International Scientific Journal


This paper proposes wireless sensor networks to monitor the condition of wind turbines. It addresses lifetime maximization issue of sensor nodes using stable election protocol for a cluster of up to nine wind turbines. This paper presents results of both experimental and simulation studies of a wind turbine plant, in which the vibration signals from each wind turbine are taken and with the help of machine learning technique, the fault diagnosis is done for a plant with wireless sensor networks. An experimental case study is performed from a wireless sensor networks with a well reported wind turbine bearing fault diagnosis data set. The outcome of the study shows that if the number of wind turbines is five for one base station, then the lifetime of the sensor nodes are maximum using MATLAB.
PAPER REVISED: 2017-05-25
PAPER ACCEPTED: 2017-06-13
CITATION EXPORT: view in browser or download as text file
THERMAL SCIENCE YEAR 2017, VOLUME 21, ISSUE Supplement 2, PAGES [S523 - S531]
  1. Shukla, S., et al., Analysis of Statistical Features for Fault Detection in Ball Bearing, Proceedings, IEEE International Conference on Computational Intelligence and Computing Research (ICCIC), Madurai, In-dia, 2015, pp. 589-595
  2. Indira, V., et al., A Method for Calculation of Optimum Data Size and Bin Size of Histogram Features in Fault Diagnosis of Mono-Block Centrifugal Pump, Expert Systems with Applications, 38 (2011), 6, pp. 7708-7717
  3. Powar, U., Fault Diagnosis of Roller Bearing using Vibration Signals through ARMA Features and Tree Family Classifier, International Journal of Engineering Research & Technology, 4 (2015), 7, pp. 688-692
  4. Bajric, R., et al., Feature Extraction Using Discrete Wavelet Transform for Gear Fault Diagnosis of Wind Turbine Gearbox, Shock and Vibration, 2016, ID 6748469
  5. Farajzadeh-Zanjani, M., et al., Efficient Feature Extraction of Vibration Signals for Diagnosing Bearing Defects in Induction Motors, Proceedings, International Joint Conference on Neural Networks (IJCNN), Vancouver, B. C., Canada, IEEE, 2016, pp. 4504-4511
  6. Ballal, P., et al., Mechanical Fault Diagnosis using Wireless Sensor Networks and a Two-Stage Neural Network Classifier, Proceedings, Aerospace Conference, IEEE, Big Sky, Mont., USA, 2009, pp. 1-10
  7. Bajracharya, C., et al., Performance Analysis of Wireless Sensor Networks for Wind Turbine Monitor-ing Systems, Proceedings, IEEE Southeast Conference, Fort Lauderdale, Fla., USA, 2015
  8. Mahboub, A., et al., Multi-Zonal Approach Clustering Based on Stable Election Protocol in Heterogene-ous Wireless Sensor Networks, Proceedings, 4th IEEE International Colloquium on Information Science and Technology (CiSt), Tangier, Moroco, 2016, pp. 912-917
  9. Bergmann, W., Hou, L.-Q., Energy Efficient Machine Condition Monitoring Using Wireless Sensor Networks, Proceedings, International Conference on Wireless Communication and Sensor Network (WCSN), Wuhan, China, 2014, pp. 285-290
  10. Sugumaran, V., et al., Fault Diagnostics of Roller Bearing Using Kernel Based Neighbourhood Score Multi-Class Support Vector Machine, Expert Systems with Applications, 34 (2008), 4, pp. 3090-3098

© 2022 Society of Thermal Engineers of Serbia. Published by the Vinča Institute of Nuclear Sciences, National Institute of the Republic of Serbia, Belgrade, Serbia. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial-NoDerivs 4.0 International licence