Alexis Lebranchu

The relationship between wind speed and the power produced by a wind turbine is expressed by its power curve. Power curves are commonly used to monitor the production performance of a wind turbine by asset managers to ensure optimal production. They can also be used as a tool to detect faults occurring on a wind turbine when the fault causes a decrease in performance. However, the wide dispersion of data generally observed around the reference power curve limits the detection performance of power curve-based techniques. Fault indicators, such as residuals, which measure the difference between the actual power produced and the expected power, are largely affected by this dispersion. To increase the detection performance of power-based fault detection methods, a hybrid solution of mono-multi-turbine residual generation is proposed in this paper to reduce the influence of the power curve dispersion. A new simulation framework, modeling the effect of wind nature (turbulent/laminar) on the wind turbine performance, is also proposed. This allows us to evaluate and compare the performances of two fault detection methods in their multi-turbine implementation. The results show that the application of a multi-turbine approach to a basic residual generation method significantly improves its detection performance and makes it as efficient as a more complex method.

Wind turbines being one of the fastest growing sources of renewable energy have garnered significant scientific interest for the monitoring and fault analysis using SCADA data. Various monitoring approaches using power curves, i.e. industry wide characteristic curves expressing produced power as a function of wind speed, have been proposed in the literature. However, an objective comparison of the performance of these methods is difficult. The difficulty comes from (i) the variability in operational and environmental conditions taken into account; (ii) the nature, size and type of data-sets used and (iii) the type and signatures of faults considered for validation. To solve this problem, an approach with a twofold contribution is proposed in this work: 1) an original procedure to generate realistic and controlled simulations of 10 minutes SCADA data, simulating situations when the wind turbine is operating in normal or faulty conditions, is presented; 2) a framework for objective performance assessment of the fault detection methods, based on the proposed controlled and standardized simulation scheme is presented. Objective performance evaluation metrics, such as detection probability and false alarm rates are computed and represented as characteristic Receiver Operating Curves (ROC). The proposed simulation approach is shown to provide a useful global framework for objective performance analysis. A number of realistically simulated and controlled data streams are used to compare and discuss the performances of two fault detection methods referenced in the literature.