Anomaly detection-based condition monitoring

dc.contributor.authorKáš, Martin
dc.contributor.authorWamba, Francis Fomi
dc.date.accessioned2023-01-30T11:00:31Z
dc.date.available2023-01-30T11:00:31Z
dc.date.issued2022
dc.description.abstract-translatedThe impact of an anomaly is domain-dependent. In a dataset of network activities, an anomaly can imply an intrusion attack. Other objectives of anomaly detection are industrial damage detection, data leak prevention, identifying security vulnerabilities or military surveillance. Anomalies are observations or a sequences of observations which distribution deviates remarkably from the general distribution of the whole dataset. The big majority of the dataset consists of normal (healthy) data points. The anomalies form only a very small part of the dataset. Anomaly detection is the technique to find these observations and its methods are specific to the type of data. While there is a wide spectrum of anomaly detection approaches today, it becomes more and more difficult to keep track of all the techniques. As a matter of fact, it is not clear which of the three categories of detection methods, i.e., statistical approaches, machine learning approaches or deep learning approaches is more appropriate to detect anomalies on time-series data which are mainly used in industry. Typical industrial device has multidimensional characteristic. It is possible to measure voltage, current, active power, vibrations, rotational speed, temperature, pressure difference, etc. on such device. Early detection of anomalous behavior of industrial device can help reduce or prevent serious damage leading to significant financial lost. This paper is a summary of the methods used to detect anomalies in condition monitoring applications.en
dc.format6 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationKÁŠ, M. WAMBA, FF. Anomaly detection-based condition monitoring. INSIGHT: Non-Destructive Testing and Condition Monitoring, 2022, roč. 64, č. 8, s. 453-458. ISSN: 1354-2575cs
dc.identifier.document-number860987900007
dc.identifier.doi10.1784/insi.2022.64.8.453
dc.identifier.issn1354-2575
dc.identifier.obd43937182
dc.identifier.uri2-s2.0-85137170415
dc.identifier.urihttp://hdl.handle.net/11025/51190
dc.language.isoenen
dc.project.IDEF16_026/0008389/LoStr: Výzkumná spolupráce pro dosažení vyšší účinnosti a spolehlivosti lopatkových strojůcs
dc.publisherBritish Institute of Non-Destructive Testingen
dc.relation.ispartofseriesINSIGHT: Non-Destructive Testing and Condition Monitoringen
dc.rightsPlný text není přístupný.cs
dc.rights© British Institute of Non-Destructive Testingen
dc.rights.accessclosedAccessen
dc.subject.translatedAnomaly detectionen
dc.subject.translatedDeep Learningen
dc.subject.translatedMachine Learningen
dc.titleAnomaly detection-based condition monitoringen
dc.typečlánekcs
dc.typearticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
Anomaly Detection Based Condition Monitoring.pdf
Size:
984.44 KB
Format:
Adobe Portable Document Format