Supervised and unsupervised learning process in damage classification of rolling element bearings

• Autorzy: Strączkiewicz M. , Czop P. , Barszcz T.

Warianty tytułu

PL

Nadzorowany i nienadzorowany proces uczenia w klasyfikacji uszkodzeń łożysk tocznych

• Języki publikacji: EN

Abstrakty

EN

Damage classification plays a crucial role in the process of management in nearly every branch of industry. In fact, is becomes equally important as damage detection, since it can provide information of malfunction severity and hence lead to improvement of a production or manufacturing process. Within this paper selected supervised and unsupervised pattern recognition methods are employed for this purpose. The attention of the authors is given to assessment of selection, performance benchmarking and applicability of selected pattern recognition methods. The investigation is performed on the data collected using an experimental test grid and rolling element bearing with deteriorating condition of an outer race.

PL

Klasyfikacja uszkodzeń odgrywa ważną rolę w procesie zarządzania w niemalże każdej gałęzi przemysłu. W rzeczywistości staje się ona równie istotna co samo wykrywanie uszkodzenia ponieważ pozwala określić stopień uszkodzenia, a co za tym idzie, poprawić efektywność zarządzania zakładem przemysłowym. W tym celu wykorzystano wybrane nadzorowane i nienadzorowane metody rozpoznawania wzorców. W artykule zwrócono uwagę na ocenę wyboru, porównanie wydajności oraz możliwości wykorzystania tych metod. Analiza przeprowadzona została na danych zgromadzonyh na eksperymentalnym stanowisku testowym, gdzie obserwowany jest stan łożyska tocznego z pogłębiającym się uszkodzeniem bieżni zewnętrznej.

Słowa kluczowe

EN

fault classification; pattern recognition; rolling element bearing; multiple classifiers comparison

PL

klasyfikacja uszkodzeń; rozpoznawanie wzorców; łożysko toczne; porównanie klasyfikatorów

• Wydawca: Polskie Towarzystwo Diagnostyki Technicznej
• Czasopismo: Diagnostyka
• Rocznik: 2016
• Tom: Vol. 17, No. 2
• Strony: 71--80
• Opis fizyczny: Bibliogr. 43 poz., rys., tab., wykr.

Twórcy

autor

Strączkiewicz M.

• AGH University of Science and Technology, Department of Robotics and Mechatronics, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Czop P.

• AGH University of Science and Technology, Department of Robotics and Mechatronics, al. Mickiewicza 30, 30-059 Kraków, Poland

autor

Barszcz T.

• AGH University of Science and Technology, Department of Robotics and Mechatronics, al. Mickiewicza 30, 30-059 Kraków, Poland

Bibliografia

• [1] Barszcz T, Jabłoński A, Strączkiewicz M. New generation of condition monitoring systems for nonstationary machinery – proposal of the architecture, 10th International Conference on Condition Monitoring and Machinery Failure Prevention Technologies, 2013, Krakow, Poland, pp. 1-10.
• [2] Rytter A. Vibrational based inspection of civil engineering structures, fractures and dynamics [PhD thesis], defended publicly at the University of Aalborg; Department of Building Technology and Structural Engineering, Aalborg University, April 20, 1993, p. 206.
• [3] Urbanek J, Barszcz T, Antoni J. A two-step procedure for estimation of instantaneous rotational speed with large fluctuations, Mechanical Systems and Signal Processing 38/1 (2013) 96-102.
• [4] Barszcz T, Randall RB. Application of spectral kurtosis for detection of a tooth crack in the planetary gear of a wind turbine, Mechanical Systems and Signal Processing 23 (2009) 1352-1365.
• [5] Barszcz T, Czop P. Presentation of a virtual power plant environment and its application with combined first-principle and data-driven models intended for the diagnostics of a power plant, Pt. 1, Simulation 88/2 (2012) 139-166.
• [6] Strączkiewicz M, Barszcz T, Jabłoński A. Detection and classification of alarm threshold violations in condition monitoring systems working in highly varying operational conditions, Journal of Physics. Conference Series 628 (2015), doi:10.1088/1742-6596/628/1/012087.
• [7] Barszcz T, Strączkiewicz M. Novel intuitive hierarchical structures for condition monitoring system of wind turbines, Diagnostyka, 14/3 (2013) 53-60.
• [8] Tabaszewski M. Optimization of a nearest neighbors classifier for diagnosis of condition of rolling bearings, Diagnostyka 15/1 (2014) 37-42.
• [9] Jain AK, Duin R PW, Mao J. Statistical Pattern Recognition: A Review, IEEE Transactions on Pattern Analysis and Machine Intelligence 22/1 (2000) 4-37.
• [10] Vachtsevanos G, Lewis F, Roemer M, Hess A, Wu B. Intelligent Fault Diagnosis and Prognosis for Engineering Systems, John Wiley & Sons, New York, 2006.
• [11] Van Der Heijden F, Duin R P W, de Ridder D, Tax D M J. Classification, Parameter Estimation and State Estimation, An Engineering Approach using MATLAB, 2004, John Wiley and Sons, Chichester, England.
• [12] Worden K, Staszewski WJ, Hensman JJ. Natural computing for mechanical systems research: a tutorial overview, Mechanical Systems and Signal Processing, 25 (2011) 4-111.
• [13] Theodoridis S, Koutroumbas K. Pattern Recognition, Fourth Edition, Academic Press, 2008.
• [14] Mechefske CK, Mathew J. Fault detection and diagnosis in low speed rolling element bearing. Part II: the use of nearest neighbor classification, Mechanical Systems and Signal Processing 6 (1992) 309-316.
• [15] Lei Y, Zuo MJ, Gear crack level identification based on weighted K nearest neighbor classification algorithm, Mechanical Systems and Signal Processing 23/5 (2009) 1535-1547.
• [16] Casimir R, Boutleux E, Clerc G, Yahoui A. The use of features selection and nearest neighbors rule for faults diagnostic in induction motors, Engineering Applications of Artificial Intelligence 19 (2006) 169-177.
• [17] McCullagh P, Nelder JA. Generalized Linear Models, New York: Chapman & Hall, 1990.
• [18] Schlechtingen M, Ferreira I. Santos, Comparative analysis of neural network and regression based condition monitoring approaches for wind turbine fault detection, Mechanical Systems and Signal Processing 25/5 (2011) 1849-1875.
• [19] McLachlan GJ. Discriminant Analysis and Statistical Pattern Recognition, Wiley, Hoboken, NJ, 1992.
• [20] Kim Y, Kim NY, Park SY, Lee DK, Lee JH. Classification and individualization of used engine oils using elemental composition and discriminant analysis, Forensic Science International 230/1-3 (2013) 58-67.
• [21] Du Zh, Jin X. Multiple faults diagnosis for sensors in air handling unit using Fisher discriminant analysis, Energy Conversion and Management, 49/12 (2008) 3654-3665.
• [22] Houshmand AA, Kannatey-Asibu Jr E. Statistical process control of acoustic emission for cutting tool monitoring, Mechanical Systems and Signal Processing 3/4 (1989) 405-424.
• [23] Sánchez J, Perronnin F, Mensink T, Verbeek J. Image Classification with the Fisher Vector: Theory and Practice, International Journal of Computer Vision, 105/3 (2013) 222-245.
• [24] Głowacz A, Głowacz A, Korohoda P. Recognition of Monochrome Thermal Images of Synchronous Motor with the Application of Binarization and Nearest Mean Classifier, Archives of Metallurgy and Materials, 59/1 (2014) 31-34.
• [25] Parzen E. On the estimation of a probability density function and mode, The Annals of Mathematical Statistics., 33 (1962) 1065-1076.
• [26] Chen X, Xu G. A self-adaptive alarm method for tool condition monitoring based on Parzen window estimation, Journal of Vibroengineering 15/3 (2013) 1537-1545.
• [27] Qian Y, Mita A. Structural damage identification using Parzen-window approach and neural networks, Structural Control and Health Monitoring, 14/4 (2007) 576–590.
• [28] Joo Er M, Wu S, Lu J, and Toh H L. Face recognition with radial basis function (RBF) neural networks, IEEE Transactions on Neural Networks, 13/3 (2002) 697-710.
• [29] Paya B A, Esat I I, Badi M N M. Artificial neural network based fault diagnostics of rotating machinery using wavelet transforms as a preprocessor, Mechanical Systems and Signal Processing 11/5 (1997) 751-765.
• [30] Baillie DC, Mathew J. A comparison of autoregressive modeling techniques for fault diagnosis of rolling element bearings, Mechanical Systems and Signal Processing 10/1 (1996) 1-17.
• [31] Rousseeuw P J, Silhouettes: A graphical aid to the interpretation and validation of cluster analysis, Journal of Computational and Applied Mathematics 20 (1987) 53-65.
• [32] Thalamuthu A, Mukhopadhyay I, Zheng X, Tseng GC. Evaluation and comparison of gene clustering methods in microarray analysis, Bioinformatics, 22/19 (2006) 2405-2412.
• [33] Hullermeier E. Fuzzy methods in machine learning and data mining: Status and prospects, Fuzzy Sets and Systems 156 (2005) 387-406.
• [34] Liu TI, Singonahalli JH, Iyer NR. Detection of roller bearings defects using expert system and fuzzy logic, Mechanical Systems and Signal Processing, 10 (1996) 595-614.
• [35] Strączkiewicz M, Czop P, Barszcz T. The use of a fuzzy logic approach for integration of vibrationbased diagnostic features of rolling element bearings, Journal of Vibroengineering, 17/4 (2015), 1760-1768.
• [36] Jabłoński A, Barszcz T. Validation of vibration measurements for heavy duty machinery diagnostics, Mechanical Systems and Signal Processing 48/1 (2013) 248-263.
• [37] Epps IK. An investigation into Vibrations Excited by Discrete Faults in Rolling Element Bearings, PhD Thesis, School of Mechanical Engineering, The University of Canterbury, Christchurch, New Zealand, 1991.
• [38] Rawashdeh M, Ralescu A. Fuzzy cluster validity with generalized silhouettes, Proceedings of the 23rd Annual Midwest Artificial Intelligence and Cognitive Science Conference, Cincinnati, Ohio, USA, 2012, pp. 11–18.
• [39] Bezdek J C. Cluster validity with fuzzy sets, Taylor & Francis Group 3/3 (1973) 58-73.
• [40] Sheng Li A. The Improved Partition Coefficient, Procedia Engineering, 24 (2011) 534–538.
• [41] Yeh JH, Joung FJ, Lin JC. CDV Index: A Validity Index for Better Clustering Quality Measurement, Journal of Computer and Communications 2/4 (2014) 163-171.
• [42] Wang W, Zhang Y, On fuzzy cluster validity indices, Fuzzy Sets and Systems 158/19 (2007) 2095-2117.
• [43] Dudoit S, Fridlyand J. A prediction-based resampling method for estimating the number of clusters in a dataset Genome Biology 3/7 (2002) 1-21.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.