Prof. Sirish L. Shah

Department of Chemical and Materials Engineering
University of Alberta, Canada


Process data analytics: From process and performance monitoring to causality capture…..the road less travelled


It is now common to have archival history of thousands of sensors sampled every second over long time periods. Yet we frequently have process engineers complain: “….We are drowning in data but starving for information…”. How can these rich data sets be put to use? This talk will address the issue of information and knowledge extraction from data with emphasis on process and performance monitoring including fault detection and isolation. Most of the major plant, factory, process, equipment and tool disruptions are avoidable, and yet preventable and predictive data analytics for fault detection and diagnosis are not the norm in most industries. It is not uncommon to see simple and preventable faults disrupt the operation of an entire integrated manufacturing facility. For example, faults such as malfunctioning sensors or actuators, inoperative alarm systems, poor controller tuning or configuration can render the most sophisticated control systems useless. Such disruptions can cost in the excess of $1 million per day and on the average they rob the plant of 7% of its annual capacity. Process data analytic methods rely on the notion of sensor fusion whereby data from many sensors or units are combined with process information, such as physical connectivity of process units, to give a holistic picture of health of an integrated plant. Such methods are at a stage where these strategies are being implemented for off-line and on-line deployment. Typical analytic methods require the execution of following steps: data quality assessment, outlier detection, noise filtering, data segmentation followed by process and performance monitoring including root cause detection of faults. For efficient and informative analytics, data analysis is ideally carried out in the temporal as well as spectral domains, on a multitude and NOT singular sensor signals to detect process abnormality. This presentation will discuss the field of process data analytics via industrial case studies. The case studies involve detection and investigation of root cause(s) of plant-wide oscillations that require the determination of process topology from process data, using Granger causality and transfer entropy methods, to explain the propagation of plant-wide disturbances.

Brief Biography:

Sirish L. Shah has been with the University of Alberta since 1978, where he is currentlyProfessor of Chemical and Materials Engineering and held the NSERC-Matrikon-Suncor-iCORE Senior Industrial Research Chair in Computer Process Control from 1999 to 2012. He was the recipient of the Albright & Wilson Americas Award of the Canadian Society for Chemical Engineering (CSChE) in recognition of distinguished contributions to chemical engineering in 1989, the Killam Professor in 2003 and the D.G. Fisher Award of the CSChE for significant contributions in the field of systems and control in 2006. He has held visiting appointments at Oxford University and Balliol College as a SERC fellow , Kumamoto University (Japan) as a senior research fellow of the Japan Society for the Promotion of Science (JSPS) , the University of Newcastle, Australia, IIT-Madras, India and the National University of Singapore. The main area of his current research is process and performance monitoring, system identification and design and implementation of softsensors. He has co-authored two books, the first titled, Performance Assessment of Control Loops: Theory and Applications, and a recent book titled ‘Diagnosis of Process Nonlinearities and Valve Stiction: Data Driven Approaches”.