Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods

Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods

Anomaly detection is becoming increasingly important to enhance reliability and resiliency in the Industry 4.0 framework. In this work, we investigate different methods for anomaly detection on in-production manufacturing machines taking into account their variability, both in operation and in wear...

Full description

Bibliographic Details
Main Authors: Federico Pittino, Michael Puggl, Thomas Moldaschl, Christina Hirschl
Format: Article
Language:English
Published: MDPI AG 2020-04-01
Series:Sensors
Subjects:
anomaly detection
statistical machine learning
in-production data
Online Access:https://www.mdpi.com/1424-8220/20/8/2344
id doaj-f3255425639342f2833bb9a13f08b5d2
record_format Article
spelling doaj-f3255425639342f2833bb9a13f08b5d22020-11-25T02:53:18ZengMDPI AGSensors1424-82202020-04-01202344234410.3390/s20082344Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning MethodsFederico Pittino0Michael Puggl1Thomas Moldaschl2Christina Hirschl3Silicon Austria Labs GmbH, Villach A-9524, AustriaLAM Research AG, Villach A-9524, AustriaSilicon Austria Labs GmbH, Villach A-9524, AustriaSilicon Austria Labs GmbH, Villach A-9524, AustriaAnomaly detection is becoming increasingly important to enhance reliability and resiliency in the Industry 4.0 framework. In this work, we investigate different methods for anomaly detection on in-production manufacturing machines taking into account their variability, both in operation and in wear conditions. We demonstrate how the nature of the available data, featuring any anomaly or not, is of importance for the algorithmic choice, discussing both statistical machine learning methods and control charts. We finally develop methods for automatic anomaly detection, which obtain a recall close to one on our data. Our developed methods are designed not to rely on a continuous recalibration and hand-tuning by the machine user, thereby allowing their deployment in an in-production environment robustly and efficiently.https://www.mdpi.com/1424-8220/20/8/2344anomaly detectionstatistical machine learningin-production data
collection DOAJ
language English
format Article
sources DOAJ
author Federico Pittino
Michael Puggl
Thomas Moldaschl
Christina Hirschl
spellingShingle Federico Pittino
Michael Puggl
Thomas Moldaschl
Christina Hirschl
Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods
Sensors
anomaly detection
statistical machine learning
in-production data
author_facet Federico Pittino
Michael Puggl
Thomas Moldaschl
Christina Hirschl
author_sort Federico Pittino
title Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods
title_short Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods
title_full Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods
title_fullStr Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods
title_full_unstemmed Automatic Anomaly Detection on In-Production Manufacturing Machines Using Statistical Learning Methods
title_sort automatic anomaly detection on in-production manufacturing machines using statistical learning methods
publisher MDPI AG
series Sensors
issn 1424-8220
publishDate 2020-04-01
description Anomaly detection is becoming increasingly important to enhance reliability and resiliency in the Industry 4.0 framework. In this work, we investigate different methods for anomaly detection on in-production manufacturing machines taking into account their variability, both in operation and in wear conditions. We demonstrate how the nature of the available data, featuring any anomaly or not, is of importance for the algorithmic choice, discussing both statistical machine learning methods and control charts. We finally develop methods for automatic anomaly detection, which obtain a recall close to one on our data. Our developed methods are designed not to rely on a continuous recalibration and hand-tuning by the machine user, thereby allowing their deployment in an in-production environment robustly and efficiently.
topic anomaly detection
statistical machine learning
in-production data
url https://www.mdpi.com/1424-8220/20/8/2344
work_keys_str_mv AT federicopittino automaticanomalydetectiononinproductionmanufacturingmachinesusingstatisticallearningmethods
AT michaelpuggl automaticanomalydetectiononinproductionmanufacturingmachinesusingstatisticallearningmethods
AT thomasmoldaschl automaticanomalydetectiononinproductionmanufacturingmachinesusingstatisticallearningmethods
AT christinahirschl automaticanomalydetectiononinproductionmanufacturingmachinesusingstatisticallearningmethods
_version_ 1724725418703978496

Similar Items