Active trailing edge flap system fault detection via machine learning

Active trailing edge flap (AFlap) systems have shown promising results in reducing wind turbine (WT) loads. The design of WTs relying on AFlap load reduction requires implementing systems to detect, monitor, and quantify any potential fault or performance degradation of the flap system to avoid jeopardizing the wind turbine's safety and performance. Currently, flap fault detection or monitoring systems are yet to be developed. This paper presents two approaches based on machine learning to diagnose the health state of an AFlap system. Both approaches rely only on the sensors commonly available on commercial WTs, avoiding the need and the cost of additional measurement systems. The first approach combines manual feature engineering with a random forest classifier. The second approach relies on random convolutional kernels to create the feature vectors. The study shows that the first method is reliable in classifying all the investigated combinations of AFlap health states in the case of asymmetrical flap faults not only when the WT operates in normal power production but also before startup. Instead, the second method can identify some of the AFlap health states for both asymmetrical and symmetrical faults when the WT is in normal power production. These results contribute to developing the systems for detecting and monitoring active flap faults, which are paramount for the safe and reliable integration of active flap technology in future wind turbine design.