Real-time pattern matching and ranking for early prediction of industrial alarm floods. (March 2022)

• Record Type: Journal Article
• Authors: Parvez, Md Rezwan; Hu, Wenkai; Chen, Tongwen
• Is Part Of: Control engineering practice. Volume 120(2022)
• Publication Date: 2022-03
• Subjects: Alarm systems -- Alarm floods -- Similarity analysis -- Pattern matching -- Operator decision support; Automatic control -- Periodicals; 629.89
• DOI: 10.1016/j.conengprac.2021.105004
• Languages: English
• ISSNs: 0967-0661

Abstract

Abstract: Early prediction of an incoming alarm flood sequence can provide valuable information to industrial operators, so as to facilitate taking corrective actions in time. A real-time pattern matching and ranking approach is proposed in this work to conduct similarity analysis under an online alarm flood situation and to export the results as a ranking list of historical alarm flood sequences. Unit and set-based pre-matching mechanisms are proposed to remove irrelevant sequences, and a set-based indexing and extension strategy is applied to further avoid unnecessary computation. Real-time decision supports in the form of ranking of similar historical alarm flood sequences are presented to the industrial operators. The ranking list will be updated with the increasing of the online alarm flood sequence. Moreover, the industrial operators, with real-time assistance, can predict the incoming alarm sequence and will be pro-active in identifying the potential problems. The effectiveness of the proposed method is demonstrated by an industrial case study based on real alarm & event logs from a refinery plant.