Power electronic converter nonlinear identification method based on multi-entropy feature extraction

Abstract

The invention provides a power electronic converter nonlinear identification method based on multi-entropy feature extraction. The method is mainly based on ensemble empirical mode decomposition, Hilbert transform and a least square support vector machine. The method comprises: sequentially solving the power spectrum entropy of the original signal x(t), solving the EMD energy entropy of the effective IMF component R-IMF obtained by screening after EEMD decomposition, and solving the time-frequency information, namely time-frequency spectrum entropy, contained in the original signal after Hilbert transformation is carried out on the R-IMF. The multiple entropies are used as different feature information of the same class to be input into the LS-SVM model, and through training of the model,high accuracy is achieved for recognition of some nonlinear phenomena in the power electronic converter.

Description

technical field [0001] The invention belongs to the field of stability analysis of power electronic converters, and relates to a nonlinear identification method of power electronic converters based on multiple entropy value feature extraction. Background technique [0002] Compared with traditional linear power supplies and motor-type AC and DC power supplies, power electronic converters have the advantages of small size, light weight, low cost, and powerful functions. Power electronic converters have gradually become the main power conversion devices, such as long-distance power transmission converter stations, photovoltaic power generation, wind power generation and other new energy sources to achieve efficient conversion of electric energy is inseparable from power electronic converters. [0003] According to the design requirements, when the power electronic converter is controlled, the nonlinear behavior of the power electronic converter is often caused by improper para...

AI Technical Summary

Problems solved by technology

However, the difference in entropy values ​​obtained through the power spectrum is small, and it is impossible to accurately distinguish various nonlinear behaviors in power electronic converters.

Images