Real-time control of WECs based on NAR, NARX and LSTM artificial neural network

Tuo Li; Ming Zhang; Shuang-Rui Yu; Zhi-Ming Yuan

Real-time control of WECs based on NAR, NARX and LSTM artificial neural network

Tuo Li, Ming Zhang, Shuang-Rui Yu, Zhi-Ming Yuan

Naval Architecture, Ocean And Marine Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

1 Citation (Scopus)

24 Downloads (Pure)

Abstract

In this study, we aim to improve WECs’ performance for maximizing energy absorption through a sub-optimal method of phase control by latching is applied to the device. The forecasting of future wave force is required for the optimal control command deducted. An artificial neural network, namely LSTM (Long Short-Term Memory) is proposed to accurately predict the short-term wave force. The hydrodynamic properties of a point absorber is analyzed based on the 3D potential flow theory in frequency-domain. Cummin’s equation and a 4th-order state-space model are used to efficiently represent the hydrodynamic behavior of the WEC under irregular waves in time-domain. The Nonlinear Autoregressive artificial neural network(NAR-ANN) and NARx network are used to verify the method proposed in this paper. The simulation results show that the mean square error value, root mean square error value and R² value based on the LSTM prediction model are better than those of the NAR prediction model. The prediction performance of LSTM is more suitable for processing the time series.

Original language	English
Title of host publication	The Proceedings of The Thirty-second (2022) International Ocean and Polar Engineering Conference
Editors	Jin S. Chung, Igor Buzin, Hiroyasu Kawai, Hua Liu, Ivana Kubat, Bor-Feng Peng, Ali Reza, Venkatachalam Sriram, Suak Ho Van, Decheng Wan, Satoru Yamaguchi, Shiqiang Yan
Place of Publication	Cupertino, CA
Publisher	International Society of Offshore and Polar Engineers
Pages	359-367
Number of pages	9
ISBN (Print)	9781880653814
Publication status	Published - 5 Jun 2022
Event	The Thirty-second (2022) International Ocean and Polar Engineering Conference - Shanghai, China Duration: 5 Jun 2022 → 10 Jun 2022

Publication series

Name	The Proceedings of the International Ocean and Polar Engineering Conference
ISSN (Print)	1098-6189

Conference

Conference	The Thirty-second (2022) International Ocean and Polar Engineering Conference
Country/Territory	China
City	Shanghai
Period	5/06/22 → 10/06/22

Keywords

wave force prediction
latching control
wave energy converter (WEC)
LSTM
NAR-ANN
NARx

Access to Document

Li-etal-ISOPE-2022-Real-time-control-of-WECs-based-on-NAR-NARX-and-LSTM-artificial-neural-networkAccepted author manuscript, 1.25 MBLicence: Strath_1

Cite this

Li, T., Zhang, M., Yu, S.-R., & Yuan, Z.-M. (2022). Real-time control of WECs based on NAR, NARX and LSTM artificial neural network. In J. S. Chung, I. Buzin, H. Kawai, H. Liu, I. Kubat, B.-F. Peng, A. Reza, V. Sriram, S. H. Van, D. Wan, S. Yamaguchi, & S. Yan (Eds.), The Proceedings of The Thirty-second (2022) International Ocean and Polar Engineering Conference (pp. 359-367). (The Proceedings of the International Ocean and Polar Engineering Conference). International Society of Offshore and Polar Engineers.

Li, Tuo ; Zhang, Ming ; Yu, Shuang-Rui et al. / Real-time control of WECs based on NAR, NARX and LSTM artificial neural network. The Proceedings of The Thirty-second (2022) International Ocean and Polar Engineering Conference. editor / Jin S. Chung ; Igor Buzin ; Hiroyasu Kawai ; Hua Liu ; Ivana Kubat ; Bor-Feng Peng ; Ali Reza ; Venkatachalam Sriram ; Suak Ho Van ; Decheng Wan ; Satoru Yamaguchi ; Shiqiang Yan. Cupertino, CA : International Society of Offshore and Polar Engineers, 2022. pp. 359-367 (The Proceedings of the International Ocean and Polar Engineering Conference).

@inproceedings{3aeeb5b2c8b54ece8bd0ef4ae8a8951c,

title = "Real-time control of WECs based on NAR, NARX and LSTM artificial neural network",

abstract = "In this study, we aim to improve WECs{\textquoteright} performance for maximizing energy absorption through a sub-optimal method of phase control by latching is applied to the device. The forecasting of future wave force is required for the optimal control command deducted. An artificial neural network, namely LSTM (Long Short-Term Memory) is proposed to accurately predict the short-term wave force. The hydrodynamic properties of a point absorber is analyzed based on the 3D potential flow theory in frequency-domain. Cummin{\textquoteright}s equation and a 4th-order state-space model are used to efficiently represent the hydrodynamic behavior of the WEC under irregular waves in time-domain. The Nonlinear Autoregressive artificial neural network(NAR-ANN) and NARx network are used to verify the method proposed in this paper. The simulation results show that the mean square error value, root mean square error value and R2 value based on the LSTM prediction model are better than those of the NAR prediction model. The prediction performance of LSTM is more suitable for processing the time series.",

keywords = "wave force prediction, latching control, wave energy converter (WEC), LSTM, NAR-ANN, NARx",

author = "Tuo Li and Ming Zhang and Shuang-Rui Yu and Zhi-Ming Yuan",

year = "2022",

month = jun,

day = "5",

language = "English",

isbn = "9781880653814",

series = "The Proceedings of the International Ocean and Polar Engineering Conference",

publisher = "International Society of Offshore and Polar Engineers",

pages = "359--367",

editor = "Chung, {Jin S.} and Igor Buzin and Hiroyasu Kawai and Hua Liu and Ivana Kubat and Bor-Feng Peng and Ali Reza and Venkatachalam Sriram and Van, {Suak Ho} and Decheng Wan and Satoru Yamaguchi and Shiqiang Yan",

booktitle = "The Proceedings of The Thirty-second (2022) International Ocean and Polar Engineering Conference",

address = "United States",

note = "The Thirty-second (2022) International Ocean and Polar Engineering Conference ; Conference date: 05-06-2022 Through 10-06-2022",

}

Li, T, Zhang, M, Yu, S-R & Yuan, Z-M 2022, Real-time control of WECs based on NAR, NARX and LSTM artificial neural network. in JS Chung, I Buzin, H Kawai, H Liu, I Kubat, B-F Peng, A Reza, V Sriram, SH Van, D Wan, S Yamaguchi & S Yan (eds), The Proceedings of The Thirty-second (2022) International Ocean and Polar Engineering Conference. The Proceedings of the International Ocean and Polar Engineering Conference, International Society of Offshore and Polar Engineers, Cupertino, CA, pp. 359-367, The Thirty-second (2022) International Ocean and Polar Engineering Conference, Shanghai, China, 5/06/22.

Real-time control of WECs based on NAR, NARX and LSTM artificial neural network. / Li, Tuo; Zhang, Ming; Yu, Shuang-Rui et al.
The Proceedings of The Thirty-second (2022) International Ocean and Polar Engineering Conference. ed. / Jin S. Chung; Igor Buzin; Hiroyasu Kawai; Hua Liu; Ivana Kubat; Bor-Feng Peng; Ali Reza; Venkatachalam Sriram; Suak Ho Van; Decheng Wan; Satoru Yamaguchi; Shiqiang Yan. Cupertino, CA: International Society of Offshore and Polar Engineers, 2022. p. 359-367 (The Proceedings of the International Ocean and Polar Engineering Conference).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Real-time control of WECs based on NAR, NARX and LSTM artificial neural network

AU - Li, Tuo

AU - Zhang, Ming

AU - Yu, Shuang-Rui

AU - Yuan, Zhi-Ming

PY - 2022/6/5

Y1 - 2022/6/5

N2 - In this study, we aim to improve WECs’ performance for maximizing energy absorption through a sub-optimal method of phase control by latching is applied to the device. The forecasting of future wave force is required for the optimal control command deducted. An artificial neural network, namely LSTM (Long Short-Term Memory) is proposed to accurately predict the short-term wave force. The hydrodynamic properties of a point absorber is analyzed based on the 3D potential flow theory in frequency-domain. Cummin’s equation and a 4th-order state-space model are used to efficiently represent the hydrodynamic behavior of the WEC under irregular waves in time-domain. The Nonlinear Autoregressive artificial neural network(NAR-ANN) and NARx network are used to verify the method proposed in this paper. The simulation results show that the mean square error value, root mean square error value and R2 value based on the LSTM prediction model are better than those of the NAR prediction model. The prediction performance of LSTM is more suitable for processing the time series.

AB - In this study, we aim to improve WECs’ performance for maximizing energy absorption through a sub-optimal method of phase control by latching is applied to the device. The forecasting of future wave force is required for the optimal control command deducted. An artificial neural network, namely LSTM (Long Short-Term Memory) is proposed to accurately predict the short-term wave force. The hydrodynamic properties of a point absorber is analyzed based on the 3D potential flow theory in frequency-domain. Cummin’s equation and a 4th-order state-space model are used to efficiently represent the hydrodynamic behavior of the WEC under irregular waves in time-domain. The Nonlinear Autoregressive artificial neural network(NAR-ANN) and NARx network are used to verify the method proposed in this paper. The simulation results show that the mean square error value, root mean square error value and R2 value based on the LSTM prediction model are better than those of the NAR prediction model. The prediction performance of LSTM is more suitable for processing the time series.

KW - wave force prediction

KW - latching control

KW - wave energy converter (WEC)

KW - LSTM

KW - NAR-ANN

KW - NARx

UR - https://onepetro.org/ISOPEIOPEC/proceedings/ISOPE22/All-ISOPE22/ISOPE-I-22-053/493677

M3 - Conference contribution book

SN - 9781880653814

T3 - The Proceedings of the International Ocean and Polar Engineering Conference

SP - 359

EP - 367

BT - The Proceedings of The Thirty-second (2022) International Ocean and Polar Engineering Conference

A2 - Chung, Jin S.

A2 - Buzin, Igor

A2 - Kawai, Hiroyasu

A2 - Liu, Hua

A2 - Kubat, Ivana

A2 - Peng, Bor-Feng

A2 - Reza, Ali

A2 - Sriram, Venkatachalam

A2 - Van, Suak Ho

A2 - Wan, Decheng

A2 - Yamaguchi, Satoru

A2 - Yan, Shiqiang

PB - International Society of Offshore and Polar Engineers

CY - Cupertino, CA

T2 - The Thirty-second (2022) International Ocean and Polar Engineering Conference

Y2 - 5 June 2022 through 10 June 2022

ER -

Li T, Zhang M, Yu SR , Yuan ZM. Real-time control of WECs based on NAR, NARX and LSTM artificial neural network. In Chung JS, Buzin I, Kawai H, Liu H, Kubat I, Peng BF, Reza A, Sriram V, Van SH, Wan D, Yamaguchi S, Yan S, editors, The Proceedings of The Thirty-second (2022) International Ocean and Polar Engineering Conference. Cupertino, CA: International Society of Offshore and Polar Engineers. 2022. p. 359-367. (The Proceedings of the International Ocean and Polar Engineering Conference).

Real-time control of WECs based on NAR, NARX and LSTM artificial neural network

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this