Association rules mining based analysis of consequential alarm sequences in chemical processes

• The proposed alarm association rule mining algorithm integrates the fuzzy set, Apriori algorithm and time sequence.
• The time-series discretization sliding windows is introduced based on the alarm sequences interval and weighted.
• Establishing fuzzy-driven causal knowledge bases and compatible fuzzy inference mechanism.
• The results which are represented by linguistic rules can be used to provide appropriate suggestions to operators.

In the context of industrial alarm rationalization, the analysis of consequential alarms is helpful for finding out root alarms so as to avoid alarm flooding. Motivated by this idea, this paper introduces a weighted fuzzy association rules mining approach to discovering correlated alarm sequences. Combining fuzzy sets, Apriori algorithms and alarm time series analysis, the algorithm does not search the entire item sets to find out root causes of consequential alarms. Furthermore, by transforming the association rules into fuzzy-driven causal knowledge bases and establishing the compatible fuzzy inference mechanism, a rationalized alarm topology is eventually created. Experimental results of a chemical plant show that the novel approach taking advantage of fuzzy inferences and data mining strategies is potentially effective to remove redundant alarm sequences.