Fault diagnosis of wind turbine based on H-SKDB model
DOI: 10.23977/acss.2020.040101 | Downloads: 14 | Views: 566
Baoyi Wang 1, Dongbing Yuan 1, Shaomin Zhang 1
1 School of Control and Computer Engineering,North China Electric Power University,Baoding 071003,China
Corresponding AuthorBaoyi Wang
The wind farm is in a bad wind area, which causes wind turbine faults to occur. Fault diagnosis of wind turbines is helpful for the maintenance and operation of wind turbines. The SKDB (Extensible Bayesian Network) model has the characteristics of high fault diagnosis accuracy and short training time. Based on the SKDB model, the Bayesian network structure is constructed by the method of mutual information addition calculation, then a fault diagnosis model of wind turbine based on H-SKDB is proposed, which realizes the fault diagnosis of wind turbine equipment information status. The experimental results show that the fault diagnosis method has higher calculation accuracy and shorter calculation time.
KEYWORDSBayesian Network, Fault Diagnosis, Wind Turbine, H-SKDB
CITE THIS PAPER
Baoyi Wang, Dongbing Yuan and Shaomin Zhang. Fault diagnosis of wind turbine based on H-SKDB model. Advances in Computer, Signals and Systems (2020) 4: 1-6. DOI: http://dx.doi.org/10.23977/acss.2020.040101.
 Y. Li, S. Liu, and L. Shu, “Wind turbine fault diagnosis based on Gaussian process classifiers applied to operational data,” Renewable Energy, vol. 134, pp. 357–366, Apr. 2019.
 A. M. Martinez, G. I. Webb, S. Chen, and N. A. Zaidi, “Scalable Learning of Bayesian Network Classifiers,” Journal of Machine Learning Research, vol. 17, no. 44, pp. 1–35, 2016.
 A. Lebranchu, S. Charbonnier, C. Bérenguer, and F. Prévost, “A combined mono- and multi-turbine approach for fault indicator synthesis and wind turbine monitoring using SCADA data,” ISA Transactions, Dec.2019. 87: p. 272-281.
 T. S. Abdelgayed, W. G. Morsi, and T. S. Sidhu, “A New Approach for Fault Classification in Microgrids Using Optimal Wavelet Functions Matching Pursuit,” IEEE Transactions on Smart Grid, vol. 9, no. 5, pp. 4838–4846, Sep. 2018.
 F. Petitjean, W. Buntine, G. I. Webb, and N. Zaidi, “Accurate parameter estimation for Bayesian network classifiers using hierarchical Dirichlet processes,” Machine Learning, vol. 107, no. 8–10, pp. 1303–1331, Sep. 2018.
 J. Li, X. Zhang, X. Zhou, and L. Lu, “Reliability assessment of wind turbine bearing based on the Degradation-Hidden-Markov model,” Renewable Energy, vol. 132, pp. 1076–1087, Mar. 2019.
 G. Helbing and M. Ritter, “Deep Learning for fault detection in wind turbines,” Renewable and Sustainable Energy Reviews, vol. 98, pp. 189–198, Dec. 2018.
 J. Lei, C. Liu, and D. Jiang, “Fault diagnosis of wind turbine based on Long Short-term memory networks,” Renewable Energy, vol. 133, pp. 422–432, Apr. 2019.
 S. Shi, B. Zhu, S. Mirsaeidi, and X. Dong, “Fault Classification for Transmission Lines Based on Group Sparse Representation,” IEEE Transactions on Smart Grid, vol. 10, no. 4, pp. 4673-4682, July 2019.
 J.-Y. Zhou, F.-Y. Wang, and D.-J. Zeng, “Hierarchical Dirichlet Processes and Their Applications: A Survey: Hierarchical Dirichlet Processes and Their Applications: A Survey,” Acta Automatica Sinica, vol. 37, no. 4, pp. 389–407, Jul. 2011.
 Zheng, Haiyang & Song, Zhe. (2009). Models for Monitoring of Wind Farm Power. Renewable Energy. 34. 583-590.