Effective lifetime extension in the marine environment for tidal energy

Duration: 48 months (2019 - 2023)


Tidal turbines are designed to withstand the maximum loadings they can expect to experience during their operational lifetime, including peak loadings and fatigue. Fatigue loadings arise from turbulence and wave action. High peak and fatigue loadings, combined with uncertainty in loading modelling, leads to conservative designs; expensive, heavy devices; and resultant high transport and deployment costs (high CAPEX).

During operation, fatigue and peak loadings contribute to wear on a systems; this reduces turbines reliability, availability, efficiency and lifetime, and increases operational costs (OPEX). Improved control of turbines to reduce damaging loadings will improve device reliability and extend the lifetime of components, leading to reduced OPEX. In addition, improved control and a better understanding of the resource and the turbine response can be used to optimise performance to increase device yield.

Artificial Intelligence has already been successfully deployed in the mature wind industry to deliver significant commercial benefits by allowing turbines to adapt continually to changing conditions.


To use artificial intelligence to improve tidal turbines’ performance and accelerate their commercialisation.

Scientific and technical contents

  • Integration of state-of-the-art tidal and wind turbine technology.
  • Testing of a system prototype through experiments on the test bench and then towing and deployment at two tidal sites.
  • Testing on underwater and floating systems, with gearbox and direct drive turbines.
  • Socio-economic assessment of tidal turbine energy at regional, national and European levels.
  • Independent verification of project findings.
  • Environmental characterisation of deployment sites, and assessment and modelling of the potential environmental impacts of tidal turbines.


ELEMENT presentation video

ELEMENT public deliverables (PDF)

ELEMENT webinars

Partners and funding

This project was led by Nova Innovation.

The total project budget was €4,985K.

This project received funding from the European Research and Innovation Programme Horizon 2020.

Photo credit : Nova Innovation

Closed search overlay screen