Tampere University of Technology

TUTCRIS Research Portal

Deep autoencoder feature extraction for fault detection of elevator systems

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

Details

Original languageEnglish
Title of host publicationEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Subtitle of host publicationESANN 2019, Bruges (Belgium), 24 - 26 April 2019
EditorsMichel Verleysen
Place of PublicationBruges (Belgium)
Publisheri6doc.com publication
Pages191-196
Number of pages6
Volume27
Edition2019
ISBN (Electronic)978-287-587-066-7
ISBN (Print)978-287-587-065-0
Publication statusPublished - 24 Apr 2019
Publication typeA4 Article in a conference publication
EventEUROPEAN SYMPOSIUM ON ARTIFICIAL NEURAL NETWORKS, COMPUTATIONAL INTELLIGENCE AND MACHINE LEARNING -
Duration: 1 Jan 1900 → …

Conference

ConferenceEUROPEAN SYMPOSIUM ON ARTIFICIAL NEURAL NETWORKS, COMPUTATIONAL INTELLIGENCE AND MACHINE LEARNING
Period1/01/00 → …

Abstract

In this research, we propose a generic deep autoencoder model for automated feature extraction from the elevator sensor data. Extracted deep features are classified with random forest algorithm for fault detection. Sensor data are labelled as healthy or faulty based on the maintenance actions recorded. In our research, we have included all fault types present for each elevator. The remaining healthy data is used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved nearly 100% accuracy in fault detection along with avoiding false positives based on new extracted deep features, which outperform the results using existing features.

ASJC Scopus subject areas

Publication forum classification