Business Sectors
Events
Contents
Smart O&M solution could revolutionise turbine performance monitoring
Artificial intelligence developed by UK-based Cognitive could help address an industrywide issue of wind turbine underperformance, helping to diagnose and fix problems, the ORE Catapult believes
Cognitive has joined forces with RWE and the Offshore Renewable Energy (ORE) Catapult to accelerate the commercialisation of its innovative Wind AI technology, to bring about a step-change in wind turbine performance monitoring.
A better understanding of true turbine performance in a windfarm could mean that maintenance ‘early warning signs’ are spotted sooner, saving millions of pounds in lost revenue.
“Cognitive’s Wind AI is a real-time, hyper-accurate solution and, in an industry first, proved that it can identify performance degradation with a less than 1% error,” said the ORE Catapult. “This quantum leap in real-time accuracy means Wind AI can provide a unique opportunity to optimise operations and maintenance practices.”
As part of the Innovate UK-funded project, ORE Catapult conducted a traditional power performance assessment (PPA) using LiDAR data provided by RWE. Wind AI was also deployed and tested by RWE on an offshore windfarm, where the technology created 2.4M machine learning models to monitor several hundred megawatts of offshore assets, using the data supplied by the instrumentation already installed on the turbines.
Cognitive co-founder and director of applied AI Christopher Fraser said, “Wind AITM does not use wind speed measurement as an input. Instead, it ‘learns’ the performance of each turbine against every other turbine under every conceivable set of conditions, and then uses that information to create algorithms to accurately determine the predicted and actual performance of each turbine at any given moment, thus highlighting any that are underperforming.”
An ORE Catapult cost analysis verified that Wind AI could reduce the levelised cost of energy and lead to an increase in annual energy production. It also concluded that Wind AI has the potential to predict component failures before they occur, enabling predictive maintenance to take place and potentially reducing overall corrective maintenance frequencies by 5%.
Mr Fraser continued, “Our estimates suggest that if every turbine in every windfarm in the UK was producing optimally, this would deliver the equivalent energy of two new windfarms, each the size of Greater Gabbard, just by using existing assets to their fullest.”
RWE production manager James Vause said, “At the Rampion offshore windfarm, our goal is to continuously improve our O&M efficiency. Wind AI supports us by identifying any underperformance in our assets very early on, which we can then evaluate and engineer solutions for, putting a stop to any potentially significant or cumulative impact on our production.”
ORE Catapult senior innovation manager Andrew MacDonald said Cognitive’s technology is providing a solution for one of the industry’s largest, unsolved challenges. “We are looking forward to continuing to work with Cognitive as they expand their AI solutions to further improve cost reductions in the offshore wind sector,” he said.
Following on from this project, Cognitive is working with ORE Catapult and SSE on another Innovate UK-funded project, AI Analyst, to further develop its predictive maintenance technology. This is an industrial research programme that builds upon a successful novel proof-of-concept technology that provides automatic modelling, early-fault detection, and diagnosis using transfer learning. The project will provide a practical solution for O&M requirements, delivering a genuinely unique offering which can be readily commercialised and exported globally to all industrial internet of things-connected assets.
Cognitive is already working with RWE and the Offshore Wind Growth Partnership as part of the WAVES project to develop its machine learning tool to improve vessel to turbine transfers that could save the industry £1.0M (US$1.3M) per installed GW every year.
Related to this Story
Events
Maritime Regulations Webinar Week
16 Dec 2025
GMT - ONLINE
Floating energy: successfully unlocking stranded gas using FLNGs and FSRUs
24 Feb 2026GMT - ONLINE
© 2024 Riviera Maritime Media Ltd.
