A dependency model-based approach for identifying and evaluating power quality problems

The purpose of this paper is to present a diagnostic system that will not only monitor sensor data streams, but also classify power conditions, and diagnose power quality problems both in real-time and off-line. Signal processing techniques are applied to extract features from monitored data for event detection and classification. A cause-effect relationship model is used to trace the power quality related events to particular equipment of a system under consideration. The methodology has been implemented in a software tool. Results obtained from the application of this tool on monitored data collected from a facility validate the utility of this approach.