Comparing machine learning methods on concept drift detection for Predictive Maintenance

Research output: Chapter in Book/Report/Conference proceedingsConference contributionpeer-review

1 Citation (Scopus)

Abstract

In this work we present a comparison of various machine learning algorithms with the objective of detecting concept drifts in data streams characteristical for condition monitoring of industrial production plants. Although there is a fair number of contributions employing machine learning algorithms in related fields such as traditional time series forecasting or concept drift learning, data sets with sensor streams from a production plant are rarely covered. This work aims at shedding some light on the matter of how efficient the depicted algorithms perform on concept drift detection to pave the way for Predictive Maintenance (PdM) and which intermediate data processing steps therefore might be beneficial.
Original languageEnglish
Title of host publication30th European Modeling and Simulation Symposium, EMSS 2018
EditorsYuri Merkuryev, Miquel Angel Piera, Francesco Longo, Agostino G. Bruzzone, Michael Affenzeller, Emilio Jimenez
PublisherDIME UNIVERSITY OF GENOA
Pages115-122
Number of pages8
ISBN (Electronic)9788885741065
ISBN (Print)978-88-85741-03-4
Publication statusPublished - 2018
EventThe 30th European Modeling & Simulation Symposium EMSS 2018 - Budapest, Hungary, Hungary
Duration: 17 Sep 201819 Sep 2018
http://www.msc-les.org/conf/emss2018/index.html

Publication series

Name30th European Modeling and Simulation Symposium, EMSS 2018

Conference

ConferenceThe 30th European Modeling & Simulation Symposium EMSS 2018
Country/TerritoryHungary
CityBudapest, Hungary
Period17.09.201819.09.2018
Internet address

Keywords

  • Machine Learning
  • Predictive Maintenance
  • Concept Drift Detection
  • Time Series Regression
  • Machine learning
  • Time series regression
  • Concept drift detection
  • Predictive maintenance

Fingerprint

Dive into the research topics of 'Comparing machine learning methods on concept drift detection for Predictive Maintenance'. Together they form a unique fingerprint.

Cite this