Evaluation of Multiclass Novelty Detection Algorithms for Electric Machine Monitoring

2019 ◽  
Author(s):  
M. Ramirez Chavez ◽  
L. Ruiz Soto ◽  
F. Arellano Espitia ◽  
J. J. Saucedo ◽  
M. Delgado Prieto ◽  
...  
Keyword(s):  
Novelty Detection ◽  
Electric Machine ◽  
Detection Algorithms ◽  
Machine Monitoring

scholarly journals Comparison of Novelty Detection Methods for Detection of Various Rotary Machinery Faults

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3536
Author(s):  
Jakub Górski ◽  
Adam Jabłoński ◽  
Mateusz Heesch ◽  
Michał Dziendzikowski ◽  
Ziemowit Dworakowski
Keyword(s):  
Novelty Detection ◽  
Feature Space ◽  
Detection Methods ◽  
Data Sets ◽  
Similar Distribution ◽  
Detection Algorithms ◽  
Rotary Machinery ◽  
Detection Approach ◽  
Input Reconstruction ◽  
Quantitative Indicators

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.

scholarly journals Automated diagnosis of heart valve degradation using novelty detection algorithms and machine learning

PLoS ONE ◽  
2019 ◽  
Vol 14 (9) ◽  
pp. e0222983 ◽  
Author(s):  
Bernhard Vennemann ◽  
Dominik Obrist ◽  
Thomas Rösgen
Keyword(s):  
Machine Learning ◽  
Heart Valve ◽  
Novelty Detection ◽  
Automated Diagnosis ◽  
Detection Algorithms

scholarly journals Evaluation of Multiclass Novelty Detection Algorithms for Data Streams

2015 ◽  
Vol 27 (11) ◽  
pp. 2961-2973 ◽  
Author(s):  
Elaine Ribeiro de Faria ◽  
Isabel Ribeiro Goncalves ◽  
Jo ao Gama ◽  
Andre Carlos Ponce de Leon Ferreira Carvalho
Keyword(s):  
Data Streams ◽  
Novelty Detection ◽  
Detection Algorithms

scholarly journals A comparative evaluation of novelty detection algorithms for discrete sequences

2019 ◽  
Vol 53 (5) ◽  
pp. 3787-3812 ◽  
Author(s):  
Rémi Domingues ◽  
Pietro Michiardi ◽  
Jérémie Barlet ◽  
Maurizio Filippone
Keyword(s):  
Comparative Evaluation ◽  
Novelty Detection ◽  
Detection Algorithms ◽  
Discrete Sequences

scholarly journals Evaluation Methodology for Multiclass Novelty Detection Algorithms

2013 ◽  
Author(s):  
Elaine R. Faria ◽  
Isabel J.C.R. Goncalves ◽  
Joao Gama ◽  
Andre C.P.L.F. Carvalho
Keyword(s):  
Novelty Detection ◽  
Evaluation Methodology ◽  
Detection Algorithms

The application of black-box modeling in long-term tunnel deformation monitoring

2021 ◽  
Author(s):  
Kristof Maes ◽  
Stijn François ◽  
Wim Salens ◽  
Gerrit Feremans ◽  
Koen Segher
Keyword(s):  
Asset Management ◽  
Early Stage ◽  
Novelty Detection ◽  
Warning System ◽  
Principal Component ◽  
Black Box ◽  
Deformation Monitoring ◽  
Detection Algorithms ◽  
Tunnel Monitoring

<p>Tunnel closures related to maintenance and reconstruction works can lead to large economical costs and should therefore be avoided. This paper explores the use of novelty detection algorithms for long-term tunnel monitoring. The aim is to detect tunnel damage in an early stage, as such providing a tool to support the asset management. The proposed strategy is applied to the monitoring of the Waasland tunnel in Antwerp, where the deformations and temperatures have been monitored over a period of 14 months. The case demonstrates that novelty detection by means of principal component analysis enables the identification of minor changes in the tunnel response, and can therefore be embedded in an early detection warning system.</p>

Novelty Detection in System Monitoring and Control with HONU

2016 ◽  
pp. 61-78 ◽  
Author(s):  
Cyril Oswald ◽  
Matous Cejnek ◽  
Jan Vrba ◽  
Ivo Bukovsky
Keyword(s):  
Novelty Detection ◽  
Self Organizing Map ◽  
Monitoring And Control ◽  
Control Loops ◽  
Detection Algorithms ◽  
Novel Approach ◽  
Adaptive Monitoring ◽  
Multiple Input ◽  
Single Input ◽  
And Control

With focus on Higher Order Neural Units (HONUs), this chapter reviews two recently introduced adaptive novelty detection algorithms based on supervised learning of HONU with extension to adaptive monitoring of existing control loops. Further, the chapter also introduces a novel approach for novelty detection via local model monitoring with Self-organizing Map (SOM) and HONU. Further, it is discussed how these principles can be used to distinguish between external and internal perturbations of identified plant or control loops. The simulation result will demonstrates the potentials of the algorithms for single-input plants as well as for some representative of multiple-input plants and for the improvement of their control.

Insider Threat Detection based on User behavior Model and Novelty Detection Algorithms

2017 ◽  
Vol 43 (4) ◽  
pp. 276-287 ◽  
Author(s):  
Haedong Kim ◽  
Junhong Kim ◽  
Minsik Park ◽  
Suhyoun Cho ◽  
Pilsung Kang
Keyword(s):  
User Behavior ◽  
Novelty Detection ◽  
Insider Threat ◽  
Threat Detection ◽  
Behavior Model ◽  
Detection Algorithms

Machine learning in industrial measurement technology for detection of known and unknown faults of equipment and sensors

2019 ◽  
Vol 86 (11) ◽  
pp. 706-718
Author(s):  
Tizian Schneider ◽  
Steffen Klein ◽  
Andreas Schütze
Keyword(s):  
Condition Monitoring ◽  
Novelty Detection ◽  
Industrial Condition ◽  
Fault Classification ◽  
Measurement Technology ◽  
Suggested Approach ◽  
Detection Algorithms ◽  
Advantages And Disadvantages ◽  
Data Scientist ◽  
Industrial Measurement

AbstractThis paper focuses on the application of novelty detection in combination with supervised fault classification for industrial condition monitoring. Its goal is to provide a guideline for engineers on how to apply novelty detection for outlier detection, monitoring of supervised classification and detection of unknown faults without the need of a data scientist. All guidelines are demonstrated by means of a publicly available condition monitoring dataset. In each application case the results achieved with different common novelty detection algorithms are compared, advantages and disadvantages of the respective algorithms are shown. To increase applicability of the suggested approach visualization of results is emphasized and all algorithms have been included in a publicly available data analysis software toolbox with graphical user interface.

Sign in / Sign up

Export Citation Format

Share Document