Maximization of energy absorption for a wave energy converter using the deep machine learning

Research output: Contribution to journalArticle

4 Citations (Scopus)

Abstract

A controller is usually used to maximize the energy absorption of wave energy converter. Despite the development of various control strategies, the practical implementation of wave energy control is still difficult since the control inputs are the future wave forces. In this work, the artificial intelligence technique is adopted to tackle this problem. A multi-layer artificial neural network is developed and trained by the deep machine learning algorithm to forecast the short-term wave forces. The model predictive control strategy is used to implement real-time latching control action to a heaving point-absorber. Simulation results show that the average energy absorption is increased substantially with the controller. Since the future wave forces are predicted, the controller is applicable to a full-scale wave energy converter in practice. Further analysis indicates that the prediction error has a negative effect on the control performance, leading to the reduction of energy absorption.

LanguageEnglish
Pages340-349
Number of pages10
JournalEnergy
Volume165
Issue numberA
Early online date18 Sep 2018
DOIs
Publication statusPublished - 15 Dec 2018

Fingerprint

Energy absorption
Learning systems
Controllers
Model predictive control
Real time control
Power control
Learning algorithms
Artificial intelligence
Neural networks

Keywords

  • wave energy converter
  • wave energy control
  • energy absorption
  • neural network
  • deep machine learning
  • wave force prediction

Cite this

@article{0f5ab84d8a474ae3a2146c6c8514b3bd,
title = "Maximization of energy absorption for a wave energy converter using the deep machine learning",
abstract = "A controller is usually used to maximize the energy absorption of wave energy converter. Despite the development of various control strategies, the practical implementation of wave energy control is still difficult since the control inputs are the future wave forces. In this work, the artificial intelligence technique is adopted to tackle this problem. A multi-layer artificial neural network is developed and trained by the deep machine learning algorithm to forecast the short-term wave forces. The model predictive control strategy is used to implement real-time latching control action to a heaving point-absorber. Simulation results show that the average energy absorption is increased substantially with the controller. Since the future wave forces are predicted, the controller is applicable to a full-scale wave energy converter in practice. Further analysis indicates that the prediction error has a negative effect on the control performance, leading to the reduction of energy absorption.",
keywords = "wave energy converter, wave energy control, energy absorption, neural network, deep machine learning, wave force prediction",
author = "Liang Li and Zhiming Yuan and Yan Gao",
year = "2018",
month = "12",
day = "15",
doi = "10.1016/j.energy.2018.09.093",
language = "English",
volume = "165",
pages = "340--349",
journal = "Energy",
issn = "0360-5442",
number = "A",

}

Maximization of energy absorption for a wave energy converter using the deep machine learning. / Li, Liang; Yuan, Zhiming; Gao, Yan.

In: Energy, Vol. 165, No. A, 15.12.2018, p. 340-349.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Maximization of energy absorption for a wave energy converter using the deep machine learning

AU - Li, Liang

AU - Yuan, Zhiming

AU - Gao, Yan

PY - 2018/12/15

Y1 - 2018/12/15

N2 - A controller is usually used to maximize the energy absorption of wave energy converter. Despite the development of various control strategies, the practical implementation of wave energy control is still difficult since the control inputs are the future wave forces. In this work, the artificial intelligence technique is adopted to tackle this problem. A multi-layer artificial neural network is developed and trained by the deep machine learning algorithm to forecast the short-term wave forces. The model predictive control strategy is used to implement real-time latching control action to a heaving point-absorber. Simulation results show that the average energy absorption is increased substantially with the controller. Since the future wave forces are predicted, the controller is applicable to a full-scale wave energy converter in practice. Further analysis indicates that the prediction error has a negative effect on the control performance, leading to the reduction of energy absorption.

AB - A controller is usually used to maximize the energy absorption of wave energy converter. Despite the development of various control strategies, the practical implementation of wave energy control is still difficult since the control inputs are the future wave forces. In this work, the artificial intelligence technique is adopted to tackle this problem. A multi-layer artificial neural network is developed and trained by the deep machine learning algorithm to forecast the short-term wave forces. The model predictive control strategy is used to implement real-time latching control action to a heaving point-absorber. Simulation results show that the average energy absorption is increased substantially with the controller. Since the future wave forces are predicted, the controller is applicable to a full-scale wave energy converter in practice. Further analysis indicates that the prediction error has a negative effect on the control performance, leading to the reduction of energy absorption.

KW - wave energy converter

KW - wave energy control

KW - energy absorption

KW - neural network

KW - deep machine learning

KW - wave force prediction

UR - https://www.sciencedirect.com/journal/energy

U2 - 10.1016/j.energy.2018.09.093

DO - 10.1016/j.energy.2018.09.093

M3 - Article

VL - 165

SP - 340

EP - 349

JO - Energy

T2 - Energy

JF - Energy

SN - 0360-5442

IS - A

ER -