNN) is proposed in this paper. One of the advantages of this method is that it takes the measurements of Microelectromechanical Systems (MEMS) gyrosocpes, besides ship Euler angles, as the inputs of IDNN, which can greatly increase the prediction precision of ship attitude with little increase in system cost. The effectiveness of proposed method is validated through a data set sampled in a ship simulation hardware system. Moreover, the factors that affect the prediction performance are also explored through a set of experiments. The prediction method proposed can achieve high precision, that is, the root-mean-square prediction errors for roll, pitch and yaw, are 0.26 deg, 0.12 deg and 0.26 deg, respectively, when the prediction time is 2 sec. This precision is high enough for most attitude stabilization control systems.",
author = "Yunlong Wang and {N. Soltani}, Mohsen and Hussain, {Dil muhammed Akbar}",
year = "2017",
month = "5",
doi = "10.23919/ACC.2017.7963714",
language = "English",
pages = "4901--4907",
booktitle = "Proceedings of 2017 American Control Conference (ACC)",
publisher = "IEEE Press",

}

Wang, Y, N. Soltani, M & Hussain, DMA 2017, Ship Attitude Prediction Based on Input Delay Neural Network and Measurements of Gyroscopes. i Proceedings of 2017 American Control Conference (ACC). IEEE Press, s. 4901-4907, 2017 American Control Conference, Seattle, USA, 24/05/2017. https://doi.org/10.23919/ACC.2017.7963714

Ship Attitude Prediction Based on Input Delay Neural Network and Measurements of Gyroscopes. / Wang, Yunlong; N. Soltani, Mohsen; Hussain, Dil muhammed Akbar.

Proceedings of 2017 American Control Conference (ACC). IEEE Press, 2017. s. 4901-4907.

Publikation: Bidrag til bog/antologi/rapport/konference proceedingKonferenceartikel i proceedingForskningpeer review

TY - GEN

T1 - Ship Attitude Prediction Based on Input Delay Neural Network and Measurements of Gyroscopes

AU - Wang, Yunlong

AU - N. Soltani, Mohsen

AU - Hussain, Dil muhammed Akbar

PY - 2017/5

Y1 - 2017/5

N2 - Due to the uncertainty and random nature of ocean waves, the accurate prediction of ship attitude is hard to be achieved, especially in high sea states. A ship attitude prediction method using Input Delay Neural Network (IDNN) is proposed in this paper. One of the advantages of this method is that it takes the measurements of Microelectromechanical Systems (MEMS) gyrosocpes, besides ship Euler angles, as the inputs of IDNN, which can greatly increase the prediction precision of ship attitude with little increase in system cost. The effectiveness of proposed method is validated through a data set sampled in a ship simulation hardware system. Moreover, the factors that affect the prediction performance are also explored through a set of experiments. The prediction method proposed can achieve high precision, that is, the root-mean-square prediction errors for roll, pitch and yaw, are 0.26 deg, 0.12 deg and 0.26 deg, respectively, when the prediction time is 2 sec. This precision is high enough for most attitude stabilization control systems.

AB - Due to the uncertainty and random nature of ocean waves, the accurate prediction of ship attitude is hard to be achieved, especially in high sea states. A ship attitude prediction method using Input Delay Neural Network (IDNN) is proposed in this paper. One of the advantages of this method is that it takes the measurements of Microelectromechanical Systems (MEMS) gyrosocpes, besides ship Euler angles, as the inputs of IDNN, which can greatly increase the prediction precision of ship attitude with little increase in system cost. The effectiveness of proposed method is validated through a data set sampled in a ship simulation hardware system. Moreover, the factors that affect the prediction performance are also explored through a set of experiments. The prediction method proposed can achieve high precision, that is, the root-mean-square prediction errors for roll, pitch and yaw, are 0.26 deg, 0.12 deg and 0.26 deg, respectively, when the prediction time is 2 sec. This precision is high enough for most attitude stabilization control systems.

U2 - 10.23919/ACC.2017.7963714

DO - 10.23919/ACC.2017.7963714

M3 - Article in proceeding

SP - 4901

EP - 4907

BT - Proceedings of 2017 American Control Conference (ACC)

PB - IEEE Press

ER -