A novel and innovative solution addressing wind turbines’ main bearing failure predictions using SCADA data is presented. This methodology enables to cut setup times and has more flexible requirements when compared to the current predictive algorithms. The proposed solution is entirely unsupervised as it does not require the labeling of data through work orders logs. Results of interpretable algorithms, which are tailored to capture specific aspects of main bearing failures, are merged into a combined health status indicator making use of Ensemble Learning principles. Based on multiple specialized indicators, the interpretability of the results is greater compared to black-box solutions that try to address the problem with a single complex algorithm. The proposed methodology has been tested on a dataset covering more than two year of operations from two onshore wind farms, counting a total of 84 turbines. All four main bearing failures are anticipated at least one month of time in advance. Combining individual indicators into a composed one proved effective with regard to all the tracked metrics. Accuracy of 95.1%, precision of 24.5% and F1 score of 38.5% are obtained averaging the values across the two windfarms. The encouraging results, the unsupervised nature and the flexibility and scalability of the proposed solution are appealing, making it particularly attractive for any online monitoring system used on single wind farms as well as entire wind turbine fleets.

The goal of this paper is to develop, implement, and validate a methodology for wind turbines’ main bearing fault prediction based on an ensemble of an artificial neural network (normality model designed at turbine level) and an isolation forest (anomaly detection model designed at wind park level) algorithms trained only on SCADA data. The normal behavior and the anomalous samples of the wind turbines are identified and several interpretable indicators are proposed based on the predictions of these algorithms, to provide the wind park operators with understandable information with enough time to plan operations ahead and avoid unexpected costs. The stated methodology is validated in a real underproduction wind park composed by 18 wind turbines.

A hybrid health monitoring system for wind turbine generators is introduced. The novelty of this research consists in approaching a 115-wind turbine fleet by using the fusion of multiple sources of information. Analog SCADA data is analyzed through an autoencoder which allows to identify anomalous patterns within the input variables. Alarm logs are processed and merged to the anomaly detection output, creating a reliable health estimator of generator conditions. The proposed methodology has been tested on a fleet of 115 wind turbines from four different manufacturers located in various locations around Europe. The solution has been compared with other existing data modeling techniques offering impressive results on the fleet. An accuracy of 82% and a Kappa of 56% were obtained. The detailed methodology is presented using one of the available windfarms, composed of 13 onshore wind turbines rated 2 MW power. The rigorous evaluation of the results, the utilization of real data and the heterogeneity of the dataset prove the validity of the system and its applicability in an online operating scenario.

SCADA operating data are more and more used across the wind energy domain, both as a basis for power output prediction and turbine health status monitoring. Current industry practice to work with this data is by aggregating the signals at coarse resolution of typically 10-min averages, in order to reduce data transmission and storage costs. However, aggregation, i.e., downsampling, induces an inevitable loss of information and is one of the main causes of skepticism towards the use of SCADA operating data to model complex systems such as wind turbines. This research aims to quantify the amount of information that is lost due to this downsampling of SCADA operating data and characterize it with respect to the external factors that might influence it. The issue of information loss is framed by three key questions addressing effects on the local and global scale as well as the influence of external conditions. Moreover, recommendations both for wind farm operators and researchers are provided with the aim to improve the information content. We present a methodology to determine the ideal signal resolution that minimized storage footprint, while guaranteeing high quality of the signal. Data related to the wind, electrical signals, and temperatures of the gearbox resulted as the critical signals that are largely affected by an information loss upon aggregation and turned out to be best recorded and stored at high resolutions. All analyses were carried out using more than one year of 1 Hz SCADA data of onshore wind farm counting 12 turbines located in the UK.

Wind energy is a form of renewable energy with the highest installed capacity. However, it is necessary to reduce the operation and maintenance costs and extend the lifetime of wind turbines to make wind energy more competitive. This paper presents a power-derating-based Fault-Tolerant Control (FTC) model in 2 MW three-bladed wind turbines implemented using the National Renewable Energy Laboratory’s (NREL) Fatigue, Aerodynamics, Structures, and Turbulence (FAST) wind turbine simulator. This control strategy is potentially supported by the health status of the gearbox, which was predicted by means of algorithms and quantified in an indicator denominated as a merge developed by SMARTIVE, a pioneering of in this idea. Fuzzy logic was employed in order to decide whether to down-regulate the output power or not, and to which level to adjust to the needs of the turbines. Simulation results demonstrated that a reduction in the power output resulted in a safer operation, since the stresses withstood by the blades and tower significantly decreased. Moreover, the results supported empirically that a diminution in the generator torque and speed was acheived, resulting in a drop in the gearbox bearing and oil temperatures. By implementing this power-derating FTC, the downtime due to failure stops could be controlled, and thus the power production noticeably grew. It has been estimated that more than 325,000 tons of CO₂ could be avoided yearly if implemented globally.

The energy sector has undergone drastic changes and critical revolutions in the last few decades. Renewable energy sources have grown significantly, now representing a sizeable share of the energy production mix. Wind energy has seen increasing rate of adoptions, being one of the more convenient and sustainable mean of producing energy. Research and innovation have helped greatly in driving down production and operation costs of wind energy, yet important challenges still remain open. This thesis addresses predictive maintenance and monitoring of wind turbines, aiming to present predictive frameworks designed with the necessities of the industry in mind. More concretely: interpretability, scalability, modularity and reliability of the predictions are the objectives —together with limited data requirements— of this project. Of all the available data at the disposal of wind turbine operators, SCADA is the principal source of information utilized in this research, due to its wide availability and low cost. Ensemble models played an important role in the development of the presented predictive frameworks thanks to their modular nature which allows to combine very diverse algorithms and data types. Important insights gained from these experiments are the beneficial effect of combining multiple and diverse sources of data —for example SCADA and alarms logs—, the easiness of combining different algorithms and indicators, and the noticeable gain in predicting performance that it can provide. Finally, given the central role that SCADA data plays in this thesis, but also in the wind energy industry, a detailed analysis of the limitations and shortcomings of SCADA data is presented. In particular, the ef- fect of data aggregation —a common practice in the wind industry— is determined developing a methodological framework that has been used to study high–frequency SCADA data. This lead to the conclusion that typical aggregation periods, i.e. 5–10 minutes that are the standard in wind energy industry are not able to capture and maintain the information content of fast–changing signals, such as wind and electrical measurements. El sector energètic ha experimentat importants canvis i revolucions en les últimes dècades. Les fonts d’energia renovables han crescut significativament, i ara representen una part important en el conjunt de generació. L’energia eòlica ha augmentat significativament, convertint-se en una de les millors alternatives per produir energia verda. La recerca i la innovació ha ajudat a reduir considerablement els costos de producció i operació de l’energia eòlica, però encara hi ha oberts reptes importants. Aquesta tesi aborda el manteniment predictiu i el seguiment d’aerogeneradors, amb l’objectiu de presentar solucions d’algoritmes de predicció dissenyats tenint en compte les necessitats de la indústria. Més concretament conceptes com, la interpretabilitat, escalabilitat, modularitat i fiabilitat de les prediccions ho són els objectius, juntament amb els requisits limitats per les de dades disponibles d’aquest projecte. De totes les dades disponibles a disposició dels operadors d’aerogeneradors, les dades del sistema SCADA són la principal font d’informació utilitzada en aquest projecte, per la seva àmplia disponibilitat i baix cost. En el present treball, els models de conjunt tenen un paper important en el desenvolupament dels marcs predictius presentats gràcies al seu caràcter modular que permet l’ús d’algoritmes i tipus de dades molt diversos. Resultats importants obtinguts d’aquests experiments són l’efecte beneficiós de combinar múltiples i diverses fonts de dades, per exemple, SCADA i dades d’alarmes, la facilitat de combinar diferents algorismes i indicadors i el notable guany en predir el rendiment que es pot oferir. Finalment, donat el paper central que SCADA l’anàlisi de dades juga en aquesta tesi, però també en la indústria de l’energia eòlica, una anàlisi detallada de la es presenten les limitacions i les mancances de les dades SCADA. En particular es va estudiar l’efecte de l’agregació de dades -una pràctica habitual en la indústria eòlica-. Dins d’aquest treball es proposa un marc metodològic que s’ha utilitzat per estudiar dades SCADA d’alta freqüència. Això va portar a la conclusió que els períodes d’agregació típics, de 5 a 10 minuts que són l’estàndard a la indústria de l’energia eòlica, no són capaços de capturar i mantenir el contingut d’informació de senyals que canvien ràpidament, com ara mesures eòliques i elèctriques