Machine Learning for Wind Turbine Blades Maintenance Management

Abstract

Delamination in Wind Turbine Blades (WTB) is a common structural problem that can generate large costs. Delamination is the separation of layers of a composite material, which produces points of stress concentration. These points suffer greater traction and compression forces in working conditions, and they can trigger cracks, and partial or total breakage of the blade. Early detection of delamination is crucial for the prevention of breakages and downtime. The main novelty presented in this paper has been to apply an approach for detecting and diagnosing the delamination WTB. The approach is based on signal processing of guided waves, and multiclass pattern recognition using machine learning. Delamination was induced in the WTB to check the accuracy of the approach. The signal is denoised by wavelet transform. The autoregressive Yule-Walker model is employed for feature extraction, and Akaike's information criterion method for feature selection. The classifiers are quadratic discriminant analysis, k-nearest neighbors, decision trees, and neural network multilayer perceptron. The confusion matrix is employed to evaluate the classification, especially the receiver operating characteristic analysis by: recall, specificity, precision, and F-score.

Acoustic Maintenance Management Employing Unmanned Aerial Vehicles in Renewable Energies

“…The operators take decisions according to analytics methods [6][7][8], where in fault detection and diagnosis have been studying novel techniques in the last few years [9][10][11]. In order to improve the O&M process, condition-based maintenance systems are widely employed for the wind energy systems [12][13][14]. These systems allow useful information about the condition of the WTs to be extracted.…”

Maintenance Management in Wind Turbines by Monitoring the Bearing Temperature

“…(1.1). 1 Maintenance Management in Wind turbines 7 Figure 5 presents the behaviour of the bearing temperature versus wind speed in the different seasons of the year (winter, spring, summer and autumn). The main conclusions are: -WT 1 has a lower temperature in most cases, therefore, its heat dissipation is better and / or there is less friction between components.…”

“…dition, WTs are made up of various complex systems that give rise to a whole, therefore, the failures or damages can occur in various parts of the system [1,5,6].…”

Damage diagnosis for offshore fixed wind turbines

“…However, QDA is most commonly used in medicine [9], [10] and genomics [11], [12], as a classifier or as a pattern-recognition method. A recent application of QDA in WT fault detection is proposed by [13] where an approach for detecting and diagnosing the delamination in wind turbine blades is proposed.…”