Power plant monitoring and diagnosis: Development of a visual steady state detector
Monitorización y diagnóstico de centrales térmicas: desarrollo de un detector visual de estados estacionarios
| 2014 | |
|
Series temporales Minería de datos Diagnostico Pronóstico Generadores de vapor Time series Data-mining Diagnosis Prognosis Steam generators |
|
| Español | |
| Universidad de Montevideo | |
| REDUM | |
| http://revistas.um.edu.uy/index.php/ingenieria/article/view/346 | |
| Acceso abierto | |
| Atribución 4.0 Internacional |
| Sumario: | The design and features of a Matlab® application, focused to providing support for data mining by serial time computing is presented. The input data come from both historical records from industrial (thermo-energetic) processes but also it can be generated by direct simulation through the Simulink application. The aim of this study is the monitorization of the different quasi-stationary states (QSS) in a power plant, in order to identify and perform the diagnosis of possible malfunctions. Up to 8 signals, linearly normalized and distributed can be visualized and the user, by means of two cursors, can select short windows of recorded signals. In this version, statistical data are computed, facilitating the static modeling which can be exported to an Excel file. It is an open software application allowing the implementation of new features. A particular command makes easier the dynamic modeling and its applicability is exemplified by analysis of times series from a particular 250 MWe thermal power plant. |
|---|
