Pattern Extraction From Industrial Alarm Flood Sequences by a Modified CloFAST Algorithm
- 6 April 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 18 (1) , 288-296
Abstract
Alarm systems are critical for process safety and efficiency of complex industrial facilities. However, the presence of alarm floods severely compromises the performance of alarm systems. To cope with alarm floods, data mining has been applied to discover interesting patterns from historical alarm data, and such patterns can be used for alarm suppression, root cause analysis, and decision supports. However, most existing methods ignored the timestamps in pattern extraction or obtained complete patterns with significant redundancy. In this article, a new method is proposed to extract alarm flood patterns using a modified CloFAST algorithm. The contributions are twofold: first, a closed alarm sequence mining approach is proposed based on the CloFAST algorithm with improvements to incorporate timestamps and tolerate alarm order switchings; second, a pattern distillation strategy is designed to merge similar alarm sequences and export compact alarm sequential patterns. The proposed method is capable of avoiding influences of order ambiguities and also minimizing the redundancy of extracted patterns. The effectiveness of the proposed method is demonstrated by an industrial case study involving alarm data from a large-scale industrial facility.Keywords
Funding Information
- Natural Sciences and Engineering Research Council of Canada
- National Natural Science Foundation of China (61903345)
This publication has 26 references indexed in Scilit:
- An accelerated alignment method for analyzing time sequences of industrial alarm floodsJournal of Process Control, 2017
- Discovering Association Rules of Mode-Dependent Alarms From Alarm and Event LogsIEEE Transactions on Control Systems Technology, 2017
- A local alignment approach to similarity analysis of industrial alarm flood sequencesControl Engineering Practice, 2016
- Association rules mining based analysis of consequential alarm sequences in chemical processesJournal of Loss Prevention in the Process Industries, 2016
- Fault template extraction to assist operators during industrial alarm floodsEngineering Applications of Artificial Intelligence, 2016
- A weighted dissimilarity index to isolate faults during alarm floodsControl Engineering Practice, 2015
- CloFAST: closed sequential pattern mining using sparse and vertical id-listsKnowledge and Information Systems, 2015
- Criteria-based alarm flood pattern recognition using historical data from automated production systems (aPS)Mechatronics, 2015
- An Overview of Industrial Alarm Systems: Main Causes for Alarm Overloading, Research Status, and Open ProblemsIEEE Transactions on Automation Science and Engineering, 2015
- Pattern matching of alarm flood sequences by a modified Smith–Waterman algorithmChemical Engineering Research and Design, 2013