A data-driven approach for analyzing faults in wind turbine gearbox is developed and tested. More specifically, faults in a ring gear are predicted in advance. Time-domain statistical metrics, such as jerk, root mean square (RMS), crest factor (CF), and kurtosis, are investigated to identify faulty components of a wind turbine. The components identified are validated with the fast Fourier transformation (FFT) of vibration data. Fifty neural networks (NNs) with different parameter settings are trained to obtain the best performing model. Models based on original vibration data, and transformed jerk data are constructed. The jerk model based on multisensor data outperforms the other models and therefore is used for testing and validation of previously unseen data. Short-term predictions of up to 15 time intervals, each representing 0.1 s, are performed. The prediction accuracy varies from 91.68% to 94.78%.
Skip Nav Destination
Article navigation
August 2013
Research-Article
Modeling and Prediction of Gearbox Faults With Data-Mining Algorithms
Andrew Kusiak
Andrew Kusiak
1
Professor
e-mail: andrew-kusiak@uiowa.edu
and Industrial Engineering,
The University of Iowa,
Iowa City, IA 52242-1527
e-mail: andrew-kusiak@uiowa.edu
Department of Mechanical
and Industrial Engineering,
The University of Iowa,
Iowa City, IA 52242-1527
1Corresponding author.
Search for other works by this author on:
Andrew Kusiak
Professor
e-mail: andrew-kusiak@uiowa.edu
and Industrial Engineering,
The University of Iowa,
Iowa City, IA 52242-1527
e-mail: andrew-kusiak@uiowa.edu
Department of Mechanical
and Industrial Engineering,
The University of Iowa,
Iowa City, IA 52242-1527
1Corresponding author.
Contributed by the Solar Energy Division of ASME for publication in the JOURNAL OF SOLAR ENERGY ENGINEERING. Manuscript received January 21, 2012; final manuscript received September 20, 2012; published online March 26, 2013. Assoc. Editor: Christian Masson.
J. Sol. Energy Eng. Aug 2013, 135(3): 031007 (11 pages)
Published Online: March 26, 2013
Article history
Received:
January 21, 2012
Revision Received:
September 20, 2012
Citation
Verma, A., Zhang, Z., and Kusiak, A. (March 26, 2013). "Modeling and Prediction of Gearbox Faults With Data-Mining Algorithms." ASME. J. Sol. Energy Eng. August 2013; 135(3): 031007. https://doi.org/10.1115/1.4023516
Download citation file:
Get Email Alerts
Mass Flow Control Strategy for Maximum Energy Extraction in Thermal Energy Storage Tanks
J. Sol. Energy Eng (December 2025)
Exergy Optimization of a Hybrid Multi-Evaporative Desalination Plant Powered by Solar and Geothermal Energy
J. Sol. Energy Eng (June 2025)
Correlation for Maximum Heat Transfer Between Fluidized Bed and Its Wall and Application to Solar Power Plants
J. Sol. Energy Eng (June 2025)
Related Articles
Wind Turbine Gearbox Fault Detection Using Multiple Sensors With Features Level Data Fusion
J. Eng. Gas Turbines Power (April,2012)
Prediction of Status Patterns of Wind Turbines: A Data-Mining Approach
J. Sol. Energy Eng (February,2011)
Monitoring Wind Turbine Vibration Based on SCADA Data
J. Sol. Energy Eng (May,2012)
Vibration-Based Condition Monitoring of Wind Turbine Gearboxes Based on Cyclostationary Analysis
J. Eng. Gas Turbines Power (March,2019)
Related Proceedings Papers
Related Chapters
Real-Time Prediction Using Kernel Methods and Data Assimilation
Intelligent Engineering Systems through Artificial Neural Networks
Knowledge Discovery Results as a Threat to Privacy
International Conference on Electronics, Information and Communication Engineering (EICE 2012)
The Applications of the Cloud Theory in the Spatial DMKD
International Conference on Electronics, Information and Communication Engineering (EICE 2012)