Skip to main content

DESARROLLO Y VALIDACION DE SISTEMAS DE MONITORIZACION INTELIGENTE, ESTRATEGIAS DE CONTROL DEL PITCH Y DE AMORTIGUACION ESTRUCTURAL PARA AEROGENERADORES OFFSHORE FLOTANTES

DPI2017-82930-C2-1-R

•
Funding agency name Agencia Estatal de Investigación
Funding agency acronym AEI
Program Programa Estatal de I+D+i Orientado a los Retos de la Sociedad
Call Proyectos I+D+i Retos de Investigación
Call year 2017
State Plan 2017-2020 Plan Estatal de Investigación Científica y Técnica y de Innovación
Beneficiary centre UNIVERSITAT POLITECNICA DE CATALUNYA

Resultados relacionados

Resultados totales (Incluyendo duplicados): 26
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Data classification methodology for electronic noses using uniform manifold approximation and projection and extreme learning machine

  • Leon Medina, Jersson Xavier|||0000-0002-9198-1996
  • Parés Mariné, Núria|||0000-0002-2914-9904
  • Anaya Vejar, Maribel
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc|||0000-0001-8958-6789
The classification and use of robust methodologies in sensor array applications of electronic noses (ENs) remain an open problem. Among the several steps used in the developed methodologies, data preprocessing improves the classification accuracy of this type of sensor. Data preprocessing methods, such as data transformation and data reduction, enable the treatment of data with anomalies, such as outliers and features, that do not provide quality information; in addition, they reduce the dimensionality of the data, thereby facilitating the tasks of a machine learning classifier. To help solve this problem, in this study, a machine learning methodology is introduced to improve signal processing and develop methodologies for classification when an EN is used. The proposed methodology involves a normalization stage to scale the data from the sensors, using both the well-known min-max approach and the more recent mean-centered unitary group scaling (MCUGS). Next, a manifold learning algorithm for data reduction is applied using uniform manifold approximation and projection (UMAP). The dimensionality of the data at the input of the classification machine is reduced, and an extreme learning machine (ELM) is used as a machine learning classifier algorithm. To validate the EN classification methodology, three datasets of ENs were used. The first dataset was composed of 3600 measurements of 6 volatile organic compounds performed by employing 16 metal-oxide gas sensors. The second dataset was composed of 235 measurements of 3 different qualities of wine, namely, high, average, and low, as evaluated by using an EN sensor array composed of 6 different sensors. The third dataset was composed of 309 measurements of 3 different gases obtained by using an EN sensor array of 2 sensors. A 5-fold cross-validation approach was used to evaluate the proposed methodology. A test set consisting of 25% of the data was used to validate the methodology with unseen data. The results showed a fully correct average classification accuracy of 1 when the MCUGS, UMAP, and ELM methods were used. Finally, the effect of changing the number of target dimensions on the reduction of the number of data was determined based on the highest average classification accuracy., This work was funded in part with resources from the Fondo de Ciencia, Tecnología e Innovación (FCTeI) del Sistema General de Regalías (SGR) from Colombia. The authors express their gratitude to the Administrative Department of Science, Technology, and Innovation–Colciencias with the grant 779–“Convocatoria para la Formación de Capital Humano de Alto Nivel para el Departamento de Boyacá 2017” for sponsoring the research presented herein. This study has been partially funded by the Spanish Agencia Estatal de Investigación (AEI)-Ministerio de Economía, Industria y Competitividad (MINECO), and the Fondo Europeo de Desarrollo Regional (FEDER) through research projects DPI2017-82930-C2-1-R and PGC2018-097257-B-C33; and by the Generalitat de Catalunya through research projects 2017-SGR-388 and 2017-SGR-1278., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Siamese neural networks for damage detection and diagnosis of jacket-type offshore wind turbine platforms

  • Baquerizo, Joseph
  • Tutivén Gálvez, Christian|||0000-0001-6322-4608
  • Puruncajas Maza, Bryan
  • Vidal Seguí, Yolanda|||0000-0003-4964-6948
  • Sampietro Saquicela, José Luis
Offshore wind energy is increasingly being realized at deeper ocean depths where jacket foundations are now the greatest choice for dealing with the hostile environment. The structural stability of these undersea constructions is critical. This paper states a methodology to detect and classify damage in a jacket-type support structure for offshore wind turbines. Because of the existence of unknown external disturbances (wind and waves), standard structural health monitoring technologies, such as guided waves, cannot be used directly in this application. Therefore, using vibration-response-only accelerometer measurements, a methodology based on two in-cascade Siamese convolutional neural networks is proposed. The first Siamese network detects the damage (discerns whether the structure is healthy or damaged). Then, in case damage is detected, a second Siamese network determines the damage diagnosis (classifies the type of damage). The main results and claims of the proposed methodology are the following ones: (i) It is solely dependent on accelerometer sensor output vibration data, (ii) it detects damage and classifies the type of damage, (iii) it operates in all wind turbine regions of operation, (iv) it requires less data to train since it is built on Siamese convolutional neural networks, which can learn from very little data compared to standard machine/deep learning algorithms, (v) it is validated in a scaled-down experimental laboratory setup, and (vi) its feasibility is demonstrated as all computed metrics (accuracy, precision, recall, and F1 score) for the obtained results remain above 96%., Peer Reviewed, Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant::7.2 - Per a 2030, augmentar substancialment el percentatge d’energia renovable en el con­junt de fonts d’energia, Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant
UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Imbalanced multi-class classification of structural damage in a wind turbine foundation

  • Leon Medina, Jersson Xavier|||0000-0002-9198-1996
  • Parés Mariné, Núria|||0000-0002-2914-9904
  • Anaya, Maribel
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc|||0000-0001-8958-6789
Damage diagnosis for offshore wind turbine foundations is a topic that remains open in the scientific community due to the importance of increasing safety and ensuring functionality. To deal with the challenge of online and in-service structural health monitoring (SHM) for wind turbines, approaches based on the vibration-response of the structure and captured by sensors such as the accelerometers need to be considered. This work presents a novel methodology to improve the structural damage classification of wind turbine foundations. This methodology consists of several stages. First, the data acquisition to collect and organize the information from the sensors attached to the structure, following the use of a mean-centered group scaling (MCGS) procedure to normalize the raw data and eliminate the difference between the magnitudes of the sensors. Next, a data unfolding to allow the multivariable analysis is performed. Then a linear feature extraction stage is applied to reduce the high dimensionality of the signals. Subsequently, the new feature array serves as the input to a supervised machine learning algorithm which allow to perform the classification task. A five-fold cross-validation procedure is used to obtain the goodness of classification. Several classification performance measures are calculated considering an imbalanced data set obtained with experimental data of a small-scale wind turbine foundation structure to validate the results of the proposed methodology., This work has been partially funded by the Spanish Agencia Estatal de Investigación (AEI) — Ministerio de Economía, Industria y Competitividad (MINECO), and the Fondo Europeo de Desarrollo Regional (FEDER) through the research projects DPI2017-82930-C2-1-R and PGC2018-097257-B-C33; and by the Generalitat de Catalunya through the research projects 2017-SGR-388 and 2017-SGR-1278., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Wind turbine main bearing fault prognosis based solely on SCADA data

  • Encalada-Dávila, Ángel
  • Puruncajas Maza, Bryan
  • Tutivén Gálvez, Christian|||0000-0001-6322-4608
  • Vidal Seguí, Yolanda|||0000-0003-4964-6948
As stated by the European Academy of Wind Energy (EAWE), the wind industry has identified main bearing failures as a critical issue in terms of increasing wind turbine reliability and availability. This is owing to major repairs with high replacement costs and long downtime periods associated with main bearing failures. Thus, the main bearing fault prognosis has become an economically relevant topic and is a technical challenge. In this work, a data-based methodology for fault prognosis is presented. The main contributions of this work are as follows: (i) Prognosis is achieved by using only supervisory control and data acquisition (SCADA) data, which is already available in all industrial-sized wind turbines; thus, no extra sensors that are designed for a specific purpose need to be installed. (ii) The proposed method only requires healthy data to be collected; thus, it can be applied to any wind farm even when no faulty data has been recorded. (iii) The proposed algorithm works under different and varying operating and environmental conditions. (iv) The validity and performance of the established methodology is demonstrated on a real underproduction wind farm consisting of 12 wind turbines. The obtained results show that advanced prognostic systems based solely on SCADA data can predict failures several months prior to their occurrence and allow wind turbine operators to plan their operations., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Trends in condition monitoring for pitch bearings

  • Sandoval Núñez, Diego Aníbal|||0000-0003-1414-266X
  • Leturiondo, Urko
  • Pozo Montero, Francesc|||0000-0001-8958-6789
  • Vidal Seguí, Yolanda|||0000-0003-4964-6948
  • Salgado, Óscar
The value of wind power generation for energy sustainability in the future is undeniable. Since operation and maintenance activities account for a sizeable portion of the cost associated with offshore wind turbine operation, strategies are needed to decrease this cost. One strategy, condition monitoring (CM) of wind turbines, allows the useful life of several parts to be extended and has generated great interest in the industry. Pitch bearings are one type of critical component, by virtue of the time and logistics involved in their maintenance tasks. As the complex working conditions of pitch bearings entail the need for diverse and innovative monitoring techniques, the classical bearing analysis techniques are not suitable. This paper provides a literature review of several condition monitoring techniques. First, they are arranged according to the nature of the signal, such as vibration, acoustic emission and so on. Secondly, they are arranged by relevant authors in compliance with the signal nature. While little research has been performed, an outline is significant for further contributions to the literature., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Vibration-Response-Only Structural Health Monitoring for Offshore Wind Turbine Jacket Foundations via Convolutional Neural Networks

  • Puruncajas Maza, Bryan
  • Vidal Seguí, Yolanda|||0000-0003-4964-6948
  • Tutivén Gálvez, Christian|||0000-0001-6322-4608
This work deals with structural health monitoring for jacket-type foundations of offshore wind turbines. In particular, a vibration-response-only methodology is proposed based on accelerometer data and deep convolutional neural networks. The main contribution of this article is twofold: (i) a signal-to-image conversion of the accelerometer data into gray scale multichannel images with as many channels as the number of sensors in the condition monitoring system, and (ii) a data augmentation strategy to diminish the test set error of the deep convolutional neural network used to classify the images. The performance of the proposed method is analyzed using real measurements from a steel jacket-type offshore wind turbine laboratory experiment undergoing different damage scenarios. The results, with a classification accuracy over 99%, demonstrate that the stated methodology is promising to be utilized for damage detection and identification in jacket-type support structures., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Manifold learning algorithms applied to structural damage classification

  • Leon Medina, Jersson Xavier|||0000-0002-9198-1996
  • Anaya Vejar, Maribel
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc|||0000-0001-8958-6789
A comparative study of four manifold learning algorithms was carried out to perform the dimensionality reduction process within a proposed methodology for damage classification in structural health monitoring (SHM). Isomap, locally linear embedding (LLE), stochastic proximity embedding (SPE), and laplacian eigenmaps were used as manifold learning algorithms. The methodology included several stages that comprised: data normalization, dimensionality reduction, classification through K- Nearest Neighbors (KNN) machine learning model and finally holdout cross-validation with 25% of data for training and the remaining 75% of data for testing. Results evaluated in an experimental setup showed that the best classification accuracy was 100% when the methodology uses isomap algorithm with a hyperparameter k of 170 and 8 dimensions as a feature vector at the input to the KNN classification machine., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Early fault detection in the main bearing of wind turbines based on Gated Recurrent Unit (GRU) neural networks and SCADA data

  • Encalada-Dávila, Ángel
  • Moyón, Luis
  • Tutivén Gálvez, Christian|||0000-0001-6322-4608
  • Puruncajas Maza, Bryan
  • Vidal Seguí, Yolanda|||0000-0003-4964-6948
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, Failures in the main bearings of wind turbines are critical in terms of downtime and replacement cost. Early diagnosis of their faults would lower the levelized cost of wind energy. Thus, this work discusses a gated recurrent unit (GRU) neural network, which detects faults in the main bearing some months ahead (when the event that initiates/develops the failure releases heat) the actual fatal fault materializes. GRUs feature internal gates that govern information flow and are utilized in this study for their capacity to understand whether data in a time series is crucial enough to preserve or forget. It is noteworthy that the proposed methodology only requires healthy supervisory control and data acquisition (SCADA) data. Thus, it can be deployed to old wind parks (nearing the end of their lifespan) where specific high-frequency condition monitoring sensors are not installed and to new wind parks where faulty historical data do not exist yet. The strategy is trained, validated, and finally tested using SCADA data from an in-production wind park composed of nine wind turbines., Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant, Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant::7.2 - Per a 2030, augmentar substancialment el percentatge d’energia renovable en el con­junt de fonts d’energia, Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant::7.3 - Per a 2030, duplicar la taxa mundial de millora de l’eficiència energètica
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Entropy indicators: an approach for low-speed bearing diagnosis

  • Sandoval Núñez, Diego Aníbal|||0000-0003-1414-266X
  • Leturiondo, Urko
  • Vidal Seguí, Yolanda|||0000-0003-4964-6948
  • Pozo Montero, Francesc|||0000-0001-8958-6789
To increase the competitiveness of wind energy, the maintenance costs of offshore floating and fixed wind turbines need to be reduced. One strategy is the enhancement of the condition monitoring techniques for pitch bearings, because their low operational speed and the high loads applied to them make their monitoring challenging. Vibration analysis has been widely used for monitoring the bearing condition with good results obtained for regular bearings, but with difficulties when the operational speed decreases. Therefore, new techniques are required to enhance the capabilities of vibration analysis for bearings under such operational conditions. This study proposes the use of indicators based on entropy for monitoring a low-speed bearing condition. The indicators used are approximate, dispersion, singular value decomposition, and spectral entropy of the permutation entropy. This approach has been tested with vibration signals acquired in a test rig with bearings under different health conditions. The results show that entropy indicators (EIs) can discriminate with higher-accuracy damaged bearings for low-speed bearings compared with the regular indicators. Furthermore, it is shown that the combination of regular and entropy-based indicators can also contribute to a more reliable diagnosis., This study was partially funded by the Spanish Agencia Estatal de Investigación (AEI)—Ministerio de Economía, Industria y Competitividad (MINECO), the Fondo Europeo de Desarrollo Regional (FEDER) through the research projects DPI2017-82930-C2-1-R and DPI2017-82930-C2-2-R, and by the Generalitat de Catalunya through the research project 2017 SGR 388., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Desarrollo y validación de sistemas de monitorización inteligente para aerogeneradores

UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Ensemble of feature extraction methods to improve the structural damage classification in a wind turbine foundation

  • Leon Medina, Jersson Xavier|||0000-0002-9198-1996
  • Parés Mariné, Núria|||0000-0002-2914-9904
  • Anaya, Maribel
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc|||0000-0001-8958-6789
The condition monitoring of offshore wind power plants is an important topic that remains open. This monitoring search to lower the maintenance cost of this plants. One of the main components of the wind power plant is the wind turbine foundation. This study describes a data driven structural damage classification methodology applied in a wind turbine foundation. A vibration-response was captured in the structure using an accelerometer network. After arranged the obtained data a feature vector of 58,008 features was obtained. An ensemble approach of dimensionality reduction methods was applied to obtain a new set of features that is used to train a machine learning based classification model. Four different damage scenarios were applied in the structure. Therefore, considering the healthy structure, there are 5 classes in total that were correctly classified. As a result, 100\% of classification accuracy was obtained after applying the damage classification methodology in a wind-turbine offshore jacket-type foundation benchmark structure., This work has been partially funded by the Spanish Agencia Estatal de Investigación (AEI) - Ministerio de Economía, Indústria y Competitividad (MINECO), and the Fondo Europeo de Desarrollo Regional (FEDER) through the research projects DPI2017-82930-C2-1-R and PGC2018-097257-B-C33; and by the Generalitat de Catalunya through the research projects 2017-SGR-388 and 2017-SGR-1278., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Revisión de las técnicas de monitorización del estado de los rodamientos de las palas de los aerogeneradores, Revision of the condition based monitoring techniques of the pitch bearings from wind turbines

  • Sandoval Núñez, Diego Aníbal|||0000-0003-1414-266X
  • Leturiondo, Urko
  • Pozo Montero, Francesc|||0000-0001-8958-6789
  • Vidal Seguí, Yolanda|||0000-0003-4964-6948
  • Salgado, Óscar
El aumento continuo del consumo energético ha sido una necesidad para el desarrollo de la sociedad humana, produciendo la energía necesaria históricamente con combustibles fósiles. El uso de estos combustibles y su contribución negativa al planeta ha sido evidente con el fenómeno del cambio climático. Esto ha provocado la concienciación por parte de la sociedad e instituciones de la generación de electricidad por medios convencionales (combustibles fósiles) como insostenible a medio y largo plazo. Por este motivo, las fuentes de energía sostenibles y eficientes se están convirtiendo en un objetivo fundamental en la actualidad. La energía eólica es una de estas opciones, al contar con costes económicamente viables. Una gran parte de los costes asociados a los aerogeneradores instalados mar adentro son producto de las actividades de operación y mantenimiento, las cuales pueden ser mejoradas. Para ello, una estrategia es la monitorización de la condición, que permite extender la vida útil de los componentes que forman el aerogenerador. Dentro de los componentes presen- tes en un aerogenerador, los rodamientos de pala son uno de los elementos críticos por ser frecuente su fallo, junto con el tiempo y la logística involucradas en su recambio. Estos temas en su con- junto motivan la realización de la presente revisión de las técnicas empleadas en la monitorización de la condición. Identificar estos temas permite visualizar y proponer líneas futuras de investigación., Peer Reviewed
UPCommons. Portal del coneixement obert de la UPC
Publication Artículo científico (JournalArticle)

Structural damage classification in a jacket-type wind-turbine foundation using principal component analysis and extreme gradient boosting

  • Leon Medina, Jersson Xavier|||0000-0002-9198-1996
  • Anaya Vejar, Maribel
  • Parés Mariné, Núria|||0000-0002-2914-9904
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc|||0000-0001-8958-6789
Damage classification is an important topic in the development of structural health monitoring systems. When applied to wind-turbine foundations, it provides information about the state of the structure, helps in maintenance, and prevents catastrophic failures. A data-driven pattern-recognition methodology for structural damage classification was developed in this study. The proposed methodology involves several stages: (1) data acquisition, (2) data arrangement, (3) data normalization through the mean-centered unitary group-scaling method, (4) linear feature extraction, (5) classification using the extreme gradient boosting machine learning classifier, and (6) validation applying a 5-fold cross-validation technique. The linear feature extraction capabilities of principal component analysis are employed; the original data of 58,008 features is reduced to only 21 features. The methodology is validated with an experimental test performed in a small-scale wind-turbine foundation structure that simulates the perturbation effects caused by wind and marine waves by applying an unknown white noise signal excitation to the structure. A vibration-response methodology is selected for collecting accelerometer data from both the healthy structure and the structure subjected to four different damage scenarios. The datasets are satisfactorily classified, with performance measures over 99.9% after using the proposed damage classification methodology., This work is partially funded by Fondo de Ciencia, Tecnología e Innovación (FCTeI) del Sistema General de Regalías (SGR). The authors express their gratitude to the Administrative Department of Science, Technology and Innovation—Colciencias with the grant 779—“Convocatoria para la Formación de Capital Humano de Alto Nivel para el Departamento de Boyacá 2017” for sponsoring the research presented herein. This work has been partially funded by the Spanish Agencia Estatal de Investigación (AEI)—Ministerio de Economía, Industria y Competitividad (MINECO), and the Fondo Europeo de Desarrollo Regional (FEDER) through the research projects DPI2017- 82930-C2-1-R and PGC2018-097257-B-C33; and by the Generalitat de Catalunya through the research projects 2017-SGR-388 and 2017-SGR-1278., Peer Reviewed
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Desarrollo y validación de sistemas de monitorización inteligente para aerogeneradores

Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Ensemble of feature extraction methods to improve the structural damage classification in a wind turbine foundation

  • Leon Medina, Jersson Xavier
  • Parés Mariné, Núria
  • Anaya, Maribel
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc
The condition monitoring of offshore wind power plants is an important topic that remains open. This monitoring search to lower the maintenance cost of this plants. One of the main components of the wind power plant is the wind turbine foundation. This study describes a data driven structural damage classification methodology applied in a wind turbine foundation. A vibration-response was captured in the structure using an accelerometer network. After arranged the obtained data a feature vector of 58,008 features was obtained. An ensemble approach of dimensionality reduction methods was applied to obtain a new set of features that is used to train a machine learning based classification model. Four different damage scenarios were applied in the structure. Therefore, considering the healthy structure, there are 5 classes in total that were correctly classified. As a result, 100\% of classification accuracy was obtained after applying the damage classification methodology in a wind-turbine offshore jacket-type foundation benchmark structure., This work has been partially funded by the Spanish Agencia Estatal de Investigación (AEI) - Ministerio de Economía, Indústria y Competitividad (MINECO), and the Fondo Europeo de Desarrollo Regional (FEDER) through the research projects DPI2017-82930-C2-1-R and PGC2018-097257-B-C33; and by the Generalitat de Catalunya through the research projects 2017-SGR-388 and 2017-SGR-1278., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Structural damage classification in a jacket-type wind-turbine foundation using principal component analysis and extreme gradient boosting

  • Leon Medina, Jersson Xavier
  • Anaya Vejar, Maribel
  • Parés Mariné, Núria
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc
Damage classification is an important topic in the development of structural health monitoring systems. When applied to wind-turbine foundations, it provides information about the state of the structure, helps in maintenance, and prevents catastrophic failures. A data-driven pattern-recognition methodology for structural damage classification was developed in this study. The proposed methodology involves several stages: (1) data acquisition, (2) data arrangement, (3) data normalization through the mean-centered unitary group-scaling method, (4) linear feature extraction, (5) classification using the extreme gradient boosting machine learning classifier, and (6) validation applying a 5-fold cross-validation technique. The linear feature extraction capabilities of principal component analysis are employed; the original data of 58,008 features is reduced to only 21 features. The methodology is validated with an experimental test performed in a small-scale wind-turbine foundation structure that simulates the perturbation effects caused by wind and marine waves by applying an unknown white noise signal excitation to the structure. A vibration-response methodology is selected for collecting accelerometer data from both the healthy structure and the structure subjected to four different damage scenarios. The datasets are satisfactorily classified, with performance measures over 99.9% after using the proposed damage classification methodology., This work is partially funded by Fondo de Ciencia, Tecnología e Innovación (FCTeI) del Sistema General de Regalías (SGR). The authors express their gratitude to the Administrative Department of Science, Technology and Innovation—Colciencias with the grant 779—“Convocatoria para la Formación de Capital Humano de Alto Nivel para el Departamento de Boyacá 2017” for sponsoring the research presented herein. This work has been partially funded by the Spanish Agencia Estatal de Investigación (AEI)—Ministerio de Economía, Industria y Competitividad (MINECO), and the Fondo Europeo de Desarrollo Regional (FEDER) through the research projects DPI2017- 82930-C2-1-R and PGC2018-097257-B-C33; and by the Generalitat de Catalunya through the research projects 2017-SGR-388 and 2017-SGR-1278., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Entropy indicators: an approach for low-speed bearing diagnosis

  • Sandoval Núñez, Diego Aníbal
  • Leturiondo, Urko
  • Vidal Seguí, Yolanda
  • Pozo Montero, Francesc
To increase the competitiveness of wind energy, the maintenance costs of offshore floating and fixed wind turbines need to be reduced. One strategy is the enhancement of the condition monitoring techniques for pitch bearings, because their low operational speed and the high loads applied to them make their monitoring challenging. Vibration analysis has been widely used for monitoring the bearing condition with good results obtained for regular bearings, but with difficulties when the operational speed decreases. Therefore, new techniques are required to enhance the capabilities of vibration analysis for bearings under such operational conditions. This study proposes the use of indicators based on entropy for monitoring a low-speed bearing condition. The indicators used are approximate, dispersion, singular value decomposition, and spectral entropy of the permutation entropy. This approach has been tested with vibration signals acquired in a test rig with bearings under different health conditions. The results show that entropy indicators (EIs) can discriminate with higher-accuracy damaged bearings for low-speed bearings compared with the regular indicators. Furthermore, it is shown that the combination of regular and entropy-based indicators can also contribute to a more reliable diagnosis., This study was partially funded by the Spanish Agencia Estatal de Investigación (AEI)—Ministerio de Economía, Industria y Competitividad (MINECO), the Fondo Europeo de Desarrollo Regional (FEDER) through the research projects DPI2017-82930-C2-1-R and DPI2017-82930-C2-2-R, and by the Generalitat de Catalunya through the research project 2017 SGR 388., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Siamese neural networks for damage detection and diagnosis of jacket-type offshore wind turbine platforms

  • Baquerizo, Joseph
  • Tutivén Gálvez, Christian
  • Puruncajas Maza, Bryan
  • Vidal Seguí, Yolanda
  • Sampietro Saquicela, José Luis
Offshore wind energy is increasingly being realized at deeper ocean depths where jacket foundations are now the greatest choice for dealing with the hostile environment. The structural stability of these undersea constructions is critical. This paper states a methodology to detect and classify damage in a jacket-type support structure for offshore wind turbines. Because of the existence of unknown external disturbances (wind and waves), standard structural health monitoring technologies, such as guided waves, cannot be used directly in this application. Therefore, using vibration-response-only accelerometer measurements, a methodology based on two in-cascade Siamese convolutional neural networks is proposed. The first Siamese network detects the damage (discerns whether the structure is healthy or damaged). Then, in case damage is detected, a second Siamese network determines the damage diagnosis (classifies the type of damage). The main results and claims of the proposed methodology are the following ones: (i) It is solely dependent on accelerometer sensor output vibration data, (ii) it detects damage and classifies the type of damage, (iii) it operates in all wind turbine regions of operation, (iv) it requires less data to train since it is built on Siamese convolutional neural networks, which can learn from very little data compared to standard machine/deep learning algorithms, (v) it is validated in a scaled-down experimental laboratory setup, and (vi) its feasibility is demonstrated as all computed metrics (accuracy, precision, recall, and F1 score) for the obtained results remain above 96%., Peer Reviewed, Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant::7.2 - Per a 2030, augmentar substancialment el percentatge d’energia renovable en el con­junt de fonts d’energia, Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Vibration-Response-Only Structural Health Monitoring for Offshore Wind Turbine Jacket Foundations via Convolutional Neural Networks

  • Puruncajas Maza, Bryan
  • Vidal Seguí, Yolanda
  • Tutivén Gálvez, Christian
This work deals with structural health monitoring for jacket-type foundations of offshore wind turbines. In particular, a vibration-response-only methodology is proposed based on accelerometer data and deep convolutional neural networks. The main contribution of this article is twofold: (i) a signal-to-image conversion of the accelerometer data into gray scale multichannel images with as many channels as the number of sensors in the condition monitoring system, and (ii) a data augmentation strategy to diminish the test set error of the deep convolutional neural network used to classify the images. The performance of the proposed method is analyzed using real measurements from a steel jacket-type offshore wind turbine laboratory experiment undergoing different damage scenarios. The results, with a classification accuracy over 99%, demonstrate that the stated methodology is promising to be utilized for damage detection and identification in jacket-type support structures., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Trends in condition monitoring for pitch bearings

  • Sandoval Núñez, Diego Aníbal
  • Leturiondo, Urko
  • Pozo Montero, Francesc
  • Vidal Seguí, Yolanda
  • Salgado, Óscar
The value of wind power generation for energy sustainability in the future is undeniable. Since operation and maintenance activities account for a sizeable portion of the cost associated with offshore wind turbine operation, strategies are needed to decrease this cost. One strategy, condition monitoring (CM) of wind turbines, allows the useful life of several parts to be extended and has generated great interest in the industry. Pitch bearings are one type of critical component, by virtue of the time and logistics involved in their maintenance tasks. As the complex working conditions of pitch bearings entail the need for diverse and innovative monitoring techniques, the classical bearing analysis techniques are not suitable. This paper provides a literature review of several condition monitoring techniques. First, they are arranged according to the nature of the signal, such as vibration, acoustic emission and so on. Secondly, they are arranged by relevant authors in compliance with the signal nature. While little research has been performed, an outline is significant for further contributions to the literature., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Data classification methodology for electronic noses using uniform manifold approximation and projection and extreme learning machine

  • Leon Medina, Jersson Xavier
  • Parés Mariné, Núria
  • Anaya Vejar, Maribel
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc
The classification and use of robust methodologies in sensor array applications of electronic noses (ENs) remain an open problem. Among the several steps used in the developed methodologies, data preprocessing improves the classification accuracy of this type of sensor. Data preprocessing methods, such as data transformation and data reduction, enable the treatment of data with anomalies, such as outliers and features, that do not provide quality information; in addition, they reduce the dimensionality of the data, thereby facilitating the tasks of a machine learning classifier. To help solve this problem, in this study, a machine learning methodology is introduced to improve signal processing and develop methodologies for classification when an EN is used. The proposed methodology involves a normalization stage to scale the data from the sensors, using both the well-known min-max approach and the more recent mean-centered unitary group scaling (MCUGS). Next, a manifold learning algorithm for data reduction is applied using uniform manifold approximation and projection (UMAP). The dimensionality of the data at the input of the classification machine is reduced, and an extreme learning machine (ELM) is used as a machine learning classifier algorithm. To validate the EN classification methodology, three datasets of ENs were used. The first dataset was composed of 3600 measurements of 6 volatile organic compounds performed by employing 16 metal-oxide gas sensors. The second dataset was composed of 235 measurements of 3 different qualities of wine, namely, high, average, and low, as evaluated by using an EN sensor array composed of 6 different sensors. The third dataset was composed of 309 measurements of 3 different gases obtained by using an EN sensor array of 2 sensors. A 5-fold cross-validation approach was used to evaluate the proposed methodology. A test set consisting of 25% of the data was used to validate the methodology with unseen data. The results showed a fully correct average classification accuracy of 1 when the MCUGS, UMAP, and ELM methods were used. Finally, the effect of changing the number of target dimensions on the reduction of the number of data was determined based on the highest average classification accuracy., This work was funded in part with resources from the Fondo de Ciencia, Tecnología e Innovación (FCTeI) del Sistema General de Regalías (SGR) from Colombia. The authors express their gratitude to the Administrative Department of Science, Technology, and Innovation–Colciencias with the grant 779–“Convocatoria para la Formación de Capital Humano de Alto Nivel para el Departamento de Boyacá 2017” for sponsoring the research presented herein. This study has been partially funded by the Spanish Agencia Estatal de Investigación (AEI)-Ministerio de Economía, Industria y Competitividad (MINECO), and the Fondo Europeo de Desarrollo Regional (FEDER) through research projects DPI2017-82930-C2-1-R and PGC2018-097257-B-C33; and by the Generalitat de Catalunya through research projects 2017-SGR-388 and 2017-SGR-1278., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Imbalanced multi-class classification of structural damage in a wind turbine foundation

  • Leon Medina, Jersson Xavier
  • Parés Mariné, Núria
  • Anaya, Maribel
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc
Damage diagnosis for offshore wind turbine foundations is a topic that remains open in the scientific community due to the importance of increasing safety and ensuring functionality. To deal with the challenge of online and in-service structural health monitoring (SHM) for wind turbines, approaches based on the vibration-response of the structure and captured by sensors such as the accelerometers need to be considered. This work presents a novel methodology to improve the structural damage classification of wind turbine foundations. This methodology consists of several stages. First, the data acquisition to collect and organize the information from the sensors attached to the structure, following the use of a mean-centered group scaling (MCGS) procedure to normalize the raw data and eliminate the difference between the magnitudes of the sensors. Next, a data unfolding to allow the multivariable analysis is performed. Then a linear feature extraction stage is applied to reduce the high dimensionality of the signals. Subsequently, the new feature array serves as the input to a supervised machine learning algorithm which allow to perform the classification task. A five-fold cross-validation procedure is used to obtain the goodness of classification. Several classification performance measures are calculated considering an imbalanced data set obtained with experimental data of a small-scale wind turbine foundation structure to validate the results of the proposed methodology., This work has been partially funded by the Spanish Agencia Estatal de Investigación (AEI) — Ministerio de Economía, Industria y Competitividad (MINECO), and the Fondo Europeo de Desarrollo Regional (FEDER) through the research projects DPI2017-82930-C2-1-R and PGC2018-097257-B-C33; and by the Generalitat de Catalunya through the research projects 2017-SGR-388 and 2017-SGR-1278., Peer Reviewed, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Revisión de las técnicas de monitorización del estado de los rodamientos de las palas de los aerogeneradores, Revision of the condition based monitoring techniques of the pitch bearings from wind turbines

  • Sandoval Núñez, Diego Aníbal
  • Leturiondo, Urko
  • Pozo Montero, Francesc
  • Vidal Seguí, Yolanda
  • Salgado, Óscar
El aumento continuo del consumo energético ha sido una necesidad para el desarrollo de la sociedad humana, produciendo la energía necesaria históricamente con combustibles fósiles. El uso de estos combustibles y su contribución negativa al planeta ha sido evidente con el fenómeno del cambio climático. Esto ha provocado la concienciación por parte de la sociedad e instituciones de la generación de electricidad por medios convencionales (combustibles fósiles) como insostenible a medio y largo plazo. Por este motivo, las fuentes de energía sostenibles y eficientes se están convirtiendo en un objetivo fundamental en la actualidad. La energía eólica es una de estas opciones, al contar con costes económicamente viables. Una gran parte de los costes asociados a los aerogeneradores instalados mar adentro son producto de las actividades de operación y mantenimiento, las cuales pueden ser mejoradas. Para ello, una estrategia es la monitorización de la condición, que permite extender la vida útil de los componentes que forman el aerogenerador. Dentro de los componentes presen- tes en un aerogenerador, los rodamientos de pala son uno de los elementos críticos por ser frecuente su fallo, junto con el tiempo y la logística involucradas en su recambio. Estos temas en su con- junto motivan la realización de la presente revisión de las técnicas empleadas en la monitorización de la condición. Identificar estos temas permite visualizar y proponer líneas futuras de investigación., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Manifold learning algorithms applied to structural damage classification

  • Leon Medina, Jersson Xavier
  • Anaya Vejar, Maribel
  • Tibaduiza Burgos, Diego Alexander
  • Pozo Montero, Francesc
A comparative study of four manifold learning algorithms was carried out to perform the dimensionality reduction process within a proposed methodology for damage classification in structural health monitoring (SHM). Isomap, locally linear embedding (LLE), stochastic proximity embedding (SPE), and laplacian eigenmaps were used as manifold learning algorithms. The methodology included several stages that comprised: data normalization, dimensionality reduction, classification through K- Nearest Neighbors (KNN) machine learning model and finally holdout cross-validation with 25% of data for training and the remaining 75% of data for testing. Results evaluated in an experimental setup showed that the best classification accuracy was 100% when the methodology uses isomap algorithm with a hyperparameter k of 170 and 8 dimensions as a feature vector at the input to the KNN classification machine., Peer Reviewed, Postprint (published version)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Early fault detection in the main bearing of wind turbines based on Gated Recurrent Unit (GRU) neural networks and SCADA data

  • Encalada-Dávila, Ángel
  • Moyón, Luis
  • Tutivén Gálvez, Christian
  • Puruncajas Maza, Bryan
  • Vidal Seguí, Yolanda
© 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works, Failures in the main bearings of wind turbines are critical in terms of downtime and replacement cost. Early diagnosis of their faults would lower the levelized cost of wind energy. Thus, this work discusses a gated recurrent unit (GRU) neural network, which detects faults in the main bearing some months ahead (when the event that initiates/develops the failure releases heat) the actual fatal fault materializes. GRUs feature internal gates that govern information flow and are utilized in this study for their capacity to understand whether data in a time series is crucial enough to preserve or forget. It is noteworthy that the proposed methodology only requires healthy supervisory control and data acquisition (SCADA) data. Thus, it can be deployed to old wind parks (nearing the end of their lifespan) where specific high-frequency condition monitoring sensors are not installed and to new wind parks where faulty historical data do not exist yet. The strategy is trained, validated, and finally tested using SCADA data from an in-production wind park composed of nine wind turbines., Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant, Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant::7.2 - Per a 2030, augmentar substancialment el percentatge d’energia renovable en el con­junt de fonts d’energia, Objectius de Desenvolupament Sostenible::7 - Energia Assequible i No Contaminant::7.3 - Per a 2030, duplicar la taxa mundial de millora de l’eficiència energètica, Postprint (author's final draft)
Recercat. Dipósit de la Recerca de Catalunya
Publication Artículo científico (JournalArticle)

Wind turbine main bearing fault prognosis based solely on SCADA data

  • Encalada-Dávila, Ángel
  • Puruncajas Maza, Bryan
  • Tutivén Gálvez, Christian
  • Vidal Seguí, Yolanda
As stated by the European Academy of Wind Energy (EAWE), the wind industry has identified main bearing failures as a critical issue in terms of increasing wind turbine reliability and availability. This is owing to major repairs with high replacement costs and long downtime periods associated with main bearing failures. Thus, the main bearing fault prognosis has become an economically relevant topic and is a technical challenge. In this work, a data-based methodology for fault prognosis is presented. The main contributions of this work are as follows: (i) Prognosis is achieved by using only supervisory control and data acquisition (SCADA) data, which is already available in all industrial-sized wind turbines; thus, no extra sensors that are designed for a specific purpose need to be installed. (ii) The proposed method only requires healthy data to be collected; thus, it can be applied to any wind farm even when no faulty data has been recorded. (iii) The proposed algorithm works under different and varying operating and environmental conditions. (iv) The validity and performance of the established methodology is demonstrated on a real underproduction wind farm consisting of 12 wind turbines. The obtained results show that advanced prognostic systems based solely on SCADA data can predict failures several months prior to their occurrence and allow wind turbine operators to plan their operations., Peer Reviewed, Postprint (published version)