Detect the undetected with Clir’s new feature

2 Min Read

Using peer-to-peer trending, Clir users can now detect changes in data that lead to false analysis.

Clir Renewables has just announced P2P, a new feature for their Data Exploration Environment. Clir’s Data Exploration Environment, Clir Explore, is a unique tool in the renewables space. Using informative data visualizations and pre-populated data variables Clir Explore allows users to view and manipulate streamlined data sets which narrow in on specific performance issues. Clir Explore makes complex analysis simple by providing the specific variables to use when identifying different kinds of anomalous turbine behavior and is comprised of 12 different features each manipulating data differently to identify underperformance. This new feature, P2P, adds to the products suite of capabilities by enabling peer-to-peer trending analysis for turbines. 

Comparing concurrent turbine data is a vital part of a complete wind farm analysis. Clir’s peer-to-peer trending tool makes it easy to detect anomalous behavior and trending over time. For example, it allows our clients to spot anemometer drift and other sensors needing to be recalibrated, as well as subtle differences in power or pitch curve behavior. The P2P tool uses concurrent data, and it’s possible to filter out any non-full performance data. P2P gives analysts a tool to analyze turbine operating data between two selected turbines and was developed to solve the problem of detecting degrading turbine components, to clean up data, and enable better analysis.

The P2P tool allows the user to compare any two turbines in their wind farm and select the variable they want to compare. Among the variables available are power, wind direction, wind speed, blade pitch angle, and generator speed. The results can be colored on time period, nacelle position, or wind directions, which means the user can easily identify if patterns are time depended or direction dependent. The scatter plot and overlaying linear regression, makes it easy to spot outliers. 

Detecting anomalous turbine behavior is easier and faster than before with the P2P tool. “Before our clients started using Clir they didn’t have the data model or tools to get their hands around numerous wind farms. Not only do you need to know what kind of underperformance you are looking for, but you also need to know which variables to use to complete the analysis. With our workbooks, users can use Clir’s catalogue of visualisations and create their own visualizations utilising the Clir data model.” says Gareth Brown, CEO of Clir Renewables.