Deep autoencoder feature extraction for fault detection of elevator systems

Krishna Mishra; Tomi Krogerus; Kalevi Huhtala

Deep autoencoder feature extraction for fault detection of elevator systems

Krishna Mishra
, Tomi Krogerus
, Kalevi Huhtala

Automation Technology and Mechanical Engineering

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

3 Citations (Scopus)

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.

Original language	English
Title of host publication	European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Subtitle of host publication	ESANN 2019, Bruges (Belgium), 24 - 26 April 2019
Editors	Michel Verleysen
Place of Publication	Bruges (Belgium)
Publisher	i6doc.com publication
Pages	191-196
Number of pages	6
Volume	27
Edition	2019
ISBN (Electronic)	978-287-587-066-7
ISBN (Print)	978-287-587-065-0
Publication status	Published - 24 Apr 2019
Publication type	A4 Article in conference proceedings
Event	EUROPEAN SYMPOSIUM ON ARTIFICIAL NEURAL NETWORKS, COMPUTATIONAL INTELLIGENCE AND MACHINE LEARNING - Duration: 1 Jan 1900 → …

Conference

Conference	EUROPEAN SYMPOSIUM ON ARTIFICIAL NEURAL NETWORKS, COMPUTATIONAL INTELLIGENCE AND MACHINE LEARNING
Period	1/01/00 → …

Publication forum classification

Publication forum level 1

ASJC Scopus subject areas

General Computer Science

Access to Document

https://www.elen.ucl.ac.be/esann/proceedings/papers.php?ann=2019

3 Citations
3 Conference contribution

Fault detection of elevator systems using deep autoencoder feature extraction
Mishra, K., Krogerus, T. & Huhtala, K., 31 May 2019, IEEE 13th International Conference on Research Challenges in Information Science: RCIS 2019, 29-31 May 2019, Brussels, Belgium. Heng, S. (ed.). 2019 ed. Brussels, Belgium: IEEE, Vol. 13. p. 43-48 6 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review
13 Citations (Scopus)
Fault detection of elevator systems using multilayer perceptron neural network
Mishra, K. & Huhtala, K., 13 Sept 2019, 24th IEEE Conference on Emerging Technologies and Factory Automation: ETFA 2019, September 10-13, 2019 in Zaragoza, Spain. Nogueiras, A. (ed.). 2019 ed. Zaragoza, Spain: IEEE, Vol. 24. p. 904-909 6 p. (IEEE Conference on Emerging Technologies and Factory Automation).
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Open Access
30 Citations (Scopus)
Fault detection of elevator systems using automated feature extraction and classification
Mishra, K., Krogerus, T. & Huhtala, K., 21 May 2018, Elevator Technology 22, Proceedings of Elevcon 2018, 22nd International Congress on Vertical Transportation Technologies: 22-24 May 2018, Berlin, Germany.. 2018 ed. Berlin: The International Association of Elevator Engineers, Vol. 22. p. 116-122 7 p.
Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

Cite this

Mishra, K., Krogerus, T., & Huhtala, K. (2019). Deep autoencoder feature extraction for fault detection of elevator systems. In M. Verleysen (Ed.), European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2019, Bruges (Belgium), 24 - 26 April 2019 (2019 ed., Vol. 27, pp. 191-196). i6doc.com publication. https://www.elen.ucl.ac.be/esann/proceedings/papers.php?ann=2019

Mishra, Krishna ; Krogerus, Tomi ; Huhtala, Kalevi. / Deep autoencoder feature extraction for fault detection of elevator systems. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2019, Bruges (Belgium), 24 - 26 April 2019. editor / Michel Verleysen. Vol. 27 2019. ed. Bruges (Belgium) : i6doc.com publication, 2019. pp. 191-196

@inproceedings{5310e262fe39423f887a8c66b4e2a84f,

title = "Deep autoencoder feature extraction for fault detection of elevator systems",

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.",

author = "Krishna Mishra and Tomi Krogerus and Kalevi Huhtala",

year = "2019",

month = apr,

day = "24",

language = "English",

isbn = "978-287-587-065-0",

volume = "27",

pages = "191--196",

editor = "Michel Verleysen",

booktitle = "European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning",

publisher = "i6doc.com publication",

edition = "2019",

note = "EUROPEAN SYMPOSIUM ON ARTIFICIAL NEURAL NETWORKS, COMPUTATIONAL INTELLIGENCE AND MACHINE LEARNING ; Conference date: 01-01-1900",

}

Mishra, K, Krogerus, T & Huhtala, K 2019, Deep autoencoder feature extraction for fault detection of elevator systems. in M Verleysen (ed.), European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2019, Bruges (Belgium), 24 - 26 April 2019. 2019 edn, vol. 27, i6doc.com publication, Bruges (Belgium), pp. 191-196, EUROPEAN SYMPOSIUM ON ARTIFICIAL NEURAL NETWORKS, COMPUTATIONAL INTELLIGENCE AND MACHINE LEARNING, 1/01/00. <https://www.elen.ucl.ac.be/esann/proceedings/papers.php?ann=2019>

Deep autoencoder feature extraction for fault detection of elevator systems. / Mishra, Krishna; Krogerus, Tomi; Huhtala, Kalevi.
European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning: ESANN 2019, Bruges (Belgium), 24 - 26 April 2019. ed. / Michel Verleysen. Vol. 27 2019. ed. Bruges (Belgium): i6doc.com publication, 2019. p. 191-196.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Deep autoencoder feature extraction for fault detection of elevator systems

AU - Mishra, Krishna

AU - Krogerus, Tomi

AU - Huhtala, Kalevi

PY - 2019/4/24

Y1 - 2019/4/24

N2 - 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.

AB - 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.

M3 - Conference contribution

SN - 978-287-587-065-0

VL - 27

SP - 191

EP - 196

BT - European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

A2 - Verleysen, Michel

PB - i6doc.com publication

CY - Bruges (Belgium)

T2 - EUROPEAN SYMPOSIUM ON ARTIFICIAL NEURAL NETWORKS, COMPUTATIONAL INTELLIGENCE AND MACHINE LEARNING

Y2 - 1 January 1900

ER -

Deep autoencoder feature extraction for fault detection of elevator systems

Abstract

Conference

Publication forum classification

ASJC Scopus subject areas

Access to Document

Fingerprint

Research output

Fault detection of elevator systems using deep autoencoder feature extraction

Fault detection of elevator systems using multilayer perceptron neural network

Fault detection of elevator systems using automated feature extraction and classification

Cite this