Detection of Frequent Alarm Patterns in Industrial Alarm Floods Using Itemset Mining Methods
By Wenkai Hu, Tongwen Chen, Sirish L. Shah. 2018
73 citations recorded by the source corpus.
The presence of alarm floods is identified as the main reason for low efficiency of alarm systems and the leading cause of many industrial accidents. In practice, a commonly used technique to deal with alarm floods is dynamic alarm suppression, which temporally suppresses predefined groups of alarms following unplanned events that are not relevant or meaningful to the operator. However, determining what alarms to suppress from a pool of thousands of configured alarm variables remains a challenging problem. This paper proposes a data-driven method to find such alarm groups by detecting frequent patterns in alarm floods from historical alarm data. Main contributions of this study are: 1) the identification and extraction of alarm floods are formulated; 2) frequent alarm patterns are defined and itemset mining methods are adapted to discover meaningful patterns in alarm floods; and 3) new visualization techniques are proposed based on exiting plots to show alarm floods and alarm patterns. The effectiveness of the proposed method is demonstrated by application to real industrial data.
Subfields: Artificial Intelligence, Information Systems, Signal Processing
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Information Systems
In Signal Processing
Citations in the corpus
- Black-Box vs. White-Box: Understanding Their Advantages and Weaknesses From a Practical Point of View (2019, methodology): “Contrast pattern-based classifiers have been applied in several practical problems, such as bot detection on twitter [9], road safety [138], crime pattern [139], cerebrovascular examination [140], describing political figures [141], sales trends [142], detection of frequent alarm patterns [143], bot”