论文部分内容阅读
该文提出一种多标签排位小波支持向量机(rank wavelet support vector machine，Rank-WSVM)，并将其应用于电能质量复合扰动分类中。Rank-WSVM将小波技术与多标签排位支持向量机(Rank-SVM)结合，利用小波的优良特性提高分类器的整体性能。首先，对电能质量扰动信号进行离散小波分解，计算 Tsallis 小波熵作为特征向量；然后利用所提出的 Rank-WSVM 多标签分类器进行分类。仿真结果表明，在不同噪声条件下，该方法有效改善了Rank-SVM的分类性能，可有效识别电压暂降、电压暂升、电压短时中断、脉冲暂态、振荡暂态、谐波和闪变等电能质量扰动及其组合而成的复合扰动。“,”Multi-label rank wavelet support vector machine (Rank-WSVM) is proposed and applied to the recognition of multiple power quality disturbances in this paper. By applying the wavelet technique to Rank-SVM classifier the efficiency is improved. Firstly, all of the common power quality disturbances and their compound ones are decomposed by discrete wavelet transform, and the Tsallis entropy of the wavelet coefficients are extracted as eigenvectors. And then, the type of multiple power quality disturbances is predicted through the Rank-WSVM. The simulation results show that Rank-WSVM proposed in this paper can effectively recognize the multiple power quality disturbances including voltage sag, voltage swell, voltage interruption, impulsive transient, oscillation transient, harmonics, flicker and their compound ones under different noise conditions.