Performance of artificial neural network in prediction of heave displacement for non-buoyant type wave energy converter

Non-buoyant type of wave energy converter is an innovative method to harness ocean waves. In this paper the assessment of heave displacement for non-buoyant type wave energy converter is investigated by means of artificial neural networks (ANNs). The significant water wave amplitude and time period are chosen as a basis for the heave displacement, and thus these two parameters are considered as effective parameters for the development of ANN model. For this purpose a wide range of dataset of about 4500 data (water wave amplitude and time period (seconds) is considered as input parameter and corresponding heave amplitude of non-buoyant body is considered as output parameter) is obtained from an extensive laboratory campaign and is used to develop an ANN. The developed model has the capability of predicting the position of non-buoyant five seconds ahead of actual heave displacement. The AI technique chosen for the model is a nonlinear autoregressive network with exogenous inputs (NARX) trained with the Levenberg-Marquardt algorithm. A comparative study of 30 different architectures is carried out and finally the best performing ANN architecture is selected and successfully validated based on the measured data.

[1]  Johannes Falnes,et al.  A REVIEW OF WAVE-ENERGY EXTRACTION , 2007 .

[2]  G. S. Dwarakish,et al.  Prediction of Tides Using Neural Networks at Karwar, West Coast of India , 2013 .

[3]  Juan R. Rabuñal,et al.  Performance of artificial neural networks in nearshore wave power prediction , 2014, Appl. Soft Comput..

[4]  J. M. Caswell.  A Nonlinear Autoregressive Approach to Statistical Prediction of Disturbance Storm Time Geomagnetic Fluctuations Using Solar Data , 2014 .

[5]  J. Vimala,et al.  Real Time wave forecasting using artificial neural network with varying input parameter , 2014 .

[6]  António F.O. Falcão,et al.  Wave energy utilization: A review of the technologies , 2010 .

[7]  Barbara Papli,et al.  Application of Neural Networks to the Prediction of Significant Wave Height at Selected Locations on the Baltic Sea , 2006 .

[8]  Soteris A. Kalogirou,et al.  Applications of artificial neural networks in energy systems , 1999 .

[9]  Belinda A. Batten,et al.  Use of artificial neural networks for real-time prediction of heave displacement in ocean buoys , 2014, 2014 International Conference on Renewable Energy Research and Application (ICRERA).

[10]  Gregorio Iglesias,et al.  Artificial intelligence applied to floating boom behavior under waves and currents , 2010 .

[11]  Mats Leijon,et al.  Offshore wave power measurements—A review , 2011 .

[12]  Kyoung Kwan Ahn,et al.  An innovative design of wave energy converter , 2012 .

[13]  Srinivasan Chandrasekaran,et al.  Laboratory experiment on using non-floating body to generate electrical energy from water waves , 2012 .

[14]  Amin Al-Habaibeh,et al.  An innovative approach for energy generation from waves , 2010 .