基于S变换和人工神经网络的电能质量扰动识别

PQ disturbances identification based on S-transform and ANN

本文提出了一种基于S变换和人工神经网络的电能质量扰动识别方法。首先通过S变换对电能质量扰动信号进行时频分析,实现了各种扰动的有效检测,然后对该检测输出信号进行特征提取,得到包含扰动时频特性的训练和测试样本集,并运用人工神经网络进行扰动训练识别,最终实现电能质量扰动信号的自动分类。测试结果表明,该方法能有效识别参数大范围内随机变化的各种电能质量扰动。

A new method based on S-transform time-frequency analysis and ANN was presented for power quality (PQ) disturbances identification. Through S-transform time-frequency analysis, the method detects out the PQ disturbances effectively. Then, feature components were extracted from the detecting outputs for classification. Finally ANN was used to identify of PQ disturbances. The testing results show that the proposed method could classify the PQ disturbances effectively.