A method for PQ multiple disturbance decomposition based on digital filtering and Independent Component Analysis

This paper proposes a method for Power Quality disturbance analysis based on Independent Component Analysis. This method aims to decompose power system signals (voltage or current) into their isolated disturbances when a multiple disturbance situation occurs, providing more specific information about the different disturbances which occur simultaneously. As the Independent Component Analysis is originally a technique applied to Multivariate Data Analysis, this work proposes a methodology for its application when only a single measured signal is available. The performance of the technique is evaluated using synthetic, as well as actual power system signals.