Canadian technology outfit Clir Renewables has developed a software product feature able to detect underperforming wind turbines.
Using layered machine learning the company has created an application that works along with other algorithms in the software to analyse turbine data and classify the information based on the reason for underperformance.
The new feature creates a synthetic event when turbine power output is well below the historical mean for that wind speed.
This information helps identify a turbine’s ongoing issues, that are not indicated by supervisory control and data acquisition data, or inflow conditions under which the turbine does not perform well. The data also provides duration and lost energy associated with the underperformance.
The application also highlights a hardware or software configuration change that reduces power performance and is able to provide a clean set of data from which the unknown causes can be deduced, and corrective actions created.
Alternatively, if the cause is still unidentified, the owner can approach the manufacturer with the cleaned data looking for answers and solutions, said the software company.
Clir Renewables data scientist Selena Farris said: “With noise filled datasets the uncertainty of any conclusions that can be drawn on causes of underperformance will increase significantly, and in a lot of cases, issues can be completely masked by the noise.
“Utilising the advances in machine learning, a well-structured data model and deep domain expertise, Clir software provides a tool to reduce this uncertainty, generating actionable insights for owners to increase performance and protect their assets from faults and failures.”