Implementation and performance results of neural network for power quality event detection

A novel method to detect power quality event in distributed power system combing wavelet network with the improved back-propagation algorithm is presented. The paper tries to explain to design complex supported orthogonal wavelets by compactly supported orthogonal real wavelets, and then explore the extraction of disturbance signal to obtain the feature information, and finally propose several novel wavelet combined information to analyze the disturbance signal, superior to real wavelet analysis result. The feature obtained from WT coefficients are inputted into wavelet network for power quality disturbance pattern recognition. The power quality disturbance recognition model is established and the improved back-propagation algorithm is used to fulfill the network parameter initialization. By means of choosing enough samples to train the recognition model, the type of disturbance can be obtained when signal representing fault is inputted to the trained network. The results of simulation analysis show that the complex wavelet transform combined with wavelet network are more sensitive to signal singularity, and found to be significant improvement over current methods in real-time detection.