A weighted dissimilarity index to isolate faults during alarm floods

Charbonnier, Sylvie; Bouchair, Nabil; Gayet, Philippe

doi:10.1016/j.conengprac.2015.09.004

Cited by 34 publications

(10 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Multiple approaches exist to this end, drawing from the data mining fields such as sequence identification and pattern recognition [6], [7], correlation analysis [8] or visualisation [9]. Many of these approaches utilise flood similarity measure of some kind, e.g., [10], [11].…”

Section: Introductionmentioning

confidence: 99%

Defining and validating similarity measures for industrial alarm flood analysis

Fullen¹,

Schüller

Niggemann³

2017

2017 IEEE 15th International Conference on Industrial Informatics (INDIN)

View full text Add to dashboard Cite

Industrial plant operators regularly observe a high number of alarms generated in a short period of time, a phenomenon which is referred to as alarm flooding. This causes plant downtime, not only because of the repair time but also by the time needed to identify the root cause of machine failurewhich is difficult during an alarm flood. Therefore, diagnosis tools that perform root cause analysis to advise plant operators can help reduce the downtime, which is a crucial issue in industry. We analyse the reproducibility and applicability of an existing approach by Ahmed et al. (2013) which is based on agglomerative hierarchical clustering where raw data in the form of alarm logs is preprocessed, floods are detected, and then clustered. The aim is, that resulting clusters represent floods that originate from the same common root cause. We extend the approach with alternative similarity measures and perform experiments regarding their effectiveness in structuring industrial alarm flood data. In our evaluation we use a real industrial use case which contains more diverse data and a larger amount of data points compared with the original study.

show abstract

Section: Introductionmentioning

confidence: 99%

Defining and validating similarity measures for industrial alarm flood analysis

Fullen¹,

Schüller

Niggemann³

2017

2017 IEEE 15th International Conference on Industrial Informatics (INDIN)

View full text Add to dashboard Cite

show abstract

“…However, there are no systematic procedures for attaining acceptable alarm system performances. In addition to these, several researchers have studied different aspects of alarm management that includes design of alarm limits for variables, prioritization of alarms 6 , reducing the number of alarms [7][8][9] , variable selection 8,10 and identifying the cause of alarms [11][12][13][14][15] .…”

Section: Introductionmentioning

confidence: 99%

“…These alarm sequence classification techniques can be broadly categorized as sequence alignment based classification, feature based classification, root cause analysis based classification and discrete event system diagnosis using Petri nets. The sequence alignment based approaches aim to capture the similarity between sequences to determine the fault 11,12,39,40 . Feature based approaches transform a sequence into a feature vector and then apply conventional classification methods such as k-nearest neighbours (knn), neural networks or support vector machines 13,41 .…”

Section: Introductionmentioning

confidence: 99%

Hidden Markov model based approach for diagnosing cause of alarm signals

Venkidasalapathy

Kravaris

2021

AIChE Journal

View full text Add to dashboard Cite

When a fault occurs in a process, it slowly propagates within the system and affects the measurements triggering a sequence of alarms in the control room. The operators are required to diagnose the cause of alarms and take necessary corrective measures. The idea of representing the alarm sequence as the fault propagation path and using the propagation path to diagnose the fault is explored. A diagnoser based on hidden Markov model is built to identify the cause of the alarm signals. The proposed approach is applied to an industrial case study: Tennessee Eastman process. The results show that the proposed approach is successful in determining the probable cause of alarms generated with high accuracy. The model was able to identify the cause accurately, even when tested with short alarm sub‐sequences. This allows for early identification of faults, providing more time to the operator to restore the system to normal operation.

show abstract

“…Effective methods have been developed to design and evaluate alarm systems, including alarm limits, , filters, , delay timers, − and deadbands, , based on performance metrics, such as the false alarm rate (FAR), missed alarm rate (MAR), and averaged alarm delay (ADD) . Approaches have been proposed to detect chattering alarms, find consequential alarms, group related alarms, and cope with alarms floods. − In addition, more advanced methods have been developed to detect mode-based alarms from historical data, design mode-based alarming strategies for hybrid process systems, present better visualization of alarm messages, monitor multimodal processes, and determine dynamic alarm limits based on process transitions …”

Section: Introductionmentioning

confidence: 99%

A New Method for Alarm Monitoring of Equipment Start-Up Operations with Applications to Pumps

Zhou

Chen

2019

Ind. Eng. Chem. Res.

View full text Add to dashboard Cite

In practice, alarms configured for steady operating states often become a nuisance during the start-up operation of industrial equipment. As a result, they not only distract plant operators, but may also cause worse consequences, such as pump trips. Motivated by such as a practical problem, this paper presents a new alarm monitoring method for equipment start-up operations. The proposed method is capable of preventing nuisance alarms as well as achieving effective alarm monitoring during equipment start-ups. The contributions of this work are two-fold: First, an offline design framework is proposed to detect the maximum unsuppression delay time and formulate dynamic alarm limits; second, an online algorithm for alarm monitoring of equipment start-ups is proposed on the basis of the designed dynamic alarm limits and the calculation of an exact unsuppression delay time. The effectiveness and practicality of the proposed method are demonstrated by an industrial case study.

show abstract

A weighted dissimilarity index to isolate faults during alarm floods

Cited by 34 publications

References 47 publications

Defining and validating similarity measures for industrial alarm flood analysis

Defining and validating similarity measures for industrial alarm flood analysis

Hidden Markov model based approach for diagnosing cause of alarm signals

A New Method for Alarm Monitoring of Equipment Start-Up Operations with Applications to Pumps

Contact Info

Product

Resources

About