go to top scroll for more

Reactive control of a wave energy converter using artificial neural networks

Citation Anderlini, E., Forehand, D.I.M., Bannon, E. and Abusara, M. Reactive control of a wave energy converter using artificial neural networks, International Journal of Marine Energy, 19: 207-220, 2017. https://doi.org/10.1016/j.ijome.2017.08.001.
Cite this using DataCite
Author(s) Anderlini, E., Forehand, D.I.M., Bannon, E. and Abusara, M.
Project partner(s) University of Edinburgh, Wave Energy Scotland, University of Exeter
Publisher International Journal of Marine Energy, 19: 207-220
DOI https://doi.org/10.1016/j.ijome.2017.08.001
Abstract A model-free algorithm is developed for the reactive control of a wave energy converter. Artificial neural networks are used to map the significant wave height, wave energy period, and the power take-off damping and stiffness coefficients to the mean absorbed power and maximum displacement. These values are computed during a time horizon spanning multiple wave cycles, with data being collected throughout the lifetime of the device so as to train the networks off-line every 20 time horizons. Initially, random values are selected for the controller coefficients to achieve sufficient exploration. Afterwards, a Multistart optimization is employed, which uses the neural networks within the cost function. The aim of the optimization is to maximise energy absorption, whilst limiting the displacement to prevent failures. Numerical simulations of a heaving point absorber are used to analyse thebehaviour of the algorithm in regular and irregular waves. Once training has occurred, the algorithm presents a similar power absorption to state-of-the-art reactive control. Furthermore, not only does dispensing with the model of the point-absorber dynamics remove its associated inaccuracies, but it also enables the controller to adapt to variations in the machine response caused by ageing.

  • Artificial neural networks are for the first time used for the reactive control of a WEC.
  • The neural network learns the optimal damping and stiffness coefficients.
  • A time averaged approach is adopted.
  • Considerations on practical issues are addressed.
  • The proposed control strategy is adaptive to changes in the system dynamics.
This work was partly funded via IDCORE, the Industrial Doctorate Centre for Offshore Renewable Energy, which trains research engineers whose work in conjunction with sponsoring companies aims to accelerate the deployment of offshore wind, wave and tidal-current technologies
Associated Project(s) ETI-MA2003: Industrial Doctorate Centre for Offshore Renewable Energy (IDCORE)
Associated Dataset(s) No associated datasets
Associated Publication(s)

A model to map levelised cost of energy for wave energy projects

An Integrated Data Management Approach for Offshore Wind Turbine Failure Root Cause Analysis

An investigation of the effects of wind-induced inclination on floating wind turbine dynamics: heave plate excursion

Application of an offshore wind farm layout optimization methodology at Middelgrunden wind farm

Characterisation of current and turbulence in the FloWave Ocean Energy Research Facility

Characterization of the tidal resource in Rathlin Sound

Comparison of Offshore Wind Farm Layout Optimization Using a Genetic Algorithm and a Particle Swarm Optimizer

Component reliability test approaches for marine renewable energy

Constraints Implementation in the Application of Reinforcement Learning to the Reactive Control of a Point Absorber

Control of a Realistic Wave Energy Converter Model Using Least-Squares Policy Iteration

Cost Reduction to Encourage Commercialisation of Marine in the UK

Cumulative impact assessment of tidal stream energy extraction in the Irish Sea

Design diagrams for wavelength discrepancy in tank testing with inconsistently scaled intermediate water depth

Development of a Condition Monitoring System for an Articulated Wave Energy Converter

Dynamic mooring simulation with Code(-)Aster with application to a floating wind turbine

ETI Insights Report - Wave Energy

Environmental interactions of tidal lagoons: A comparison of industry perspectives

Exploring Marine Energy Potential in the UK Using a Whole Systems Modelling Approach

Hybrid, Multi-Megawatt HVDC Transformer Topology Comparison for Future Offshore Wind Farms

Hydrodynamic analysis of a ducted, open centre tidal stream turbine using blade element momentum theory

Offshore wind farm electrical cable layout optimization

Offshore wind installation vessels - A comparative assessment for UK offshore rounds 1 and 2

Optimisation of Offshore Wind Farms Using a Genetic Algorithm

Quantifying uncertainty in acoustic measurements of tidal flows using a “Virtual” Doppler Current Profiler

Re-creation of site-specific multi-directional waves with non-collinear current

Reactive control of a two-body point absorber using reinforcement learning

Reliability and O & M sensitivity analysis as a consequence of site specific characteristics for wave energy converters

Reliability prediction for offshore renewable energy: Data driven insights

Resource characterization of sites in the vicinity of an island near a landmass

Review and application of Rainflow residue processing techniques for accurate fatigue damage estimation

Sensitivity analysis of offshore wind farm operation and maintenance cost and availability

Simulating Extreme Directional Wave Conditions

Testing Marine Renewable Energy Devices in an Advanced Multi-Directional Combined Wave-Current Environment

Testing the robustness of optimal access vessel fleet selection for operation and maintenance of offshore wind farms

The Industrial Doctorate Centre for Offshore Renewable Energy(IDCORE) - Case Studies

The SPAIR method: Isolating incident and reflected directional wave spectra in multidirectional wave basins

The effects of wind-induced inclination on the dynamics ofsemi-submersible floating wind turbines in the time domain

The power-capture of a nearshore, modular, flap-type wave energy converter in regular waves

UK offshore wind cost optimisation: top head mass (Presentation to All Energy, 10th May 2017)