Wind power companies are increasingly introducing fault diagnosis technologies, however, the full use of these technologies mainly depends on expert experience. This paper puts forward a fault identification method for the intelligent fault identification of wind turbine based on fault knowledge base. The model uses principal component analysis to integrate the eigenvalues of vibration and SCADA signals, and then takes the existing fault sample with the highest matching rate in the wind farm fault knowledge base as the input to train the least squares support vector regression algorithm model optimized by particle swarm optimization. The matching rates of fault samples in the fault knowledge base are updated after each diagnosis. Finally, the measured data of the wind farm are used to verify the effect of the model. It is proved that, if the fault samples are sufficiently trained, this method can accurately diagnose the existing faults from the fault base.
intelligent fault identification; knowledge base; data fusion; wind turbine
1. H.D. Peng, X.Q. Chen, M. Ren, D.Y. Yang, M. Dong, Intelligent Fault Diagnosis Technology and System for Wind Turbines, 2011, Advances of Power System and Hydroelectric Engineering, vol. 27, no. 2, pp. 61-66.
2. W.D Su, Application of Online Remote Fault Diagnosis System for Wind Turbine, 2015, Electric Safety Technology, vol. 17, no.5, pp. 63-65.
3. R. Razavi-Far, M. Kinnaert, A Multiple Observers and Dynamic Weighting Ensembles Scheme for Diagnosing New Class Faults in Wind Turbines, 2013, Control Engineering Practice, vol. 21, no. 9, pp. 1165–1177.
4. A. Aloraini, M. Sayed-Mouchaweh, Graphical Model Based Approach for Fault Diagnosis of Wind Turbines, 2014, International Conference on Machine Learning and Applications, pp. 614-619.
5. Y.J. Gu, Z.W. Jia, R. Wang, Y.T. Ren, Early Fault Diagnosis for Wind Turbine Gearbox Based on Improved Multivariate Outlier Detection, 2016, China Mechanical Engineering, vol. 27, no. 14, pp. 1905-1910.
6. Y.N. Qiu, J. Sun, M. Cao, H. Wang, Model Based Wind Turbine Gearbox Fault Detection on SCADA Data, 2014, IET Renewable Power Generation Conference, pp. 1-5.
7. Y.N. Qiu, Y.H. Feng, J. Sun, H. Wang, Applying Thermophysics for Wind Turbine Drivetrain Fault Diagnosis Using SCADA Data, 2016, IET Renewable Power Generation, vol. 10, no. 5, pp. 661-668.
8. H. Malik, S. Mishra, Application of Probabilistic Neural Network in Fault Diagnosis of Wind Turbine Using FAST, TurbSim and Simulink, 2015, Procedia Computer Science, vol. 58, pp. 186-193.
9. H. Alkhadafe, A. Al-Habaibeh, A. Lotfi, Condition Monitoring of Helical Gears Using Automated Selection of Features and Sensors, 2016, Measurement, vol. 93, pp. 164–177.
10. S.M. Zhang, D. Mao, B.Y. Wang, Application of Big Data Processing Technology in Fault Diagnosis and Early Warning of Wind Turbine Gearbox, 2016, Automation of Electric Power Systems, vol. 40, no.14, pp. 129-134.
11. Q. Wu, H.N. Cai, L.F. Huang, Feature-level Fusion Fault Diagnosis Based on PCA, 2011, Computer Science, vol. 38, no. 1, pp. 268-270.
12. Q. Xu, Y.Q. Liu, D. Tian, J.H. Zhang, Q. Long, Fault Diagnosis of Rolling Bearings Using Least Square Support Vector Regression Based on Glowworm Swarm Optimization Algorithm, 2014, Journal of Vibration and Shock, vol. 33, no. 10, pp. 8-12.
13. H.Q. Wei, Z.M. Niu, W.H. Jiang, Y.L. Ye, Application of LSSVR Optimized by Adaptive Genetic Algorithm at Modeling Igniting Temperature of Pulverized-Coal, 2011, Journal of Combustion Science and Technology, vol. 17, no. 3, pp. 191-195．