| 引用本文: | 李夏林,刘雅娟,朱武.基于配电网的复合电压暂降源分类与识别新方法[J].电力系统保护与控制,2017,45(2):131-139.[点击复制] |
| LI Xialin,LIU Yajuan,ZHU Wu.A new method to classify and identify composite voltage sag sources in distribution network[J].Power System Protection and Control,2017,45(2):131-139[点击复制] |
|
| 摘要: |
| 为了对配电网含有谐波情况下的复合电压暂降源进行分类与识别，提出了一种基于特征值综合法的复合电压暂降源分类与识别新方法。首先根据不同复合电压暂降源所引起的电压暂降波形特征的不同，定义三相电压不平衡度，将含单相接地类的复合电压暂降源与感应电机启动和变压器投入相复合的电压暂降源进行区别。然后定义交叉不平衡度并结合二次谐波电压含量对含单相接地类故障中的各类复合电压暂降源进行区分。最后利用马氏距离与概率神经网络相结合的方法对各类复合电压暂降源的故障顺序进行识别，进而形成完整的复合电压暂降源种类和故障顺序识别新方法。通过仿真实验对所提方法进行了验证，结果表明该方法能够很好地对复合电压暂降源的种类和故障顺序进行分类识别，且识别正确率高于96%。此外，所提出的分类方法还与EMD能谱熵和概率神经网络相结合的方法进行了对比分析，对比结果表明，所提方法的识别效果明显优于后者。 |
| 关键词: 复合电压暂降源 不平衡度 交叉不平衡度 马氏距离 概率神经网络 |
| DOI：10.7667/PSPC160134 |
| 投稿时间：2016-01-24修订日期：2016-06-16 |
| 基金项目:上海市教委科研创新重点项目(11ZZ173);上海市科技创新行动计划地方院校能力建设项目(10110502200,11510500900) |
|
| A new method to classify and identify composite voltage sag sources in distribution network |
| LI Xialin,LIU Yajuan,ZHU Wu |
| (College of Electronics and Information Engineering, Shanghai University of Electric Power, Shanghai 200090, China;Zhengzhou Power Supply Company, Zhengzhou 450006, China) |
| Abstract: |
| In order to classify the kinds and fault sequence of composite voltage sag sources in distribution network with harmonic, a new method to classify these composite voltage sag sources is proposed. Firstly, according to different voltage sag waveforms triggered by different types of voltage sag sources, the composite voltage sag sources containing single-phase grounding fault are classified from the composite voltage sag source consisted of transformers and induction motor. Then the intersection unbalanced degree and second-harmonic are employed to classify the composite voltage sag sources containing single-phase grounding fault. Additionally the fault sequence is classified through Mahalanobis distance and probability neural network, and a complete classification and identification method is formed. Finally, the proposed method is verified through simulation experiment, the results show that this method can well classify the kinds and fault sequence of composite voltage sag sources, and recognition accuracy is higher than 96%. In addition, the proposed method is compared with the method of the combination of EMD energy entropy and PNN, the comparison result shows that the accuracy of the proposed method is superior to the latter’s. This work is supported by Shanghai Municipal Education Commission Key Projects of Scientific Research and Innovation (No. 11ZZ173) and Local Colleges and Universities of Shanghai Science and Technology Innovation Action Plan Ability Construction Projects (No. 10110502200 and No. 11510500900). |
| Key words: composite voltage sag sources unbalanced degree intersect unbalanced degree Mahalanobis distance probability neural network |
