TUTCRIS - Tampereen teknillinen yliopisto

TUTCRIS

Fault detection of elevator systems using deep autoencoder feature extraction

Tutkimustuotosvertaisarvioitu

Standard

Fault detection of elevator systems using deep autoencoder feature extraction. / Mishra, Krishna; Krogerus, Tomi; Huhtala, Kalevi.

IEEE 13th International Conference on Research Challenges in Information Science: RCIS 2019, 29-31 May 2019, Brussels, Belgium. toim. / Samedi Heng. Vuosikerta 13 2019. toim. Brussels, Belgium : IEEE, 2019. s. 43-48.

Tutkimustuotosvertaisarvioitu

Harvard

Mishra, K, Krogerus, T & Huhtala, K 2019, Fault detection of elevator systems using deep autoencoder feature extraction. julkaisussa S Heng (Toimittaja), IEEE 13th International Conference on Research Challenges in Information Science: RCIS 2019, 29-31 May 2019, Brussels, Belgium. 2019 toim, Vuosikerta. 13, IEEE, Brussels, Belgium, Sivut 43-48, IEEE INTERNATIONAL CONFERENCE ON RESEARCH CHALLENGES IN INFORMATION SCIENCE, 1/01/00. https://doi.org/10.1109/RCIS.2019.8876984

APA

Mishra, K., Krogerus, T., & Huhtala, K. (2019). Fault detection of elevator systems using deep autoencoder feature extraction. teoksessa S. Heng (Toimittaja), IEEE 13th International Conference on Research Challenges in Information Science: RCIS 2019, 29-31 May 2019, Brussels, Belgium (2019 toim., Vuosikerta 13, Sivut 43-48). Brussels, Belgium: IEEE. https://doi.org/10.1109/RCIS.2019.8876984

Vancouver

Mishra K, Krogerus T, Huhtala K. Fault detection of elevator systems using deep autoencoder feature extraction. julkaisussa Heng S, toimittaja, IEEE 13th International Conference on Research Challenges in Information Science: RCIS 2019, 29-31 May 2019, Brussels, Belgium. 2019 toim. Vuosikerta 13. Brussels, Belgium: IEEE. 2019. s. 43-48 https://doi.org/10.1109/RCIS.2019.8876984

Author

Mishra, Krishna ; Krogerus, Tomi ; Huhtala, Kalevi. / Fault detection of elevator systems using deep autoencoder feature extraction. IEEE 13th International Conference on Research Challenges in Information Science: RCIS 2019, 29-31 May 2019, Brussels, Belgium. Toimittaja / Samedi Heng. Vuosikerta 13 2019. toim. Brussels, Belgium : IEEE, 2019. Sivut 43-48

Bibtex - Lataa

@inproceedings{1663151858804bba869c68386bbcd2d5,
title = "Fault detection of elevator systems using deep autoencoder feature extraction",
abstract = "In this research, we propose a generic deep autoencoder model for automated feature extraction from the raw sensor data. 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 remaining healthy data is used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved 100{\%} accuracy in fault detection along with avoiding false positives based on new extracted deep features, which outperform the results using existing features. Existing features are also classified with random forest to compare results. Deep autoencoder random forest provides better results due to the new deep features extracted from the dataset when compared to existing features. Our model provides good classification and is robust against overfitting characteristics. This research will help various predictive maintenance systems to detect false alarms, which will reduce unnecessary visits of service technicians to installation sites.",
author = "Krishna Mishra and Tomi Krogerus and Kalevi Huhtala",
year = "2019",
month = "5",
day = "31",
doi = "10.1109/RCIS.2019.8876984",
language = "English",
volume = "13",
pages = "43--48",
editor = "Samedi Heng",
booktitle = "IEEE 13th International Conference on Research Challenges in Information Science",
publisher = "IEEE",
edition = "2019",

}

RIS (suitable for import to EndNote) - Lataa

TY - GEN

T1 - Fault detection of elevator systems using deep autoencoder feature extraction

AU - Mishra, Krishna

AU - Krogerus, Tomi

AU - Huhtala, Kalevi

PY - 2019/5/31

Y1 - 2019/5/31

N2 - In this research, we propose a generic deep autoencoder model for automated feature extraction from the raw sensor data. 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 remaining healthy data is used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved 100% accuracy in fault detection along with avoiding false positives based on new extracted deep features, which outperform the results using existing features. Existing features are also classified with random forest to compare results. Deep autoencoder random forest provides better results due to the new deep features extracted from the dataset when compared to existing features. Our model provides good classification and is robust against overfitting characteristics. This research will help various predictive maintenance systems to detect false alarms, which will reduce unnecessary visits of service technicians to installation sites.

AB - In this research, we propose a generic deep autoencoder model for automated feature extraction from the raw sensor data. 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 remaining healthy data is used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved 100% accuracy in fault detection along with avoiding false positives based on new extracted deep features, which outperform the results using existing features. Existing features are also classified with random forest to compare results. Deep autoencoder random forest provides better results due to the new deep features extracted from the dataset when compared to existing features. Our model provides good classification and is robust against overfitting characteristics. This research will help various predictive maintenance systems to detect false alarms, which will reduce unnecessary visits of service technicians to installation sites.

U2 - 10.1109/RCIS.2019.8876984

DO - 10.1109/RCIS.2019.8876984

M3 - Conference contribution

VL - 13

SP - 43

EP - 48

BT - IEEE 13th International Conference on Research Challenges in Information Science

A2 - Heng, Samedi

PB - IEEE

CY - Brussels, Belgium

ER -