Under the pressure of climate change, renewable energy gradually replaces fossil fuels and plays nowadays a significant role in energy production. Among other types, including sun, tides and geothermal heat, wind energy appears as one of the most favorable and promising energy sources, due to its advantages being free, unlimited and ecofriendly. In 2018, the global wind power capacity grew 9.6% reaching 591 GW. With a total installed capacity of 178.8 GW in the EU, wind energy remains the second largest form of power generation capacity in the EU-28 and is likely to overtake natural gas installations in 2019. Wind power covered 14% of the EU’s electricity demand in 2018, generating 362 TWh. A sizeable share of the total annual costs of a wind turbine is spent on Operations and Maintenance (O&M) costs, which may easily reach up to 20-25% of the total leverised cost per kWh produced over the lifetime of the turbine for a new turbine. The share could be only 10-15% in case the turbine is generally new but it can climb to at least 20-35% by the end of the turbine’s lifetime. Moreover according to Wood Mackenzie Power & Renewables (WMPR) onshore wind farm operators are expected to spend nearly \$15 billion on O&M services in 2019. 57% (\$8.5 billion) of this amount will be spent on unplanned repairs and correctives prompted by component failures. Under this prism, O&M cost attracts more attention, as manufacturers and operators try to reduce it significantly on one hand by developing new turbine designs and on the other hand by adopting condition monitoring approaches. One of the most critical and rather complex assembly of wind turbines is the gearbox. Gearboxes are designed to last till the end of asset’s lifetime, according to the IEC 61400-4 standards. On the other hand, a recent study over approximately 350 offshore wind turbines indicated that gearboxes might have to be replaced as early as 6.5 years. Therefore a plethora of sensor types and signal processing methodologies have been proposed in order to accuartely detect and diagnose the presence of a fault. Among others, Envelope Analysis is one of the most important methodologies, where an envelope of the vibration signal is estimated, usually after filtering around a selected frequency band excited by impacts due to the fault. Sometimes the gearbox is equipped with many acceleration sensors and its kinematics is clearly known. In these cases Cyclostationary Analysis and the corresponding methodologies, i.e. the Cyclic Spectral Correlation and the Cyclic Spectral Coherence, have been proposed as powerful tools. On the other hand often the gearbox is equipped with a limited number of sensors and a simple global diagnostic indicator is demanded, being capable to detect globally various faults of different components. The scope of this paper is the application and comparison of a number of blind global diagnostic indicators which are based on Entropy (Shannon entropy, Rényi entropy, Tsallis entropy, Wiener entropy and Permutation entropy), on Negentropy (Infogram), on Sparsity (Sparse-L2/L1, Sparse-L1/L0, Sparse-Gini index) and on Statistics (Mean, Standard deviation, Kurtosis, etc.). The performance of the indicators is evaluated and compared on a wind turbine data set, consisted of vibration data captured by one accelerometer mounted on six 2.5 MW wind turbines, located in a wind park in northern Sweden, where two different bearing faults have been filed, for one wind turbine, during a period of 46 months. Among the different diagnostic indicators Permutation entropy achieves the best results detecting blindly the two failure events.


Comparison of Blind Diagnostic Indicators for Condition Monitoring of Wind Turbine Gearbox Bearings

Division / Sponsor:
International Gas Turbine Institute (IGTI)

Paper Proceedings: https://asmedigitalcollection.asme.org/GT/GT2020/volume/84058

Turbo Expo - Virtual Conference

Supporting the need among researchers worldwide for additional online and multimedia content, ASME now offers the ASME Conference Video Collection. This platform will collect and provide long-term access to conference presentation videos, encompassing all technology areas within ASME's technical conference and events program. About 30,000-40,000 engineers across all mechanical engineering and related disciplines participate in ASME conferences each year. This includes authors of approximately 6,000 to 8,000 technical papers published by ASME, the majority of whom also submit video presentations for our virtual conferences. The video collection will be available as an add-on to existing product packages or as a separate subscription.