Resumen
A comparison between the Dynamic Principal Component Analysis (DPCA) method and a bank of Diagnostic Observers (DO) under the same experimental data from a shell and tube industrial heat exchanger is presented. The comparative analysis shows the performance of both methods when sensors and/or actuators fail. Different metrics are discussed (i.e. robustness, quick detection, isolability capacity, explanation facility, false alarm rates and multiple faults identifiability). DO showed quicker detection for sensor and actuator faults with lower false alarm rate. Also, DO can isolate multiple faults. DPCA required a minor training effort; however, it cannot identify two or more sequential faults.
Idioma original | English |
---|---|
Páginas | 265-270 |
Número de páginas | 6 |
Estado | Published - 1 dic 2009 |
Publicado de forma externa | Sí |
Evento | ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings - Duración: 1 dic 2009 → … |
Conference
Conference | ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings |
---|---|
Período | 1/12/09 → … |
All Science Journal Classification (ASJC) codes
- Inteligencia artificial
- Visión artificial y reconocimiento de patrones
- Ingeniería de control y sistemas