Incipient faults on blade load sensors can impede the sound performance of a wind turbine, leading to increasing loads over time and severe blade degradation. As such, knowledge of the blade load sensors’ health is essential for ensuring effective load reduction by means of individual pitch control. This paper presents a condition monitoring strategy for the blade load sensors based on estimation of the loads acting on the rotor blades in the full-load region. Fault detection is achieved via appropriate residual generators, the statistical properties of which are used to design change detectors robust against measurement noise and wind field stochasticity. Specifically, a Generalized Likelihood Ratio Test for the t-Location Scale distribution is developed for ensuring robust detection of sensor blade faults. The proposed method is evaluated in a high-fidelity simulator under non-uniform wind scenarios. The simulation results show that detection of multiplicative faults on the blade load sensors is achieved even in absence of knowledge of the local wind speed.
- Blade load sensor fault
- Wind turbine
- Condition monitoring
- Filtering and change detection
- Generalized likelihood ratio test
- t-LocationScale distribution