Using Event-Intervals to Analyze Alarm Sequences in a Chemical Plant
Faculty of Computing, Health and Science
School of Computer and Security Science
A data mining approach is designed to support alarm rationalization by discovering correlated sets of alarm tags. The proposed approach is evaluated using simulation data from a model of the Vinyl Acetate chemical process as well as real plant alarm data. Results show that the propsed approach, using an event segmentation and data filtering strategy based on a cross-effect test, is significant.