Abstract
In this paper the application of cyclostationary signal processing in conjunction with Ensemble Empirical Mode Decomposition (EEMD) technique, on the fault diagnostics of wind turbine gearboxes is investigated and has been highlighted. It is shown that the EEMD technique together with cyclostationary analysis can be used to detect the damage in complex and non-linear systems such as wind turbine gearbox, where the vibration signals are modulated with carrier frequencies and are superimposed. In these situations when multiple faults alongside noisy environment are present together, the faults are not easily detectable by conventional signal processing techniques such as FFT and RMS.
Highlights
With the wind energy global installed capacity reaching 651 GW in 2019 [1], effective remote condition monitoring and predictive maintenance strategies for wind turbines are becoming more significant attracting increased attention
Spectral Analysis and Ensemble Empirical Mode Decomposition (EEMD), which will be explained in more details
The rapid growth in the use of wind turbines combined with their operation under severe loading conditions has increased the need for efficient condition monitoring technologies
Summary
With the wind energy global installed capacity reaching 651 GW in 2019 [1], effective remote condition monitoring and predictive maintenance strategies for wind turbines are becoming more significant attracting increased attention. Gearbox faults and failures take considerable time to repair They result in major downtime and loss of production capacity leading to increased maintenance costs for wind farm operators [3,4,5,6]. Gearboxes are rarely available as spare parts and it can take several months before a spare gearbox can become available It is critical for wind farm operators to pinpoint the exact gearbox component affected by the fault and quantify its severity in order to accurately plan maintenance without the risk of loss of production. Spectral Analysis and Ensemble Empirical Mode Decomposition (EEMD), which will be explained in more details It should be stressed, that wind turbines operate in variable loading conditions and the accurate evaluation of the severity of faults is very challenging [12]. False indications of non-existent faults are not uncommon when using conventional signal processing techniques
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have