Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults
Condition monitoring is an indispensable element related to the operation of rotating machinery. In this article, the monitoring system for the parallel gearbox was proposed. The novelty detection approach is used to develop the condition assessment support system, which requires data collection for...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2021-05-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/21/10/3536 |
id |
doaj-a713d3ed54974ba3a85b7034c0dd7f93 |
---|---|
record_format |
Article |
spelling |
doaj-a713d3ed54974ba3a85b7034c0dd7f932021-06-01T00:28:51ZengMDPI AGSensors1424-82202021-05-01213536353610.3390/s21103536Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery FaultsJakub Górski0Adam Jabłoński1Mateusz Heesch2Michał Dziendzikowski3Ziemowit Dworakowski4Department of Robotics and Mechatronics, Faculty of Mechanical Engineering and Robotics, AGH University of Science and Technology, 30-059 Krakow, PolandDepartment of Robotics and Mechatronics, Faculty of Mechanical Engineering and Robotics, AGH University of Science and Technology, 30-059 Krakow, PolandDepartment of Robotics and Mechatronics, Faculty of Mechanical Engineering and Robotics, AGH University of Science and Technology, 30-059 Krakow, PolandAir Force Institute of Technology, Airworthiness Division, ul. Ks. Boleslawa 6, 01-494 Warsaw, PolandDepartment of Robotics and Mechatronics, Faculty of Mechanical Engineering and Robotics, AGH University of Science and Technology, 30-059 Krakow, PolandCondition monitoring is an indispensable element related to the operation of rotating machinery. In this article, the monitoring system for the parallel gearbox was proposed. The novelty detection approach is used to develop the condition assessment support system, which requires data collection for a healthy structure. The measured signals were processed to extract quantitative indicators sensitive to the type of damage occurring in this type of structure. The indicator’s values were used for the development of four different novelty detection algorithms. Presented novelty detection models operate on three principles: feature space distance, probability distribution, and input reconstruction. One of the distance-based models is adaptive, adjusting to new data flowing in the form of a stream. The authors test the developed algorithms on experimental and simulation data with a similar distribution, using the training set consisting mainly of samples generated by the simulator. Presented in the article results demonstrate the effectiveness of the trained models on both data sets.https://www.mdpi.com/1424-8220/21/10/3536novelty detectiondata streamsoft computinggearboxfault detection |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Jakub Górski Adam Jabłoński Mateusz Heesch Michał Dziendzikowski Ziemowit Dworakowski |
spellingShingle |
Jakub Górski Adam Jabłoński Mateusz Heesch Michał Dziendzikowski Ziemowit Dworakowski Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults Sensors novelty detection data stream soft computing gearbox fault detection |
author_facet |
Jakub Górski Adam Jabłoński Mateusz Heesch Michał Dziendzikowski Ziemowit Dworakowski |
author_sort |
Jakub Górski |
title |
Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults |
title_short |
Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults |
title_full |
Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults |
title_fullStr |
Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults |
title_full_unstemmed |
Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults |
title_sort |
comparison of novelty detection methods for detection of various rotary machinery faults |
publisher |
MDPI AG |
series |
Sensors |
issn |
1424-8220 |
publishDate |
2021-05-01 |
description |
Condition monitoring is an indispensable element related to the operation of rotating machinery. In this article, the monitoring system for the parallel gearbox was proposed. The novelty detection approach is used to develop the condition assessment support system, which requires data collection for a healthy structure. The measured signals were processed to extract quantitative indicators sensitive to the type of damage occurring in this type of structure. The indicator’s values were used for the development of four different novelty detection algorithms. Presented novelty detection models operate on three principles: feature space distance, probability distribution, and input reconstruction. One of the distance-based models is adaptive, adjusting to new data flowing in the form of a stream. The authors test the developed algorithms on experimental and simulation data with a similar distribution, using the training set consisting mainly of samples generated by the simulator. Presented in the article results demonstrate the effectiveness of the trained models on both data sets. |
topic |
novelty detection data stream soft computing gearbox fault detection |
url |
https://www.mdpi.com/1424-8220/21/10/3536 |
work_keys_str_mv |
AT jakubgorski comparisonofnoveltydetectionmethodsfordetectionofvariousrotarymachineryfaults AT adamjabłonski comparisonofnoveltydetectionmethodsfordetectionofvariousrotarymachineryfaults AT mateuszheesch comparisonofnoveltydetectionmethodsfordetectionofvariousrotarymachineryfaults AT michałdziendzikowski comparisonofnoveltydetectionmethodsfordetectionofvariousrotarymachineryfaults AT ziemowitdworakowski comparisonofnoveltydetectionmethodsfordetectionofvariousrotarymachineryfaults |
_version_ |
1721414761773531136 |