Wind Turbine Main Bearing Failure Prediction using a Hybrid Neural Network

Abstract

Energy is necessary for economic growth and improved well-being, but it poses a great challenge to be generated without increasing costs and avoiding pollution. A viable option is wind energy because it is a clean and renewable. However, continuous monitoring and maintenance of wind turbines is required for the further development of wind farms. Main bearing failures were identified by the European Academy of Wind Energy as a critical issue in terms of increasing the availability and reliability of wind turbines. In this work, it is proposed a hybrid neural network for main bearing failure prognosis. This network consists of a two-dimensional convolutional neural network (to extract spatial-temporal characteristics from the data) sequentially connected with a long short-term memory network (to learn sequence patterns) to predict the slow-speed shaft temperature (the closest temperature to the main bearing). The mean square error between its real measurement and its prediction gives a failure indicator. When it is greater than a defined threshold, then an alarm is triggered and gives the maintenance staff time to check the component. The advantage of this strategy is that it does not need faulty data to be trained, since it is based on a normality model, that is, it is trained with a single class of data (healthy) and does not require incurring high costs per acquisition of new sensors since SCADA data is used (which comes in all industrial size turbine). The results show that the use of a hybrid network can identify failures around four months before a fatal failure occurs.

Overview of normal behavior modeling approaches for SCADA-based wind turbine condition monitoring demonstrated ondata from operational wind farms

“…This can be done in several ways, e.g. Hermite interpolation (see (Bermúdez et al, 2022) and (Campoverde et al, 2022)), linear interpolation (see (Chesterman et al, 2022), (Chesterman et al, 2021) and (Miele et al, 2022)), .... Another technique is called carry forward and/or backward. In this technique, the missing value is replaced by the last known value before the missing value (carry forward) or the first known value after the missing value (carry backward).…”

“…In this technique, the missing value is replaced by the last known value before the missing value (carry forward) or the first known value after the missing value (carry backward). This is used in (Bermúdez et al, 2022), (Campoverde et al, 2022), (Chesterman et al, 2022), (Chesterman et al, 2021) and (Mazidi et al, 2017). The missing values can also be handled by filling them with the values of similar non-missing observations.…”

“…-10-minutes: (Bermúdez et al, 2022), (Black et al, 2022), (Campoverde et al, 2022), (Chesterman et al, 2022), (Maron et al, 2022), (Mazidi et al, 2017), (Miele et al, 2022), (Peter et al, 2022), (Takanashi et al, 2022), (Beretta et al, 2021), (Beretta M. and J., 2020), (Catellani et al, 2021), (Chen et al, 2021), (Chesterman et al, 2021), (Meyer, 2021), (Turnbull et al, 2021), (Udo and Yar, 2021), (Beretta M. and J., 2020), (Liu et al, 2020), (McKinnon et al, 2020, (Renström et al, 2020), (Zhao et al, 2018), (Bangalore et al, 2017), (Dienst and Beseler, 2016), (Bangalore and Tjernberg, 2015), https://doi.org/10.5194/wes-2022-120 Preprint. Discussion started: 21 February 2023 c Author(s) 2023.…”

“…However, not all of them are relevant to the case that is being solved. Some papers focus on a small subset of expert-selected signals (see for example (Peter et al, 2022), (Bermúdez et al, 2022) and (Chesterman et al, 2022), ...). Other papers use a large subset of signals and reduce the dimensionality of the problem during the preprocessing step or during a model-based automatic feature selection step that extracts the relevant information (see for example (Lima et al, 2020), (Renström et al, 2020), (Dienst and Beseler, 2016), ...).…”

“…The signals that are often used for condition monitoring of wind turbines can be more or less divided into three groups: 1) environmental data like wind speed, outside temperature, ... (used in for example (Bermúdez et al, 2022), (Bermúdez et al, 2022), (Black et al, 2022), (Campoverde et al, 2022), (Mazidi et al, 2017), (Miele et al, 2022), ... ), 2) operational data from the wind turbine like active power, rotor speed, ... (used in for example (Bermúdez et al, 2022), (Black et al, 2022), (Chesterman et al, 2022), (Miele et al, 2022), (Peter et al, 2022), ...) and 3) wind turbine temperature signals like the temperatures of the generator bearings, the temperature of the main shaft bearing, the temperature of the generator stator, ... (used for example (Bermúdez et al, 2022), (Black et al, 2022), (Campoverde et al, 2022), (Chesterman et al, 2022), (Mazidi et al, 2017), ...). The first two groups are often used by default, independent of the target signal that needs to be modeled or the failure that needs to be detected.…”