基于双分辨率S变换和学习向量量化神经网络的电能质量扰动检测方法

Detection Method of Power Quality Disturbances Based on Double Resolution S Transform and Learning Vector Quantization Neural Network

随着实际电网中非线性负荷以及冲击性负荷的不断增加,电能质量问题日趋严重。实现电能质量扰动信号的准确、快速检测对于查找电能质量问题根源、改善电能质量、确保电网安全、保障经济稳定具有重大意义。为此,提出一种基于双分辨率S变换和学习向量量化(LVQ)神经网络的电能质量扰动信号检测方法。算法先采用双分辨率S变换实现扰动信号特征向量的准确、快速提取。在获得扰动信号的特征向量后对各特征向量进行归一化处理并利用经过训练的LVQ神经网络对扰动信号进行分类识别。仿真和实际测试结果表明,该文提出的基于双分辨率S变换和LVQ神经网络的电能质量扰动检测算法具有训练速度快、分类准确率高、适合嵌入式实现等优点。

As the nonlinear loads and impact loads in power grid increase,the power quality problems are becoming more and more serious.Accurate and fast detection of power quality disturbance signals has great significance for finding the cause of power quality problems and improving the power quality.Therefore,an algorithm for recognizing power quality disturbance signals is proposed in this paper based on double resolution S-transform and learning vector quantization(LVQ)neural network.Firstly,double resolution S-transform is used to extract the feature vectors of disturbance signals accurately and quickly.Then,the obtained feature vectors of disturbance signals are normalized and the trained LVQ neural network is used to classify and identify the disturbance signals.The simulation and actual test results show that the proposed algorithm based on double resolution S-transform and LVQ neural network has fast training speed,high classification accuracy and is suitable for embedded implementation.