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.
|Number of pages||6|
|Publication status||Published - 1 Dec 2009|
|Event||ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings - |
Duration: 1 Dec 2009 → …
|Conference||ICINCO 2009 - 6th International Conference on Informatics in Control, Automation and Robotics, Proceedings|
|Period||1/12/09 → …|
Copyright 2010 Elsevier B.V., All rights reserved.
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
- Computer Vision and Pattern Recognition
- Control and Systems Engineering