Technology Lecture on Performance Assessment and Proactive Maintenance in Complex Dynamic Systems

Date: 29 Jul 2005 - 29 Jul 2005

Venue: SIMTech, Auditorium, Tower Block, Level 3


With the growing complexity of dynamic control systems, the effective diagnosis of all possible failures has become increasingly difficult and time consuming. The virtually infinite variety of behavior patterns of such systems due to control inputs and environmental influences further complicates system characterization and fault diagnosis. As a result, many systems rely on limited diagnostic coverage provided by a diagnostic strategy which tests only for known or anticipated failures, and presumes the system is operating normally if the full set of tests is passed. Furthermore, these tests are often developed separately and at substantial costs in terms of time and resources. To circumvent these difficulties and provide more complete coverage for the detection of any failure, a new diagnostic method will be described in this talk, consisting of two elements: the first, based upon anomaly detection, identifies any performance deviation from normal operation, and the second, fault isolation, isolates the problem, as best as possible, to the specific component or subsystem that does not operate properly. Our prescriptive method for diagnostic design relies on the use of Self-Organizing Maps (SOM) for regionalization of the system operating conditions, followed by the performance assessment module based on Time-Frequency Analysis (TFA) and Principal Component Analysis (PCA) for anomaly detection and fault isolation. The new diagnostic procedure is demonstrated in an example of automotive engine control system. Furthermore, brief history of the S.M. Wu Manufacturing Research Center at the University of Michigan as well as the research efforts in proactive, intelligent maintenance based on predictive information about equipment condition conducted at the Center for Intelligent Maintenance Systems in the University of Michigan will be briefly presented in this talk.

About Dr Dragan Djurdjanovic

Dragan Djurdjanovic obtained his B.S. in Mechanical Engineering and in Applied Mathematics in 1997 from the University of Nis, Yugoslavia, his M.Eng. in Mechanical Engineering from the Nanyang Technological University, Singapore in 1999, and his M.S. in Electrical Eng. (Systems) and Ph.D. in Mechanical Eng. in 2002 from the University of Michigan, Ann Arbor. His research interests include advanced quality control in multi-station manufacturing systems, intelligent proactive maintenance techniques in complex systems and applications of advanced signal processing in biomedical engineering. He co-authored 19 refereed journal publications, more than 30 conference papers and is the recipient of several prizes and awards, including the Nomination for the Distinguished Ph.D. Thesis from the Department of Mechanical Engineering, University of Michigan in 2002, the University of Michigan Engineering Research Center Graduate Student of the Year in 2002 and The Outstanding Paper Award at 2001 SME North American Manufacturing Research Conference. Dr. Djurdjanovic is a member of ASME, SME and Informs. He also serves as the Chair Panelist of the Manufacturing Systems panel of the Dynamics, Systems and Control Division of ASME.

This Technology Lecture is non-chargeable.

To register, please email your particulars (name, job title, company name) to