PROJECT TITLE :

Using disturbance records to automate the diagnosis of faults and operational procedures in power generators

ABSTRACT:

Today, it is a typical apply in power generation utilities to observe the generation units using digital fault recorders. As the disturbance records are usually analysed and stored at a central office or management centre, it's become tough for engineers to analyse all this data. Some of the main steps in developing automated diagnosis tools to help in this task are the segmentation and have extraction of the recorded signals and decision making. This study presents a strategy to extract meaningful data from every phase of a disturbance signal. Within the approach described in this study, the segmentation is performed by an extended complicated Kalman filter. The main features extracted from each phase are symmetrical elements at elementary frequency of voltage and current signals. Feature Extraction uses root-mean-square values to obtain the symmetrical elements of the 3 phase quantities. This methodology focuses on offline analysis of fault recorder knowledge of power generators and it's developed not only to fault analysis, however additionally to verify traditional operational procedures, from which result most of the disturbance records. This study additionally describes an knowledgeable system which will be used to automatically classify every record into known classes, focusing the engineer's attention to the foremost relevant occurrences.