An Application of Instantaneous Spectral Entropy for the Condition Monitoring of Wind Turbines

For economic and environmental reasons, the use of renewable energy sources is a key aspect of the ongoing transition to a sustainable industrialised society. Wind energy represents a major player among these natural, carbon-neutral sources. Nevertheless, wind turbines are often subject to mechanical faults, especially due to ageing. To alleviate Operation and Maintenance costs, Vibration-Based Inspection and Condition Monitoring have been proposed in recent times. This research proposes Instantaneous Spectral Entropy and Continuous Wavelet Transform for anomaly detection and fault diagnosis, departing from gearbox vibration time histories. The approach is validated on experimental data recorded from a turbine suffering bearing failure and total gearbox replacement. From a computational point of view, the proposed algorithm was found to be efficient and therefore even potentially applicable for real-time monitoring.

Automated summary

This research proposes a method based on vibration detection and condition monitoring to alleviate operation and maintenance costs of wind turbines, and uses instantaneous spectral entropy and continuous wavelet transform for anomaly detection and fault diagnosis.