The mass of ice on wind turbines blades is one of the main problems that energy companies have in cold climates. This paper presents a novel approach to detect and classify ice thickness based on pattern recognition through guided ultrasonic waves and Machine Learning. To successfully achieve a supervised classification, it is necessary to employ a method that allows the correct extraction and selection of features of the ultrasonic signal. The main novelty in this work is that the approach considers four feature extraction methods to validate the results, grouped by linear (AutoRegressive (AR) and Principal Component Analysis) and nonlinear (nonlinear-AR eXogenous and Hierarchical Non-Linear Principal Component Analysis), and feature selection is done by Neighbourhood Component Analysis. A supervised classification was performed through Machine Learning with twenty classifiers such as Decision tree, Discriminant Analysis, Support Vector Machines, K-Nearest Neighbours, and Ensemble Classifiers. Finally, an evaluation of the classifiers was done in single frequency and multi-frequency modes, obtaining accurate results.

Nowadays, wind energy is one of the most important renewable energy sources for covering the current electrical demand. The sophistication and the complexity of the wind energy systems are constantly growing. Therefore, new maintenance management techniques are required for ensure the efficiency and rentability of these systems. This paper is focused on the extraction of information from the noise generated by wind turbines. The main causes of noise generation by wind turbines are analyzed in this paper. The noise information allows some types of failures to be detected incipiently and, consequently, preventive and corrective maintenance tasks can be improved. In this field, the use of unmanned aerial vehicles (UAV) can be very useful and facilitate the execution of the inspections. This paper presents a collection of methods for detecting failures through the processing of wind turbine noise. In addition, the possibility of employing UAVs for implement those methods is studied.