Event-Based Predictive Maintenance on Top of Sensor Data in a Real Industry 4.0 Case Study

Naskos, Athanasios; Toliopoulos, Theodoros; Gounaris, Anastasios; Vamvalis, Cosmas; Caljouw, Daniel

doi:10.1007/978-3-030-43887-6_28

Cited by 8 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the misuse detection case, the techniques that have adopted are both knowledge and ML-based, while in the anomaly detection case, it uses ML-based techniques. The algorithms that we support are inspired by predictive SN Computer Science maintenance in Industry 4.0 [28,29] and emphasize on (i) continuously monitoring for known patterns; (ii) continuously monitoring for unusual behavior following an unsupervised learning approach; and (iii) quick and easy model building for new threats at arbitrary combinations of system layers, provided that logs exist. In summary, the novelty of our proposal lies in the novel application of items (ii) and (iii) above in a IDS system and on the provision of a unified solution for monitoring for known patterns, training for new attacks and detecting anomalous behavior without previous training.…”

Section: Motivation and Contributionsmentioning

confidence: 99%

“…Multiple ML algorithms can be encapsulated in this component. Its main technique is transferred from Industry 4.0 [28,29].…”

Section: Architecturementioning

confidence: 99%

“…This section describes our novel approach to (i) identifying new threat patterns inspired by techniques used in predictive maintenance for Industry 4.0 [22,28,29] and (ii) applying CAPEC-compliant CEP and exploiting publicly available threat profile repositories.…”

Section: Identifying and Detecting Threatsmentioning

confidence: 99%

“…The steepness and shift of the sigmoid function are configured to better map the expectation of the time before the incident at which correlated events will start occurring. This technique has been successfully applied in the aviation industry for predictive maintenance purposes [22] and is tested in other predictive maintenance cases in [28,29].…”

Section: Pre-processing Phasementioning

confidence: 99%

See 3 more Smart Citations

A Methodology for Runtime Detection and Extraction of Threat Patterns

et al. 2020

Self Cite

View full text Add to dashboard Cite

As the confidentiality and integrity of modern health infrastructures is threatened by intrusions and real-time attacks related to privacy and cyber-security, there is a need for proposing novel methodologies to predict future incidents and identify new threat patterns. The main scope of this article is to propose an advanced extension to current Intrusion Detection System (IDS) solutions, which (i) harvests the knowledge out of health data sources or network monitoring to construct models for new threat patterns and (ii) encompasses methods for detecting threat patterns utilizing also advanced unsupervised machine learning data analytic methodologies. Although the work is motivated by the health sector, it is developed in a manner that is directly applicable to other domains.

show abstract

Section: Motivation and Contributionsmentioning

confidence: 99%

“…Multiple ML algorithms can be encapsulated in this component. Its main technique is transferred from Industry 4.0 [28,29].…”

Section: Architecturementioning

confidence: 99%

Section: Identifying and Detecting Threatsmentioning

confidence: 99%

Section: Pre-processing Phasementioning

confidence: 99%

See 2 more Smart Citations

A Methodology for Runtime Detection and Extraction of Threat Patterns

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…There exists extensive literature in the detection of analysis in online settings [1] and multivariate cases [9], but their application in industrial settings is still limited. More specifically, an unsupervised AD approach based on the micro-cluster continuous outlier detection (MCOD) algorithm [13] is evaluated on the same industrial use case as of the current work [18].…”

Section: Introductionmentioning

confidence: 99%

Anomaly detection and event mining in cold forming manufacturing processes

Avendano

Caljouw

Deschrijver

et al. 2020

Int J Adv Manuf Technol

Self Cite

View full text Add to dashboard Cite

Predictive maintenance is one of the main goals within the Industry 4.0 trend. Advances in data-driven techniques offer new opportunities in terms of cost reduction, improved quality control, and increased work safety. This work brings data-driven techniques for two predictive maintenance tasks: anomaly detection and event prediction, applied in the real-world use case of a cold forming manufacturing line for consumer lifestyle products by using acoustic emissions sensors in proximity of the dies of the press module. The proposed models are robust and able to cope with problems such as noise, missing values, and irregular sampling. The detected anomalies are investigated by experts and confirmed to correspond to deviations in the normal operation of the machine. Moreover, we are able to find patterns which are related to the events of interest.

show abstract

Predictive Maintenance for Sensor Enhancement in Industry 4.0

Silva

Rodrigues³

et al. 2021

Recent Challenges in Intelligent Information and Database Systems

View full text Add to dashboard Cite

Event-Based Predictive Maintenance on Top of Sensor Data in a Real Industry 4.0 Case Study

Cited by 8 publications

References 14 publications

A Methodology for Runtime Detection and Extraction of Threat Patterns

A Methodology for Runtime Detection and Extraction of Threat Patterns

Anomaly detection and event mining in cold forming manufacturing processes

Predictive Maintenance for Sensor Enhancement in Industry 4.0

Contact Info

Product

Resources

About