Machine learning and optimization for predictive maintenance based on predicting failure in the next five days

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

5 Scopus citations

Abstract

This study proposes a framework to predict machine failures using sensor data and optimize predictive/corrective maintenance schedule. Using historical data, machine learning (ML) models are trained to predict the failure probabilities for the next five days. Multiple algorithms, including feature extraction techniques, selections, and ML models (both regression and classification based) are compared. The machine learning models' output is fed to an optimization model to propose an optimized maintenance policy, and we demonstrate how prediction models can help increase system reliability at lower costs.

Original languageBritish English
Title of host publicationICORES 2021 - Proceedings of the 10th International Conference on Operations Research and Enterprise Systems
EditorsGreg H. Parlier, Federico Liberatore, Marc Demange
Pages192-199
Number of pages8
ISBN (Electronic)9789897584855
StatePublished - 2021
Event10th International Conference on Operations Research and Enterprise Systems, ICORES 2021 - Virtual, Online
Duration: 4 Feb 20216 Feb 2021

Publication series

NameICORES 2021 - Proceedings of the 10th International Conference on Operations Research and Enterprise Systems

Conference

Conference10th International Conference on Operations Research and Enterprise Systems, ICORES 2021
CityVirtual, Online
Period4/02/216/02/21

Keywords

  • Condition-based maintenance
  • Machine learning
  • Optimization
  • Predictive maintenance

Fingerprint

Dive into the research topics of 'Machine learning and optimization for predictive maintenance based on predicting failure in the next five days'. Together they form a unique fingerprint.

Cite this