Detection of Temporal Dependencies in Alarm Time Series of Industrial Plants

Folmer, Jens; Schuricht, Falk; Vogel‐Heuser, Birgit

doi:10.3182/20140824-6-za-1003.01897

Cited by 25 publications

(8 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, a human in the loop machine learning approach was chosen which enables to automatically detect notification sequences while being supervised by humans. Historical alarm logs are used for identifying significant notification sequences based on statistical pattern recognition techniques to suppress redundant notifications and visualize the cirital situations [61]. Typically, machine learning approaches are challenged by statistically non-perfect learning data.…”

Section: Agent-based Dynamic Alarm Managementmentioning

confidence: 99%

Agents enabling cyber-physical production systems

Vogel‐Heuser

Lee

Leitao

2015

At - Automatisierungstechnik

Self Cite

View full text Add to dashboard Cite

In order to be prepared for future challenges facing the industrial production domain, Cyber-Physical Production Systems (CPPS) consisting of intelligent entities which collaborate and exchange information globally are being proclaimed recently as part of Industrie 4.0. In this article the requirements of CPPS and abilities of agents as enabling technology are discussed. The applicability of agents for realizing CPPS is exemplarily shown based on three selected use cases with different requirements regarding real-time and dependability. The paper finally concludes with opportunities and open research issues that need to be faced in order to achieve agent-based CPPSs.

show abstract

Section: Agent-based Dynamic Alarm Managementmentioning

confidence: 99%

Agents enabling cyber-physical production systems

Vogel‐Heuser

Lee

Leitao

2015

At - Automatisierungstechnik

Self Cite

View full text Add to dashboard Cite

show abstract

“…Association rule (AR) mining includes finding temporal dependencies. In [16], the authors proposed an algorithm to find related dependencies among alarms in alarm logs. Statistical approaches form the basis for determining temporal dependencies between two alarms which may occur several times in an alarm log.…”

Section: Related Workmentioning

confidence: 99%

“…The existing work focuses on the various tools and techniques available for alarm pattern recognition and classification [2][3][4][5][6][7][8] using complex techniques but does not throw light on the way frequent pattern mining or data mining algorithms can be applied to find frequent sequences or patterns in alarm data. The existing work is more on the study of techniques and algorithms which help in classifying alarm floods online or find patterns in them and also help in the graphical visualization of these alarm floods [9][10][11][12][13][14][15][16][17][18][19][20][21]. As part of the present work, the main aim is to propose an offline method to help plant operators or experts to identify repetitive sequences or patterns in the alarms presented to them using data mining techniques to further assist in the area of alarm rationalization.…”

Section: Introductionmentioning

confidence: 99%

Alarm Pattern Recognition in Continuous Process Control Systems using Data Mining

Belavadi¹,

Sardar²,

Chaudhari³

2022

IJC

View full text Add to dashboard Cite

An alarm management system with the Human Machine Interface in a process control system is used to alert an operator of any abnormal situation, so that corrective action can be taken to ensure safety and productivity of the plant and quality of the product. An alarm system reporting many alarms even during the normal state of the plant is due to chattering alarms, duplicated alarms, intermittent equipment problems and certain alarms configured in the system which may not have any importance. In such a situation the operator may miss certain critical alarms leading to undesirable outcomes. So, to have an optimum alarm system, the unwanted alarms have to be identified and eliminated. In this paper, we propose an offline method to identify repetitive, frequent sequences or patterns using PrefixSpan and Bi-Directional Extension algorithms. With the identified sequences or patterns, plant operation experts can improve the effectiveness of the alarm system through alarm rationalization so that this will help the operator in making the plant more safe, reliable and productive. The main objectives of this work are the following: (i) to use a definitive method to represent alarm data in an alarm log which is Temporal data as Itemsets without a need for complex mathematical, statistical or visual methods; (ii) to use data mining algorithms for identifying Frequent sequences which can be implemented on a normal computing resource such as Personal computer; (iii) to apply the method to the complete alarm data available no matter how big they are; (iv) to study and establish that the chosen method is possible to be applied to larger sized datasets.

show abstract

“…Analysis of event logs has been performed in the context of alarm management systems, where sequential analysis is performed on the alarm notifications. In [13], an algorithm for discovering temporal alarm dependencies is proposed which utilizes conditional probabilities in an adjustable time window. In order to reduce the number of alarms in alarm floods, [2] also performed root cause analysis with a Bayesian network approach and compared di↵erent methods for learning the network probabilities.…”

Section: Analysis Of Alarm Event Logsmentioning

confidence: 99%

Mining Attributed Interaction Networks on Industrial Event Logs

Atzmueller

Kloepper²

2018

Intelligent Data Engineering and Automated Learning – IDEAL 2018

View full text Add to dashboard Cite

In future Industry 4.0 manufacturing systems reconfigurability and flexible material flows are key mechanisms. However, such dynamics require advanced methods for the reconstruction, interpretation and understanding of the general material flows and structure of the production system. This paper proposes a network-based computational sensemaking approach on attributed network structures modeling the interactions in the event log. We apply descriptive community mining methods for detecting patterns on the structure of the production system. The proposed approach is evaluated using two real-world datasets.

show abstract

Detection of Temporal Dependencies in Alarm Time Series of Industrial Plants

Cited by 25 publications

References 12 publications

Agents enabling cyber-physical production systems

Agents enabling cyber-physical production systems

Alarm Pattern Recognition in Continuous Process Control Systems using Data Mining

Mining Attributed Interaction Networks on Industrial Event Logs

Contact Info

Product

Resources

About