Recognition of multiple power quality disturbances using multi-label RBF neural networks

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.