With the increasing wind capacity, the proportion of wind power in the grid is getting higher. Therefore, it is critical for the stable operation of the power grid to find out the location of the wind turbine failures. This paper proposes a fault diagnosis method of the wind turbine converter based on the deep belief network. Firstly, multiscale analysis of the signal is carried out by using wavelet transform to extract the characteristic vector of fault signal. DBN is used to obtain fault recognition models by supervised learning that uses the feature vector. Finally, the simulation results reveal that the method has a good ability to identify the converter fault.
CITATION STYLE
Liu, Y., Chai, Y., Wei, S., & Luo, Z. (2018). Circuit fault diagnosis method of wind power converter with wavelet-DBN. In Lecture Notes in Electrical Engineering (Vol. 460, pp. 623–633). Springer Verlag. https://doi.org/10.1007/978-981-10-6499-9_60
Mendeley helps you to discover research relevant for your work.