(142b) Big Data Analytics for Upstream Processes

Authors: 
Huang, B., University of Alberta
Modern industries are awash with large amount of data. Extraction of information and knowledge discovery from data, particularly from day by day routine process operating data, is especially challenging. There exist numerous challenging issues such as data nonlinearity, non-Gaussian distributions, high dimensionality, collinearity, multiple modal operations, outlying points, missing measurement etc that must be considered during the information extraction process. This presentation will discuss state-of-the-art development of data analytics to deal with these issues and to develop predictive models, soft sensors, fault detection and diagnosis monitors, and optimization from data for upstream processes, particularly oil sands processes. The concept of data analytics is illustrated in detail by a number of applications. The success of big data analytics in industrial applications will be elaborated.
Topics: