Projection Strategies for Data-driven Intelligent Monitoring: from Information Poor to Information Rich Processes
Date: 23 Nov 2004 - 23 Nov 2004
Venue: Auditorium, Tower Block, SIMTech, 71 Nanyang Drive
Industrial processes typically experience abnormal conditions that may lead to out-of-specification products or even process shutdown. These abnormal conditions are often related to the same root causes. Data-driven process fault diagnosis techniques are often employed in process industries due to their ease of implementation, requiring very little modelling effort and prior information. Given that there are multiple datasets in the process historical database, associated with different normal and abnormal conditions, the final goal is to monitor the performance of a process over time, with emphasis on the detection of 'unnatural' events which ultimately lead to a degradation or violation of the product quality. The isolation of these events leads to the allocation of a cause, which, if eliminated, results in an increased consistency and control of the final product specification.
In this presentation, starting from the basic fundamental ideas behind these projection strategies for fully data-driven process monitoring strategies, a number of extensions will be discussed to eliminate some of the current limitations. Among them: robust strategies will be considered to deal with poor quality data typically found in industrial applications; nonlinear extensions to cope with the inherent nonlinear process characteristics and multi-scale approaches to capture information in both the time and frequency domains to deal with localised features.
Professor Romagnoli currently holds the Chair in Process Systems Engineering at the Department of Chemical Engineering at University of Sydney. He is also the Director of the Laboratory for Process Systems Engineering. He received his Bsc (Chem Eng) at the National University of the South (Argentina) 1974, and his PhD (Chem Eng) at the University of Minnesota in 1980. He is the author of more than 250 international publications and the book of “Data processing and reconciliation for chemical process operations” published by Academic Press International. He is a member of the Australian Academy of Technological Sciences and Engineering and consultant of several international companies. He has been awarded the Centenary Medal by the Prime Minister of Australia for his contributions to chemical engineering. His research interests are Process Systems Engineering for data processing and reconciliation, modelling of complex systems, advanced model-based control and intelligent process monitoring and supervision.