基于SVM的电压扰动识别研究

Research on voltage disturbance recognition based on SVM

针对电力系统中出现的电压暂升(暂降、暂断)以及谐波、电压脉冲和电压闪变这六种常见电压扰动进行建模,将特征量输入到SVM进行电能质量扰动多类分类。首先采用相应小波包分解算法将电能质量中某一频段内的信号分解到特定频段上,其次在这些特定频段上提取特征向量,最后针对该特征向量构造相应支持向量机分类器。结果表明,在较复杂的电能质量扰动情况中,支持向量机分类器仍能实现对信号的精确分类,对电能质量监测具有很好的应用价值。

The six common voltage disturbances such as voltage sag(temporary break) and harmonics, voltage pulse and voltage flicker appear in the power system are modeled, and the feature quantity is input into the SVM to classify the power quality disturbance. Firstly, the corresponding wavelet packet decomposition algorithm is used to decompose the signal in a certain frequency band of power quality into a specific frequency band, and simulate the complex interference signal in the actual power grid. Feature vectors are then extracted on these particular frequency bands. Finally, construct the corresponding support vector for the feature vector. The results show that the support vector machine classifier can still accurately classify the signal in more complex power quality disturbances, which has good application value for power quality monitoring.