A fuzzy approach for disturbances diagnosis and fault classification in power plants

Abstract

The increase in the size of the current eletric power systems (EPSs) has led to the development of monitoring techniques of EPSs, which includes SCADA (Supervisory Control and Data Acquisition) systems, WAMS (Wide Area Measurement System) and also, disturbance records systems. Disturbance records systems are based on oscillographic records, generated by Digital Fault Recorders (DFRs) and allows the analysis electrical quantities and logical signals. Generally, in power plants, all the DRFs data are centralized in the utility data centre and this results in an excess of data that difficults in the task of analysis by the specialist engineers. This paper shows a methodology for automatic analysis of disturbances in power plants. A fuzzy reasoning system is proposed to deal with the data from the DFRs. The objective of the system is to help the engineer responsible for the analysis of the DRFs's information by means of a pre-classification of data and also, diagnose the relevant occurrences.