There have been many recent developments in the application of data-based methods to machine condition monitoring. A powerful methodology based on machine learning has emerged, where diagnostics are based on a two-step procedure: extraction of damage-sensitive features, followed by unsupervised learning (novelty detection) or supervised learning (classification). The objective of the current pair of papers is simply to illustrate one state-of-the-art procedure for each step, using synthetic data representative of reality in terms of size and complexity. The second paper in the pair will deal with novelty detection. Although there has been considerable progress in the use of outlier analysis for novelty detection, most of the papers produced so far have suffered from the fact that simple algorithms break down if multiple outliers are present or if damage is already present in a training set. The objective of the current paper is to illustrate the use of phase-space thresholding; an algorithm which has the ability to detect multiple outliers inclusively in a data set.

An Illustration of New Methods in Machine Condition Monitoring, Part II: Adaptive outlier detection / Antoniadou, I.; Worden, Keith; Marchesiello, Stefano; Mba, CLEMENT UCHECHUKWU; Garibaldi, Luigi. - In: JOURNAL OF PHYSICS. CONFERENCE SERIES. - ISSN 1742-6588. - ELETTRONICO. - 842:(2017), pp. 1-7. (Intervento presentato al convegno 12th International Conference on Damage Assessment of Structures, DAMAS 2017 tenutosi a Kitakyushu, Japan nel 10-12 July 2017) [10.1088/1742-6596/842/1/012059].

An Illustration of New Methods in Machine Condition Monitoring, Part II: Adaptive outlier detection

WORDEN, KEITH;MARCHESIELLO, STEFANO;MBA, CLEMENT UCHECHUKWU;GARIBALDI, Luigi
2017

Abstract

There have been many recent developments in the application of data-based methods to machine condition monitoring. A powerful methodology based on machine learning has emerged, where diagnostics are based on a two-step procedure: extraction of damage-sensitive features, followed by unsupervised learning (novelty detection) or supervised learning (classification). The objective of the current pair of papers is simply to illustrate one state-of-the-art procedure for each step, using synthetic data representative of reality in terms of size and complexity. The second paper in the pair will deal with novelty detection. Although there has been considerable progress in the use of outlier analysis for novelty detection, most of the papers produced so far have suffered from the fact that simple algorithms break down if multiple outliers are present or if damage is already present in a training set. The objective of the current paper is to illustrate the use of phase-space thresholding; an algorithm which has the ability to detect multiple outliers inclusively in a data set.
File in questo prodotto:
File Dimensione Formato  
Antoniadou_2017_J._Phys.__Conf._Ser._842_012059.pdf

accesso aperto

Descrizione: Articolo principale
Tipologia: 2. Post-print / Author's Accepted Manuscript
Licenza: Creative commons
Dimensione 578.61 kB
Formato Adobe PDF
578.61 kB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2676292
 Attenzione

Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo