Across the onshore and offshore wind industry, unexpected turbine downtime and underperformance can see energy production – and therefore revenue – significantly lower than forecast. This can have a substantial effect on the financing of wind projects, particularly as large investors move away from fossil fuels and towards renewable energy. As such, improving turbine performance to maximise energy yield is vital to ensuring these investments remain profitable.
Clir uses AI to analyse wind turbine data. The software identifies causes of underperformance, from blade icing to suboptimal derating plans, and provides asset owners and operators with strategies to improve performance and thereby increase annual energy production by up to 5%.
Identifying the true causes of underperformance from turbine data can be extremely difficult using typical methods of analysis. By using AI to analyse turbine data, however, it is possible to generate a baseline of performance and recognise patterns that indicate not only when the turbine is performing sub-optimally, but why. This gives owners and operators the complete understanding of their asset, so they can address its underperformance.
