Mining Industrial Logs for System Level Insights

Abstract

Industrial systems are becoming more and more complex and expensive to operate. Companies are making considerable efforts to increase operational efficiency and eliminate unplanned downtime of their equipment. Condition monitoring has been applied to improve equipment availability and reliability. Most of the condition monitoring applications, however, focus on single components, not on entire systems. The objective of this research was to demonstrate that a combination of visual analytics and association rule mining can be successfully used in a condition monitoring context on system level.