Filters








621 Hits in 8.5 sec

Outlier Detection in Wind Turbine Frequency Converters Using Long-Term Sensor Data

Nils Schwenzfeier, Markus Heikamp, Ole Meyer, Andre Hönnscheidt, Michael Steffes, Volker Gruhn
2022 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
A frequency converter is one of the most important components of each wind turbine, which ensures that the frequency of the generated energy synchronises with the grid frequency and thus enables the flow  ...  In both cases, it was shown that outliers can be reliably identified using our presented approach.  ...  When analysing the data, the focus has to be on outliers in the data sets in order to detect untypical operations of the wind turbines.  ... 
doi:10.1609/aaai.v36i11.21533 fatcat:wedvagc3jvcr3l2fg5nuxn4gr4

Machine learning methods for wind turbine condition monitoring: A review

Adrian Stetco, Fateme Dinmohammadi, Xingyu Zhao, Valentin Robu, David Flynn, Mike Barnes, John Keane, Goran Nenadic
2019 Renewable Energy  
This paper reviews the recent literature on machine learning (ML) models that have been used for condition monitoring in wind turbines (e.g. blade fault detection or generator temperature monitoring).  ...  Our findings show that most models use SCADA or simulated data, with almost two-thirds of methods using classification and the rest relying on regression.  ...  Paper Task Method Description [44] Outlier detection Univariate outlier detection Detecting outliers in time signals. [45] Feature Selection Wrapper Prediction performance of a given model is used to  ... 
doi:10.1016/j.renene.2018.10.047 fatcat:r3wb7pjlsnfxtpmgiioexmkdby

Multiagent-Based Collaborative Framework for a Self-Managing Structural Health Monitoring System

Kay Smarsly, Kincho H. Law, Dietrich Hartmann
2012 Journal of computing in civil engineering  
The multi-agent framework has been implemented and validated for the monitoring of a 500 kW wind turbine in Germany.  ...  This research has demonstrated a practical adoption of a multi-agent-based structural health monitoring system for the long-term deployment in the field.  ...  Long-term monitoring results on the wind turbine are presented followed by a brief discussion on future research directions.  ... 
doi:10.1061/(asce)cp.1943-5487.0000107 fatcat:5dahzchtwnc5jhlk7qijjn5m7m

Vestas V90-3MW Wind Turbine Gearbox Health Assessment Using a Vibration-Based Condition Monitoring System

A. Romero, Y. Lage, S. Soua, B. Wang, T.-H. Gan
2016 Shock and Vibration  
This paper presents a novel approach for health condition monitoring (CM) and fault diagnosis in wind turbine gearboxes using vibration analysis.  ...  Outliers picked up during the baseline stage are decomposed by the ICD method to obtain the product components which reveal the fault information.  ...  The slope is not calculated using the last two measurements as that would be more a short term convergence indicator rather than a medium or long term convergence indicator.  ... 
doi:10.1155/2016/6423587 fatcat:fhlrnlkjyvfvvhra7upb6g7cri

Damage detection in a laboratory wind turbine blade using techniques of ultrasonic NDT and SHM

Kai Yang, Jem A. Rongong, Keith Worden
2018 Strain  
The authors would all like to thank Dr Evangelos (Vaggelis) Papatheou (now of the University of Exeter, UK) for his support in carrying out, and understanding, the modal tests on the wind turbine blade  ...  KY acknowledges the support of Professor Wieslaw Staszewski (now of AGH University, Krakow, Poland) for his supervision and guidance in the early stages of his PhD project, and for setting the main objectives  ...  In general, a wind turbine converts the kinetic energy of wind into electrical energy [6, 7] .  ... 
doi:10.1111/str.12290 fatcat:jgzcns6n5bdzrefoc2dhhlzs2a

Data-Driven Predictive Maintenance of Wind Turbine Based on SCADA Data

Wisdom Udo, Yar Muhammad
2021 IEEE Access  
Predictive maintenance in wind turbines can be achieved by analysing data obtained by sensors already equipped with the WT.  ...  We developed models using extreme gradient boosting (XGBoost) and Long Short-Term Memory (LSTM) to build the characteristics behaviour of critical WT components, and Statistical Process Control (SPC) was  ...  CONCLUSION In this paper, a system for monitoring and detecting anomalies in the wind turbine gearbox and generator is developed using SCADA data, extreme gradient boosting (XGBoost), and Long Short-Term  ... 
doi:10.1109/access.2021.3132684 fatcat:eq2cetzfuzdjre6vctqrzvrgyu

An Integrated Framework of Drivetrain Degradation Assessment and Fault Localization for Offshore Wind Turbines

Wenyu Zhao, David Siegel, Jay Lee, Liying Su
2020 International Journal of Prognostics and Health Management  
As wind energy proliferates in onshore and offshore applications, it has become significantly important to predict wind turbine downtime and maintain operation uptime to ensure maximal yield.  ...  Theapproach is validated on a 3 MW offshore turbine, where an incipient fault is detected well before existing system shuts down the unit.  ...  Yubin Zhu, for their support in terms of condition monitoring system expertise, wind turbine operation experience and providing data for the case study.  ... 
doi:10.36001/ijphm.2013.v4i3.2142 fatcat:daqkhearmjez5gcvlcnubuoj4i

Remote Health Monitoring of Wind Turbines Employing Vibroacoustic Transducers and Autoencoders

Andrzej Czyżewski
2022 Frontiers in Energy Research  
The scientific experiment resulted in data gathering and analysis to predict potential wind turbine mechanism failures.  ...  Implementation of remote monitoring technology for real wind turbine structures designed to detect potential sources of failure is described.  ...  In particular, I would like to thank two team members, namely Grzegorz Szwoch, for the literature review he conducted and Adam Kurowski for performing the analyses illustrated in some figures in Chapter  ... 
doi:10.3389/fenrg.2022.858958 fatcat:zfh3ikkmcjff3l27pnitiao7d4

The Limpet: A ROS-Enabled Multi-Sensing Platform for the ORCA Hub

Mohammed E Sayed, Markus P Nemitz, Simona Aracri, Alistair C McConnell, Ross M McKenzie, Adam A Stokes
2018 Sensors  
We simulated and classified four different faults in the operation of wind turbines.  ...  We show an example of this approach for monitoring offshore wind turbines, by designing an experimental setup to mimic a wind turbine using a stepper motor and custom-designed acrylic fan blades.  ...  Sensors 2018, 18, 3487  ... 
doi:10.3390/s18103487 pmid:30332821 pmcid:PMC6210591 fatcat:igdjwflyrna5xgoila7bzgafxa

Long-term operational data analysis of an in-service wind turbine DFIG

E. Artigao, A. Sapena-Bano, A. Honrubia-Escribano, J. Martinez-Roman, R. Puche-Panadero, E. Gomez-Lazaro
2019 IEEE Access  
The goal of this paper is to analyze a long-term monitoring campaign of an in-service WT equipped with a DFIG.  ...  in the wind energy sector.  ...  -UP Service, part of the AWESOME Project Consortium providing the wind turbine data.  ... 
doi:10.1109/access.2019.2895999 fatcat:ph55g46qlndoxat5ecmnyxc57u

Condition-based maintenance methods for marine renewable energy

Alexis Mérigaud, John V. Ringwood
2016 Renewable & Sustainable Energy Reviews  
This paper focusses on offshore wind, tidal flow and wave energy as target MRE domains and provides a comprehensive review of condition-based maintenance methodologies currently employed in MRE systems  ...  In particular, condition-based maintenance and prognostics can help to optimise maintenance activities and forewarn of impending maintenance requirements, mindful of the constrained access to MRE systems  ...  Air turbines Air turbines are used in oscillating water columns to convert the air flow into mechanical energy.  ... 
doi:10.1016/j.rser.2016.07.071 fatcat:5ekgjv5qrzflpiwsm7cdxpjkeu

A Review and Methodology Development for Remaining Useful Life Prediction of Offshore Fixed and Floating Wind turbine Power Converter with Digital Twin Technology Perspective

Krishnamoorthi Sivalingam, Marco Sepulveda, Mark Spring, Peter Davies
2018 2018 2nd International Conference on Green Energy and Applications (ICGEA)  
It is not possible to detect all the faults occurring in an offshore wind turbine using a limited number of sensors and huge amount of data to be analysed.  ...  SVM has been used for data pattern recognition, classification, regression and outliers detection since 1995.  ...  This wind speed distribution is further analysed by month and with wind speed bins of 1 m/s as it is shown in Table 62 . Frequency corresponds to 10 minutes averaged measurements.  ... 
doi:10.1109/icgea.2018.8356292 fatcat:7ievhpobkvaojnul4gb6jfcp3i

A Deep Neural Network Sensor for Visual Servoing in 3D Spaces

Petar Durdevic, Daniel Ortiz-Arroyo
2020 Sensors  
Two deep convolutional neural networks attached to the stereo camera in the drone are trained to detect wind turbines in images and stereo triangulation is used to calculate the distance from a wind turbine  ...  Our experimental results show that the sensor produces data accurate enough to be used for servoing, even in the presence of noise generated when the drone is not being completely stable.  ...  Deep CNNs, combined with long short term memory (LSTM) networks, were used to learn a local cost map representation of the road.  ... 
doi:10.3390/s20051437 pmid:32155733 fatcat:i73u7oxzejd7bomqm5og3tvmlm

Use of Learning Mechanisms to Improve the Condition Monitoring of Wind Turbine Generators: A Review

Ana Rita Nunes, Hugo Morais, Alberto Sardinha
2021 Energies  
, boosting wind turbines' availability.  ...  In particular, we start framing the predictive maintenance problem as an ML problem to detect patterns that indicate a fault on turbine generators.  ...  Ma [47] proposed a model that uses parallel factor analysis (PARAFAC) for fault detection and sensor selection of wind turbines based on SCADA data.  ... 
doi:10.3390/en14217129 fatcat:axhxvp43e5ehrjeb5hu3v22iz4

A fault detection framework using recurrent neural networks for condition monitoring of wind turbines

Yue Cui, Pramod Bangalore, Lina Bertling Tjernberg
2021 Wind Energy  
Specifically, the thesis investigates wind turbines. This thesis proposes a fault detection framework for cost-effective preventive maintenance of wind turbines by using condition monitoring systems.  ...  The fault detection framework is tested with the experience data from onshore wind farms. The results demonstrate that the framework can detect operational risks and reduce false alarms.  ...  The similar issue applies in terms of fault detection for wind turbines as well.  ... 
doi:10.1002/we.2628 fatcat:ctpo4v5jfzatbdddwnr32telji
« Previous Showing results 1 — 15 out of 621 results