Discovering Association Rules of Mode-Dependent Alarms From Alarm and Event Logs

State-based or condition-based alarming has emerged as a prevalent method to reduce nuisance alarms and inhibit alarm floods in the alarm management of process industries. Such a strategy minimizes the number of active alarms by modifying alarm attributes or suppression status based on certain conditions. However, the configuration of state-based alarms in practice relies on process knowledge, making it time and resource intensive. In order to identify associations between alarms and states, this paper proposes a completely automated data-driven method to detect mode-dependent alarms from alarm and event (A&E) logs, where the messages of alarms and operating modes are stored. Algorithms to detect frequent patterns of operating modes and association rules of mode-dependent alarms are proposed. The effectiveness and applicability of the proposed method are demonstrated by case studies involving real industrial A&E data sets.

[1]  Nina F. Thornhill,et al.  A combined analysis of plant connectivity and alarm logs to reduce the number of alerts in an automation system , 2013 .

[2]  Tongwen Chen,et al.  A local alignment approach to similarity analysis of industrial alarm flood sequences , 2016 .

[3]  Ramakrishnan Srikant,et al.  Fast algorithms for mining association rules , 1998, VLDB 1998.

[4]  Dustin Beebe,et al.  The Connection of peak alarm rates to plant incidents and what you can do to minimize , 2013 .

[5]  Neil Brown.  Alarm Management/The EEMUA Guidelines in Practice , 2003 .

[6]  Sylvie Charbonnier,et al.  A weighted dissimilarity index to isolate faults during alarm floods , 2015 .

[7]  Brandon Parker,et al.  How to Avoid Alarm Overload with Centralized Alarm Management , 2010 .

[8]  Gintaras V. Reklaitis,et al.  Intelligent Alarm Management Applied to Continuous Pharmaceutical Tablet Manufacturing: An Integrated Approach , 2013 .

[9]  Chonghun Han,et al.  On-Line Process State Classification for Adaptive Monitoring , 2006 .

[10]  Wenjun Huang,et al.  A distributed parallel alarm management strategy for alarm reduction in chemical plants , 2015 .

[11]  Wilhelmiina Hämäläinen,et al.  StatApriori: an efficient algorithm for searching statistically significant association rules , 2010, Knowledge and Information Systems.

[12]  Sirish L. Shah,et al.  An Overview of Industrial Alarm Systems: Main Causes for Alarm Overloading, Research Status, and Open Problems , 2016, IEEE Transactions on Automation Science and Engineering.

[13]  Douglas H Rothenberg,et al.  Alarm Management for Process Control: A Best-Practice Guide for Design, Implementation, and Use of Industrial Alarm Systems , 2009 .

[14]  Tongwen Chen,et al.  A new method to detect and quantify correlated alarms with occurrence delays , 2015, Comput. Chem. Eng..

[15]  Suvomoy Bhaumik,et al.  Mode Based Alarm Solutions at Syncrude Canada , 2015 .

[16]  Dal Vernon C. Reising,et al.  Addressing alarm flood situations in the process industries through alarm summary display design and alarm response strategy , 2014 .

[17]  Iman Izadi,et al.  Pattern matching of alarm flood sequences by a modified Smith–Waterman algorithm , 2013 .

[18]  Jean-Pierre Derain,et al.  A methodology of alarm filtering using dynamic fault tree , 2011, Reliab. Eng. Syst. Saf..

[19]  Fan Yang,et al.  A dynamic alarm management strategy for chemical process transitions , 2014 .

[20]  Marek Sikora,et al.  Dynamic Alarm Management in Next Generation Process Control Systems , 2012, APMS.

[21]  Tongwen Chen,et al.  An online method to remove chattering and repeating alarms based on alarm durations and intervals , 2014, Comput. Chem. Eng..

[22]  Masaru Noda,et al.  Event correlation analysis for alarm system rationalization , 2011 .