Multi-step predictions for generalized heave motion of wave compensating platform based on ELMAN neural network

Zhigang Zeng; Guohua Chen

doi:10.1109/IITAW.2009.109

Multi-step predictions for generalized heave motion of wave compensating platform based on ELMAN neural network

Zhigang Zeng, Guohua Chen

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

2 Citations (Scopus)

Abstract

BP algorithm is the typical supervised learning algorithm, so neural network cannot be trained on-line by it. For this reason, a new algorithm (TD-DBP), which was composed of temporal difference (TD) method and dynamic BP algorithm (DBP), was proposed to overcome the restriction. TD-DBP algorithm can make Elman network train on-line incrementally. The gradient descent momentum and adaptive learning rate TD-DBP algorithm can improve the training speed and stability of Elman network effectively. Using the collected real time data, the modified TD-DBP algorithm was able to realize direct multi-step predictions for generalized heave motion of wave compensating platform.

Original language	English
Title of host publication	3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009
Pages	460-463
Number of pages	4
DOIs	https://doi.org/10.1109/IITAW.2009.109
Publication status	Published - 1 Dec 2009
Externally published	Yes
Event	3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009 - NanChang, China Duration: 21 Nov 2009 → 22 Nov 2009

Conference

Conference	3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009
Country/Territory	China
City	NanChang
Period	21/11/09 → 22/11/09

Keywords

Generalized heave motion
Wave compensating Elman neural network

ASJC Scopus subject areas

Artificial Intelligence
Computer Networks and Communications
Computer Science Applications

More information

10.1109/IITAW.2009.109

Cite this

@inproceedings{9fae2783599843a694d79273b9c1e5e6,

title = "Multi-step predictions for generalized heave motion of wave compensating platform based on ELMAN neural network",

abstract = "BP algorithm is the typical supervised learning algorithm, so neural network cannot be trained on-line by it. For this reason, a new algorithm (TD-DBP), which was composed of temporal difference (TD) method and dynamic BP algorithm (DBP), was proposed to overcome the restriction. TD-DBP algorithm can make Elman network train on-line incrementally. The gradient descent momentum and adaptive learning rate TD-DBP algorithm can improve the training speed and stability of Elman network effectively. Using the collected real time data, the modified TD-DBP algorithm was able to realize direct multi-step predictions for generalized heave motion of wave compensating platform.",

keywords = "Generalized heave motion, Wave compensating Elman neural network",

author = "Zhigang Zeng and Guohua Chen",

year = "2009",

month = dec,

day = "1",

doi = "10.1109/IITAW.2009.109",

language = "English",

isbn = "9780769538600",

pages = "460--463",

booktitle = "3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009",

note = "3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009 ; Conference date: 21-11-2009 Through 22-11-2009",

}

Zeng, Z & Chen, G 2009, Multi-step predictions for generalized heave motion of wave compensating platform based on ELMAN neural network. in 3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009., 5419582, pp. 460-463, 3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009, NanChang, China, 21/11/09. https://doi.org/10.1109/IITAW.2009.109

Multi-step predictions for generalized heave motion of wave compensating platform based on ELMAN neural network. / Zeng, Zhigang; Chen, Guohua.
3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009. 2009. p. 460-463 5419582.

Research output: Chapter in book / Conference proceeding › Conference article published in proceeding or book › Academic research › peer-review

TY - GEN

T1 - Multi-step predictions for generalized heave motion of wave compensating platform based on ELMAN neural network

AU - Zeng, Zhigang

AU - Chen, Guohua

PY - 2009/12/1

Y1 - 2009/12/1

N2 - BP algorithm is the typical supervised learning algorithm, so neural network cannot be trained on-line by it. For this reason, a new algorithm (TD-DBP), which was composed of temporal difference (TD) method and dynamic BP algorithm (DBP), was proposed to overcome the restriction. TD-DBP algorithm can make Elman network train on-line incrementally. The gradient descent momentum and adaptive learning rate TD-DBP algorithm can improve the training speed and stability of Elman network effectively. Using the collected real time data, the modified TD-DBP algorithm was able to realize direct multi-step predictions for generalized heave motion of wave compensating platform.

AB - BP algorithm is the typical supervised learning algorithm, so neural network cannot be trained on-line by it. For this reason, a new algorithm (TD-DBP), which was composed of temporal difference (TD) method and dynamic BP algorithm (DBP), was proposed to overcome the restriction. TD-DBP algorithm can make Elman network train on-line incrementally. The gradient descent momentum and adaptive learning rate TD-DBP algorithm can improve the training speed and stability of Elman network effectively. Using the collected real time data, the modified TD-DBP algorithm was able to realize direct multi-step predictions for generalized heave motion of wave compensating platform.

KW - Generalized heave motion

KW - Wave compensating Elman neural network

UR - http://www.scopus.com/inward/record.url?scp=77951558590&partnerID=8YFLogxK

U2 - 10.1109/IITAW.2009.109

DO - 10.1109/IITAW.2009.109

M3 - Conference article published in proceeding or book

SN - 9780769538600

SP - 460

EP - 463

BT - 3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009

T2 - 3rd International Symposium on Intelligent Information Technology Application Workshops, IITAW 2009

Y2 - 21 November 2009 through 22 November 2009

ER -

Multi-step predictions for generalized heave motion of wave compensating platform based on ELMAN neural network

Abstract

Conference

Keywords

ASJC Scopus subject areas

More information

Other files and links

Fingerprint

Cite this