A new approach to recognize multiple power quality disturbances is proposed. Firstly, based on S-transform five kinds of features in power quality disturbance signals are extracted and using fast Fourier transform (FFT) combined with dynamic measure method six features in power quality disturbance signals are extracted. Disturbance signals are characterized by these features from the baseband, intermediate frequency, high-frequency, standard deviation of the fundamental frequency, extreme point symmetry and variations of spectrum. Characteristics aliasing or failures because of interferences between the single disturbance were fully considered in this method. Then a classifier is designed with eight rules in the form of “IF- THEN”, finally features were input into the rule-based classifier for the disturbance identification. Simulation results show that the method can effectively recognize the compound power quality disturbances with the noise including eight single disturbances and eighteen double disturbances.