DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS
Klíčová slova:
Wayside diagnosis, local binary patterns, wavelet packet energy, detecting abnormal dataAbstrakt
This paper examines three different methods in comparison for discovering abnormal sensor data retrieved by acoustic and mono-axial accelerometer sensors that are employed in the environment of different train sets and passes to achieve a cost friendly wayside diagnosis in Prague metros. Proposed methodology, Local Binary Patterns (LBP) on resized Kurtogram images is superior to compared methods up to 75.8% Fisher Linear Discriminant Analysis (FLDA) for anomaly detection in the sensor data. Results may count to be promising even if combined acoustic and vibration sensor data related Kurtograms are used for individual train sets. Proposed method is considered to be the first step in order to achieve an efficient diagnosis framework in wayside vehicle diagnosis.
Stažení
Data o stažení nejsou doposud dostupná.
Reference
(1) MAO, Chao, Yu JIANG, Dezhi WANG, Xun CHEN a Junyong TAO. Modeling and simulation of non-stationary vehicle vibration signals based on Hilbert spectrum. Mechanical Systems and Signal Processing. 2015, 50-51, 56–69. ISSN 0888-3270.
(2) HLOUŠEK, Petr. Phase analysis of interference currents of railway vehicles. Electroscope, Applied Electronics. 2008, 2008(3), 241–244. ISSN 1802-4564.
(3) DING, Weidong, Jinling WANG, Chris RIZOS a Doug KINLYSIDE. Improving adaptive Kalman estimation in GPS/INS integration. Journal of Navigation. 2007, 60(03), 517–529. ISSN 1469-7785.
(4) KILINC, Onur a Altan ONAT. Simple test procedure of strain gage measurement: an introductory implementation towards railway vehicle testing. 1st International Workshop on Construction and Electricity Applications on Vocational Education. 2015, 2(Special Issue (December)), 393–405. ISSN 2147-8503.
(5) SHAHIDI, Parham, Daniel MARAINI, Brad HOPKINS a Andrew SEIDEL. Railcar bogie performance monitoring using mutual information and support vector machines. Annual Conference Of The Prognostics And Health Management Society. 2015, 1–10.
(6) BARKE, Derek a W. K. CHIU. Structural health monitoring in the railway industry: a review. Structural Health Monitoring. 2005, 4(1), 81–93.
(7) HIDE, C., T. MOORE a M. SMITH. Adaptive Kalman filtering algorithms for integrating GPS and low cost INS. In: [online]. B.m.: IEEE, 2004, s. 227–233 [vid. 2015-09-29]. ISBN 0-7803-8416-4. Dostupné z: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1308998
(8) BISHOP, Jacob. The Kalman filter. 2007, 1–6.
(9) YEN, Gary G. a Kuo-Chung LIN. Wavelet packet feature extraction for vibration monitoring. Industrial Electronics, IEEE Transactions on. 2000, 47(3), 650–667.
(10) TAHIR, Muhammad Masood a Ayyaz HUSSAIN. Pattern Recognition of Bearing Faults using Smoother Statistical Features. arXiv preprint arXiv:1503.04444 [online]. 2015 [vid. 2016-05-28]. Dostupné z: http://arxiv.org/abs/1503.04444
(11) DWYER, Roger F. Detection of non-Gaussian signals by frequency domain kurtosis estimation. In: Acoustics, Speech, and Signal Processing, IEEE International Conference [online]. B.m.: IEEE, 1983, s. 607–610 [vid. 2016-05-29]. Dostupné z: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1172264
(12) ANTONI, Jérôme. Fast computation of the kurtogram for the detection of transient faults. Mechanical Systems and Signal Processing. 2007, 21(1), 108–124. ISSN 08883270.
(13) ZHOU, Shu-Ren, Jian-Ping YIN a Jian-Ming ZHANG. Local binary pattern (LBP) and local phase quantization (LBQ) based on Gabor filter for face representation. Neurocomputing. 2013, 116, 260–264. ISSN 09252312.
(14) GUO, Yimo, Guoying ZHAO a Matti PIETIKÄINEN. Texture classification using a linear configuration model based descriptor. In: [online]. B.m.: British Machine Vision Association, 2011, s. 119.1–119.10 [vid. 2013-07-22]. ISBN 1-901725-43-X. Dostupné z: http://www.bmva.org/bmvc/2011/proceedings/paper119/index.html
(15) KHAN, Mohammad Farhan, Ekram KHAN a Z.A. ABBASI. Image contrast enhancement using normalized histogram equalization. Optik - International Journal for Light and Electron Optics. 2015, 126(24), 4868–4875. ISSN 00304026.
(2) HLOUŠEK, Petr. Phase analysis of interference currents of railway vehicles. Electroscope, Applied Electronics. 2008, 2008(3), 241–244. ISSN 1802-4564.
(3) DING, Weidong, Jinling WANG, Chris RIZOS a Doug KINLYSIDE. Improving adaptive Kalman estimation in GPS/INS integration. Journal of Navigation. 2007, 60(03), 517–529. ISSN 1469-7785.
(4) KILINC, Onur a Altan ONAT. Simple test procedure of strain gage measurement: an introductory implementation towards railway vehicle testing. 1st International Workshop on Construction and Electricity Applications on Vocational Education. 2015, 2(Special Issue (December)), 393–405. ISSN 2147-8503.
(5) SHAHIDI, Parham, Daniel MARAINI, Brad HOPKINS a Andrew SEIDEL. Railcar bogie performance monitoring using mutual information and support vector machines. Annual Conference Of The Prognostics And Health Management Society. 2015, 1–10.
(6) BARKE, Derek a W. K. CHIU. Structural health monitoring in the railway industry: a review. Structural Health Monitoring. 2005, 4(1), 81–93.
(7) HIDE, C., T. MOORE a M. SMITH. Adaptive Kalman filtering algorithms for integrating GPS and low cost INS. In: [online]. B.m.: IEEE, 2004, s. 227–233 [vid. 2015-09-29]. ISBN 0-7803-8416-4. Dostupné z: http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1308998
(8) BISHOP, Jacob. The Kalman filter. 2007, 1–6.
(9) YEN, Gary G. a Kuo-Chung LIN. Wavelet packet feature extraction for vibration monitoring. Industrial Electronics, IEEE Transactions on. 2000, 47(3), 650–667.
(10) TAHIR, Muhammad Masood a Ayyaz HUSSAIN. Pattern Recognition of Bearing Faults using Smoother Statistical Features. arXiv preprint arXiv:1503.04444 [online]. 2015 [vid. 2016-05-28]. Dostupné z: http://arxiv.org/abs/1503.04444
(11) DWYER, Roger F. Detection of non-Gaussian signals by frequency domain kurtosis estimation. In: Acoustics, Speech, and Signal Processing, IEEE International Conference [online]. B.m.: IEEE, 1983, s. 607–610 [vid. 2016-05-29]. Dostupné z: http://ieeexplore.ieee.org/xpls/abs_all.jsp?arnumber=1172264
(12) ANTONI, Jérôme. Fast computation of the kurtogram for the detection of transient faults. Mechanical Systems and Signal Processing. 2007, 21(1), 108–124. ISSN 08883270.
(13) ZHOU, Shu-Ren, Jian-Ping YIN a Jian-Ming ZHANG. Local binary pattern (LBP) and local phase quantization (LBQ) based on Gabor filter for face representation. Neurocomputing. 2013, 116, 260–264. ISSN 09252312.
(14) GUO, Yimo, Guoying ZHAO a Matti PIETIKÄINEN. Texture classification using a linear configuration model based descriptor. In: [online]. B.m.: British Machine Vision Association, 2011, s. 119.1–119.10 [vid. 2013-07-22]. ISBN 1-901725-43-X. Dostupné z: http://www.bmva.org/bmvc/2011/proceedings/paper119/index.html
(15) KHAN, Mohammad Farhan, Ekram KHAN a Z.A. ABBASI. Image contrast enhancement using normalized histogram equalization. Optik - International Journal for Light and Electron Optics. 2015, 126(24), 4868–4875. ISSN 00304026.
Stahování
Publikováno
2017-12-20
Jak citovat
Kilinc, O., & Vágner, J. (2017). DETECTING ANOMALOUS SENSOR DATA IN WAYSIDE DIAGNOSTICS USING ENHANCED LBP-KURTOGRAMS. Perner’s Contacts, 12(4), 23–30. Získáno z https://pernerscontacts.upce.cz/index.php/perner/article/view/474
Číslo
Sekce
Články
Licence
Copyright (c) 2020 Onur Kilinc##common.commaListSeparator##Jakub Vágner
Tato práce je licencována pod Mezinárodní licencí Creative Commons Attribution 4.0 .
