PHM 2019 Keynote Speech 3

Data-Driven Fault Detection in Distributed Large-Scale Processes


Reducing uncertainties in process data is an efficient way to improve fault detection performance in large-scale industrial processes. To this end, two basic principles can be followed: (i) increasing information redundancy, for instance, by using redundant sensors (ii) using correlation relations among the process variables. In this talk, numerous schemes, methods and associated algorithms are presented aiming at reliable fault detection in distributed large-scale processes, which are recently developed at AKS.


Steven X. Ding avatar
Steven X. Ding Germany

Institute for automatic control and complex systems (AKS), University of Duisburg-Essen, Germany

Steven Ding received Ph.D. degree in electrical engineering from the Gerhard-Mercator University of Duisburg, Germany. He was a R&D engineer at Rheinmetall GmbH in Germany and became a professor of control engineering at the University of Applied Science Lausitz in Senftenberg, and served as a vice president of this university during 1998 – 2000. Since 2001, he has been a chair professor of control engineering and the head of the Institute for Automatic Control and Complex Systems (AKS) at the University of Duisburg-Essen. His research interests are model-based and data-driven fault diagnosis, control and fault-tolerant systems as well as their applications in industry with a focus on automotive systems, chemical processes, renewable energy systems and distributed automatic control systems.