The immune system in a living organism serves the purpose of defending the organism from external intrusions such as microbes, viruses or foreign bodies. The immune system identifies the presence of an intrusion, isolates the intrusion and attempts to eliminate it, or at least eliminate its effects on the normal body function. Improper function or absence of the immune system could cause serious problems (e.g. leukemia, cancer or AIDS).
In this presentation, a novel approach for anomaly detection and fault isolation in complex dynamic systems, such as automotive or aircraft engines, will be presented. In the case of highly sophisticated systems, the traditional approach to diagnostics becomes excessively cumbersome because of the need to train the condition-monitoring unit to recognise a large number of faults under highly diverse control and environmental conditions, most of which often cannot be even anticipated in advance. The newly proposed approach is inspired by natural immune systems and achieved fault detection and isolation through distributed anomaly detection. This is realised through a new modelling approach for identification of non-linear dynamic systems, where the operational space of the system is divided through unsupervised clustering into regions, within which system behaviour can be modelled using simpler, analytically more tractable models. Theoretical findings will be presented regarding the dependency of model convergence and accuracy on the topological structure of the model. Implications of local model tractability to realising self-healing functionality through adaptive control will also be discussed.
About the Speaker
Dr Dragan Djurdjano graduated with a Bachelor of Science degree in Mechanical Engineering and Applied Mathematics in 1997 from the University of Nis (Serbia), a Master's degree in Mechanical Engineering from Nanyang Technological University in 1999, a Master of Science in Electrical Engineering (Systems) and a PhD in Mechanical Engineering in 2002 from the University of Michigan, Ann Arbor. As a Research Fellow of the University of Michigan, Dr Djurdiano's research interests include quality control, intelligent proactive maintenance techniques and applications of advanced signal processing in biomedical engineering. He co-authored fifty journal papers and conference publications. He received several prizes and awards, including the Nomination for the Distinguished PhD thesis from the Department of Mechanical Engineering, University of Michigan in 2002, and the outstanding paper award at SME North American Manufacturing Research Conference in 2001.
Who Should Attend
R&D Managers, researchers, engineers, professors and students.
This lecture is free of charge. Limited seats are available on a first-come, first-served basis.
To reserve a place, please email us (eventsPostmaster@SIMTech.a-star.edu.sg
), indicating your name, designation, company name, email address and contact number.