【摘要】 在径向基(RBF)神经网络和C-均值聚类算法的基础上,提出一种适用于电能质量复合扰动分类的多标签排位分类算法—多标签径向基函数法(ML-RBF)。首先,对常见的电能质量扰动及其组合而成的复合扰动进行离散小波分解,提取各层分解系数的规范能量熵作为特征向量;然后采用C-均值聚类算法将所得的特征向量映射为RBF神经网络的输入;最后通过RBF神经网络对该电能质量复合扰动类型进行预测。仿真实验结果表明,在不同的噪声条件下,ML-RBF可以有效分类识别电能质量复合扰动。更多还原

【Abstract】 A multi-label ranking learning method named ML-RBF is designed to identify the type of multiple power quality disturbances based on RBF neural networks and C-means clustering algorithm.Firstly,several common power quality disturbances and their compound ones are decomposed by discrete wavelet transform,and the norm energy entropy of the wavelet coefficients of each level are extracted as eigenvectors.And then,the eigenvectors are mapped into the input of the RBF neural networks using C-means clustering algorithm.Finally,the type of multiple power quality disturbances is predicted through the RBF neural networks.The simulation results show that ML-RBF can recognize the multiple power quality disturbances effectively under different noise conditions.更多还原