Elevator Fault Detection Using Profile Extraction and Deep Autoencoder Feature Extraction for Acceleration and Magnetic Signals
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 including both acceleration...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-07-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/9/15/2990 |
| _version_ | 1818822022440943616 |
|---|---|
| author | Krishna Mohan Mishra Kalevi Huhtala |
| author_facet | Krishna Mohan Mishra Kalevi Huhtala |
| author_sort | Krishna Mohan Mishra |
| collection | DOAJ |
| description | 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 including both acceleration and magnetic signals. In addition, 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 remaining healthy data are used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved above 90% 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. |
| first_indexed | 2024-12-18T23:17:28Z |
| format | Article |
| id | doaj.art-cdb7cccbec004de49034d728251fa35a |
| institution | Directory Open Access Journal |
| issn | 2076-3417 |
| language | English |
| last_indexed | 2024-12-18T23:17:28Z |
| publishDate | 2019-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj.art-cdb7cccbec004de49034d728251fa35a2022-12-21T20:48:07ZengMDPI AGApplied Sciences2076-34172019-07-01915299010.3390/app9152990app9152990Elevator Fault Detection Using Profile Extraction and Deep Autoencoder Feature Extraction for Acceleration and Magnetic SignalsKrishna Mohan Mishra0Kalevi Huhtala1Unit of Automation Technology and Mechanical Engineering, Tampere University, 33720 Tampere, FinlandUnit of Automation Technology and Mechanical Engineering, Tampere University, 33720 Tampere, FinlandIn 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 including both acceleration and magnetic signals. In addition, 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 remaining healthy data are used for validation of the model to prove its efficacy in terms of avoiding false positives. We have achieved above 90% 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.https://www.mdpi.com/2076-3417/9/15/2990elevator systemdeep autoencoderfault detectionfeature extractionrandom forestprofile extraction |
| spellingShingle | Krishna Mohan Mishra Kalevi Huhtala Elevator Fault Detection Using Profile Extraction and Deep Autoencoder Feature Extraction for Acceleration and Magnetic Signals Applied Sciences elevator system deep autoencoder fault detection feature extraction random forest profile extraction |
| title | Elevator Fault Detection Using Profile Extraction and Deep Autoencoder Feature Extraction for Acceleration and Magnetic Signals |
| title_full | Elevator Fault Detection Using Profile Extraction and Deep Autoencoder Feature Extraction for Acceleration and Magnetic Signals |
| title_fullStr | Elevator Fault Detection Using Profile Extraction and Deep Autoencoder Feature Extraction for Acceleration and Magnetic Signals |
| title_full_unstemmed | Elevator Fault Detection Using Profile Extraction and Deep Autoencoder Feature Extraction for Acceleration and Magnetic Signals |
| title_short | Elevator Fault Detection Using Profile Extraction and Deep Autoencoder Feature Extraction for Acceleration and Magnetic Signals |
| title_sort | elevator fault detection using profile extraction and deep autoencoder feature extraction for acceleration and magnetic signals |
| topic | elevator system deep autoencoder fault detection feature extraction random forest profile extraction |
| url | https://www.mdpi.com/2076-3417/9/15/2990 |
| work_keys_str_mv | AT krishnamohanmishra elevatorfaultdetectionusingprofileextractionanddeepautoencoderfeatureextractionforaccelerationandmagneticsignals AT kalevihuhtala elevatorfaultdetectionusingprofileextractionanddeepautoencoderfeatureextractionforaccelerationandmagneticsignals |