Using phasor data records and sequence of events to automate the classification of disturbances of p

Abstract Nowadays, it is a common practice in power generation utilities to monitor the generation units using digital fault recorders (DFRs). As the disturbance records are in general, analyzed and stored at the central office or control center, it has become difficult for engineers to analyze all this data. This paper presents a preprocessing methodology that automatically analyzes and classifies each record into known categories, focusing the engineer’s attention to the most relevant occurrences. The scheme uses phasor records from DFR and the sequence of events (SOE) to achieve this. The data is pre-processed and then submitted to a set of expert systems in order to conclude the cause of the occurrence. Hundreds of real disturbance records and their corresponding SOE were used to evaluate the proposed scheme. The results show that about 95% of the records do not need further analysis and can be automatically stored without human intervention. The scheme is important in order to reduce the time spent with the disturbance analysis.