Wind-AI: Wind Turbine Performance modelling utilising Deep Learning with LIDAR Validation

Find Similar History 37 Claim Ownership Request Data Change Add Favourite

Title
Wind-AI: Wind Turbine Performance modelling utilising Deep Learning with LIDAR Validation

CoPED ID
14d101b5-1097-4c70-9694-3dd27c4c910f

Status
Closed


Value
£644,332

Start Date
March 31, 2020

End Date
June 29, 2021

Description

More Like This


The UK has significant wind power resources and leads the world in offshore wind power generation. In 2018 the wind industry provided 17% (57.1 TWh) of the UK electricity supply \[UK Energy Statistics, 2018\] and is forecast to increase substantially over the coming decade \[National Grid FES\]. In order to ensure renewable energy can be deployed effectively to combat climate change and to ensure costs to consumers remain low the industry must continue to develop new technologies and operate more efficiently.

Currently wind turbines can incur significant hidden losses and must routinely be tested for performance loss. This reduces the amount of power they can generate and increases the costs of operation.

This project will develop a unique method for accurately predicting wind turbine output and hence enable the monitoring of performance losses for every wind turbine at a farm without the need to regularly perform performance testing. An accurate online performance monitoring technology would allow wind turbine operators to reduce the risk of structural blade failure and other common component failure (such as yaw or pitch actuation).

The project will provide robust evidence to the industry that validates the technology as a credible monitoring technology for the optimisation of site yield and reduction in periodic maintenance; reducing costs and increasing asset production. The technology will enhance the UK's position as leader in effective management and optimisation of wind assets, reducing the cost of energy for consumers and lowering the Levelised Cost of Energy (LCOE) by up to 2.7% (based on ORE Catapult modelling).

This project will provide the basis for a UK technology to be exported to the global wind industry, creating skilled jobs, and supporting further deployment and utilisation of wind farms to help combat climate change.

Pete Andrews PM_PER
Pete Andrews PM_PER

Subjects by relevance
  1. Wind energy
  2. Costs
  3. Renewable energy sources
  4. Wind power stations
  5. Wind
  6. Climate changes
  7. Wind farms
  8. Environmental effects
  9. Cost effectiveness
  10. Turbines

Extracted key phrases
  1. Wind Turbine Performance modelling
  2. Deep Learning
  3. Significant wind power resource
  4. Offshore wind power generation
  5. Global wind industry
  6. ORE Catapult modelling
  7. Wind turbine output
  8. Wind turbine operator
  9. LIDAR Validation
  10. Wind asset
  11. Wind farm
  12. UK technology
  13. UK electricity supply
  14. AI
  15. Credible monitoring technology

Related Pages

UKRI project entry

UK Project Locations