Estimating Health Condition of the Wind Turbine Drivetrain System

Abstract

Condition Monitoring (CM) has been considered as an effective method to enhance the reliability of wind turbines and implement cost-effective maintenance. Thus, adopting an efficient approach for condition monitoring of wind turbines is desirable. This paper presents a data-driven model-based CM approach for wind turbines based on the online sequential extreme learning machine (OS-ELM) algorithm. A physical kinetic energy correction model is employed to normalize the temperature change to the value at the rated power output to eliminate the effect of variable speed operation of the turbines. The residual signal, obtained by comparing the predicted values and practical measurements, is processed by the physical correction model and then assessed with a Bonferroni interval method for fault diagnosis. Models have been validated using supervisory control and data acquisition (SCADA) data acquired from an operational wind farm, which contains various types of temperature data of the gearbox. The results show that the proposed method can detect more efficiently both the long-term aging characteristics and the short-term faults of the gearbox.

A Novel Condition Monitoring Method of Wind Turbines Based on Long Short-Term Memory Neural Network

“…However, spectral analysis based on vibration signals requires very detailed information about the bearing structural parameters [11]. Vibration signal analysis also needs very high-performance processors that increase the system cost [12]. Oil debris data analysis provides another method to monitor gearbox condition.…”

Labelling Drifts in a Fault Detection System for Wind Turbine Maintenance

“…This slight modification makes ELM training extremely fast, since only output weights need to be optimized, which is worked out by a simple ridge regression [33]. ELM have already been used to model the real operation of wind turbines, showing great generalization properties [13][14][15][16] In order to make the model predictions more robust and trustworthy, an ensemble of models [34] is used rather than an individual model. Each model from the ensemble is trained with a different batch of data, which will avoid two issues:…”

“…By using data sources, different strategies can be followed to build normal behaviour models, such as stochastic models, machine learning algorithms, Bayesian and fuzzy classifiers, time series prediction or pattern recognition. In the analyzed failure detection system a state-of-the-art neural network, Extreme Learning Machine (ELM), has been applied, due to its ability to easily model dynamic non-linear behaviours [10], and also because of its wide use in the prognostics of industrial systems and wind turbines [11][12][13][14][15][16] Whatever the selected model may be, an initial training batch is necessary for learning relationships between variables. Taking a feed-forward neural network as example, the network is trained with an historical data set, a fixed and static information about the past events of the system.…”

Assessment of Equipment Operation State with Improved Random Forest

“…Qian et al proposed an online sequential extreme learning machine (OS-ELM) algorithm for wind turbine condition monitoring. The long-term deterioration characteristics and the short-term faults of the gearbox were detected efficiently based on SCADA data and the proposed method [14]. Hsu et al regarded control charts based on an exponentially weighted moving average (EWMA) model as a main assessment method and set upper and lower limits to monitor state variables.…”