带标签信息子字典级联学习的复合电能质量扰动识别方法

Multiple power quality disturbances identification method with label information based on sub dictionary concatenate learning

针对传统字典学习方法的训练样本信号单一、重构效果差等缺点,提出一种带标签信息子字典级联的学习方法,对电能质量扰动信号进行扰动识别。该方法首先对不同类别电能质量扰动测试和训练样本采用主成分分析方法进行降维特征提取,对训练样本添加标签信息,其次对不同类别的电能质量样本训练成冗余子字典并级联成结构化字典,最后将级联的字典优化学习并由冗余误差最小值来判断目标的归属类别。仿真实验结果表明,该方法下的识别效果优于支持向量机(SVM)和稀疏表达分类(SRC),抗噪声鲁棒性更强,在信噪比20 dB以上的环境中电能质量复合扰动识别率达到91.40%以上。

Aiming at the drawbacks of traditional dictionary learning methods, such as single sample signal and poor reconstruction effect, a new approach of sub-dictionary concatenate learning （SDCL）with label information was proposed to identify the power quality disturbances （PQD） signal. Firstly, the different types of testing and training of the PQD signal samples are dimension reduced feature extraction with principal component analysis （PCA）, add the label information to train samples, then the different categories of power quality samples are trained into redundant sub-dictionary and concatenated into structured dictionary. Finally, using dictionary learning algorithm to optimize the structured dictionary and the object class is determined through minimizing the redundant error. The simulation results show that the recognition effect of SDCL method is better than that of SVM and SRC, and has good anti-noise robustness, and the multiple PQD identification rate reaches above 91.4% in the noisy circumstance with the signal to noise ratio above 20 dB.