Posters
See the list of poster presenters at the Technology Workshop 2025 – and check out their work!
For more details on each poster, click on the poster titles to read the abstract.
PO023: Enhanced Anomaly Detection Methodology and Comprehensive Results for Wind Turbines Using Deep Learning and Statistics on CMS Vibration Data
Breno Carvalho, Performance Engineer, Casa dos Ventos
Abstract
A wind turbine generator is a complex rotating machine with multiple critical subsystems. Since wind turbines within the same wind farm exhibit similar behaviors, comparing the trend of a measured signal from one turbine to others in the same fleet is often effective. However, for vibration analysis, comparing the turbine's own historical data is crucial, as vibration patterns may vary based on each turbine's individual mechanical path. Vibration data analysis remains one of the most efficient methods for early failure detection, enabling proactive maintenance planning and minimizing downtime. In this work, a process was refined and expanded to monitor rotating subsystems by identifying anomalous trends based on the frequency domain analysis of vibration data from the Condition Monitoring System of the turbines ("CMS"). Autoencoder models were trained using different ranges of the frequency domain variables to flag outlier points, and a statistical moving average methodology was applied to identify diverging trends. These trends were prioritized through a linear regression model to ensure actionable insights. With this updated methodology, the relevant anomalous variables related to main issues on the components were flagged across multiple turbines, resulting in successful predictive detection of mechanical issues. Case studies revealed how the tool enabled the identification and resolution of potential failures, with clear reductions in downtime and optimized alignment of interventions with low wind resource periods, as forecasted by power models. Additionally, integration into a proprietary Python-based system enhanced the monitoring process, streamlining maintenance planning and execution. By incorporating this tool, the operational reliability of wind turbines improved significantly. The findings emphasize the value of combining data-driven anomaly detection with strategic maintenance planning to maximize energy-based availability, minimize operational disruptions, and enhance the overall efficiency of wind farms.
No recording available for this poster.
