TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Fault detection of elevator system using profile extraction and deep autoencoder feature extraction

Tutkimustuotosvertaisarvioitu

Standard

Fault detection of elevator system using profile extraction and deep autoencoder feature extraction. / Mishra, Krishna; Saxen, John-Eric; Björkqvist, Jerker; Huhtala, Kalevi.

33rd Annual European Simulation and Modelling Conference: ESM 2019, October 28-30, 2019, Palma de Mallorca, Spain. toim. / Philippe Geril. Vuosikerta 33 2019. toim. Belgium : EUROSIS, 2019. s. 79-83 (European Simulation and Modelling Conference).

Tutkimustuotosvertaisarvioitu

Harvard

Mishra, K, Saxen, J-E, Björkqvist, J & Huhtala, K 2019, Fault detection of elevator system using profile extraction and deep autoencoder feature extraction. julkaisussa P Geril (Toimittaja), 33rd Annual European Simulation and Modelling Conference: ESM 2019, October 28-30, 2019, Palma de Mallorca, Spain. 2019 toim, Vuosikerta. 33, European Simulation and Modelling Conference, EUROSIS, Belgium, Sivut 79-83, 1/01/00.

APA

Mishra, K., Saxen, J-E., Björkqvist, J., & Huhtala, K. (2019). Fault detection of elevator system using profile extraction and deep autoencoder feature extraction. teoksessa P. Geril (Toimittaja), 33rd Annual European Simulation and Modelling Conference: ESM 2019, October 28-30, 2019, Palma de Mallorca, Spain (2019 toim., Vuosikerta 33, Sivut 79-83). (European Simulation and Modelling Conference). Belgium: EUROSIS.

Vancouver

Mishra K, Saxen J-E, Björkqvist J, Huhtala K. Fault detection of elevator system using profile extraction and deep autoencoder feature extraction. julkaisussa Geril P, toimittaja, 33rd Annual European Simulation and Modelling Conference: ESM 2019, October 28-30, 2019, Palma de Mallorca, Spain. 2019 toim. Vuosikerta 33. Belgium: EUROSIS. 2019. s. 79-83. (European Simulation and Modelling Conference).

Author

Mishra, Krishna ; Saxen, John-Eric ; Björkqvist, Jerker ; Huhtala, Kalevi. / Fault detection of elevator system using profile extraction and deep autoencoder feature extraction. 33rd Annual European Simulation and Modelling Conference: ESM 2019, October 28-30, 2019, Palma de Mallorca, Spain. Toimittaja / Philippe Geril. Vuosikerta 33 2019. toim. Belgium : EUROSIS, 2019. Sivut 79-83 (European Simulation and Modelling Conference).

Bibtex - Lataa

@inproceedings{e2443c22973548498b37aa5ff435a142,
title = "Fault detection of elevator system using profile extraction and deep autoencoder feature extraction",
abstract = "In this paper, we propose a new algorithm for data extraction from time series data, and furthermore automatic calculation of highly informative deep features to be used in fault detection. In data extraction elevator start and stop events are extracted from sensor data, and a generic deep autoencoder model is also developed for automated feature extraction from the extracted profiles. After this, extracted deep features are classified with random forest algorithm for fault detection. Sensor data are labelled as healthy and faulty based on the maintenance actions recorded. The rest of the healthy data are 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 outperforms results using existing features. Existing features are also classified with random forest to compare results. Our developed algorithm provides better results due to the new deep features extracted from the dataset when compared to existing features. This research will help various predictive maintenance systems to detect false alarms, which will in turn reduce unnecessary visits of service technicians to installation sites.",
author = "Krishna Mishra and John-Eric Saxen and Jerker Bj{\"o}rkqvist and Kalevi Huhtala",
year = "2019",
month = "10",
day = "30",
language = "English",
isbn = "9789492859099",
volume = "33",
series = "European Simulation and Modelling Conference",
publisher = "EUROSIS",
pages = "79--83",
editor = "Philippe Geril",
booktitle = "33rd Annual European Simulation and Modelling Conference",
edition = "2019",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Fault detection of elevator system using profile extraction and deep autoencoder feature extraction

AU - Mishra, Krishna

AU - Saxen, John-Eric

AU - Björkqvist, Jerker

AU - Huhtala, Kalevi

PY - 2019/10/30

Y1 - 2019/10/30

N2 - In this paper, we propose a new algorithm for data extraction from time series data, and furthermore automatic calculation of highly informative deep features to be used in fault detection. In data extraction elevator start and stop events are extracted from sensor data, and a generic deep autoencoder model is also developed for automated feature extraction from the extracted profiles. After this, extracted deep features are classified with random forest algorithm for fault detection. Sensor data are labelled as healthy and faulty based on the maintenance actions recorded. The rest of the healthy data are 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 outperforms results using existing features. Existing features are also classified with random forest to compare results. Our developed algorithm provides better results due to the new deep features extracted from the dataset when compared to existing features. This research will help various predictive maintenance systems to detect false alarms, which will in turn reduce unnecessary visits of service technicians to installation sites.

AB - In this paper, we propose a new algorithm for data extraction from time series data, and furthermore automatic calculation of highly informative deep features to be used in fault detection. In data extraction elevator start and stop events are extracted from sensor data, and a generic deep autoencoder model is also developed for automated feature extraction from the extracted profiles. After this, extracted deep features are classified with random forest algorithm for fault detection. Sensor data are labelled as healthy and faulty based on the maintenance actions recorded. The rest of the healthy data are 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 outperforms results using existing features. Existing features are also classified with random forest to compare results. Our developed algorithm provides better results due to the new deep features extracted from the dataset when compared to existing features. This research will help various predictive maintenance systems to detect false alarms, which will in turn reduce unnecessary visits of service technicians to installation sites.

M3 - Conference contribution

SN - 9789492859099

VL - 33

T3 - European Simulation and Modelling Conference

SP - 79

EP - 83

BT - 33rd Annual European Simulation and Modelling Conference

A2 - Geril, Philippe

PB - EUROSIS

CY - Belgium

ER -