RADAR-BASED STRUCTURAL MONITORING OF WIND TURBINES BLADES: FIELD RESULTS FROM TWO OPERATIONAL WIND TURBINES

Abstract

Wind energy plays a prominent role in Germany to achieve the climate targets. According to the ”Wind-an-Land-Gesetz” (literally: ”Wind on Land Act”), which has just come into force, the area used for onshore wind energy in Germany should be more than doubled from the current 0.8% to 2% until 2032. Rotor blades are one of the most significant cost factors of a wind turbine. They contribute with about 30% to the plant costs. By means of continuous monitoring of their structural integrity, it would be possible to reduce downtime and maintenance costs. This approach of “structural health monitoring” (SHM) with FMCW-radar systems has already been tested in the laboratory. In this contribution, we describe and demonstrate an SHM system for radar-based monitoring of rotor blades at two operational wind turbines. For this purpose, a sensor box with a 35 GHz radar sensor (1 000 measurements per second) and a camera system (100 images per second), is mounted on each wind turbine tower at approximately 100 m height. In order to distinguish individual rotor blades, a machine-readable marker printed on a self-adhesive film was applied on the blade’s surface. When a rotor blade passes the sensor, the camera captures an image of the marker while the radar records a measurement. The marker is then identified and the recorded data is assigned to a particular rotor blade. The ultimate goal is to detect damage-induced changes in the radar characteristic of the blades. By end of April, over 260 000 rotor blade passes had already been recorded. The data set will be discussed in the paper. Images from the FMCW-radar are classified by the rotor blade label using a convolutional neural network (CNN). Early test results for a subset already show an f1-score of 0.886 and 0.923 for each rotor blade of the evaluated wind turbine.