Bayesian Control Loop Diagnosis by Combining Historical Data & Process Knowledge of Fault Signatures
Process Knowledge of Fault Signatures
Dr. Omid Namaki Talk
Department of Electrical and Computer Engineering, University of Alberta,Canada
Venue: Advanced Control Systems Lab (ACSL)
Date & Time: 18th April 2015, 11-12
Many performance monitoring algorithms (or monitors) have been developed to assess control performance and detect problems with specific components; however, these algorithms monitor single components as stand-alone experts and can be influenced by other problems they were not meant to detect. Thus, the occurrence of a problem can lead to flood of abnormal monitor outputs and alarms which can be difficult to interpret. This work focuses on how to combine information from the many different monitoring algorithms and some of process knowledge in order to obtain a more reliable diagnosis. While traditional statistical or data based methods need data from all abnormal cases it should diagnose/isolate, this work focuses on how to improve the Bayesian control loop diagnosis by integrating process knowledge and training data when some of abnormality data are sparse or not available in historical database. Simulation of the proposed Bayesian diagnostic system on the Tennessee Eastman Challenge problem is presented. It is demonstrated that the diagnosis is possible even when there is no training data (or only few samples) from some abnormalities.
About the speaker:
Omid Namaki received the B.Sc. and M.Sc. degrees in Electrical Engineering (control systems) from University of Tehran, Tehran, Iran, in 2002 and 2005, respectively and the Ph.D. degree in Electrical Engineering (control systems) from K.N. Toosi University of Technology, Tehran, Iran, 2011.
He was a researcher with the Research Institute of Petroleum Industry, Tehran, from 2011 to 2012 and process control engineer in Farineh Fanavar Company in the field of industrial control and automation. He joined University of Alberta as a Postdoctoral Fellow in July 2013, where he is currently with the Department of Electrical and Computer Engineering. His research interests include advanced process control, abnormal event management, switching supervisory control, robust adaptive control and nonlinear control systems.