S-Transform technique for identifying the location of a switched capacitor

This paper presents an integration of S-Transform and Probabilistic Neural Network (PNN) technique for identifying the location of a switched capacitor causing a power quality problem. The transient caused by the capacitor switching is one of the important power quality (PQ) problems since it may adversely affect the system as well as sensitive loads. S-Transform has the ability to detect the disturbance correctly in the presence of noise riding on the signal. Hence, S-Transform technique is used for locating switched capacitors under noisy environment. In order to extract efficient features, capacitor switching signals are applied to two S-Transform algorithms and they are processed parallely. Those features are then applied to PNN for training and subsequently tested for automatic classification of switching signals. The simulation results reveal that the combination of S-Transform and PNN can effectively locate the switched capacitor even under the noisy environment.