Diagnostics measure for roller bearings based on variable moiré gratings

Abstract This paper is focused on the construction of a novel signal processing algorithm for the diagnostics of roller bearings. The proposed approach is based on the computational analysis of time-averaged images produced by specially designed moire gratings which are deflected from the state of equilibrium according to the recorder vibration signal of the bearing. It is demonstrated that the statistical properties of time-averaged images can be exploited as an effective diagnostics measure of roller bearings. Extensive computational experiments with a dataset provided by the Center for Intelligent Maintenance Systems, University of Cincinnati are used to demonstrate the efficacy of the proposed technique.

[1]  Wei Guo,et al.  A hybrid fault diagnosis method based on second generation wavelet de-noising and local mean decomposition for rotating machinery. , 2016, ISA transactions.

[2]  DaiQionghai,et al.  Special Section on Advanced Displays , 2013 .

[3]  Jun-Geol Baek,et al.  A Novel Image Feature for the Remaining Useful Lifetime Prediction of Bearings Based on Continuous Wavelet Transform and Convolutional Neural Network , 2018, Applied Sciences.

[4]  Chen Lu,et al.  Fault Diagnosis for Rotating Machinery: A Method based on Image Processing , 2016, PloS one.

[5]  Huei-Yung Lin,et al.  Vehicle speed detection from a single motion blurred image , 2008, Image Vis. Comput..

[6]  D. Kugiumtzis.  State space reconstruction parameters in the analysis of chaotic time series—the role of the time window length , 1996, comp-gas/9602002.

[7]  Ming Liang,et al.  Bearing fault diagnosis under unknown time-varying rotational speed conditions via multiple time-frequency curve extraction , 2018 .

[8]  Libor Machala,et al.  Blurred image restoration: A fast method of finding the motion length and angle , 2010, Digit. Signal Process..

[9]  Zenonas Navickas,et al.  Time Average Geometric Moiré—Back to the Basics , 2009 .

[10]  Kun Jiang,et al.  A deep capsule neural network with stochastic delta rule for bearing fault diagnosis on raw vibration signals , 2019 .

[11]  Michael Grass,et al.  Motion estimation and correction in cardiac CT angiography images using convolutional neural networks , 2019, Comput. Medical Imaging Graph..

[12]  Qionghai Dai,et al.  Robust blind motion deblurring using near-infrared flash image , 2013, J. Vis. Commun. Image Represent..

[13]  Minvydas Ragulskis,et al.  The structure of moiré grating lines and its influence to time-averaged fringes , 2009 .

[14]  Noureddine Zerhouni,et al.  A Data-Driven Failure Prognostics Method Based on Mixture of Gaussians Hidden Markov Models , 2012, IEEE Transactions on Reliability.

[15]  Adam Świtoński,et al.  Phase space reconstruction and estimation of the largest Lyapunov exponent for gait kinematic data , 2015 .

[16]  S. Strogatz.  Nonlinear Dynamics and Chaos: With Applications to Physics, Biology, Chemistry and Engineering , 1995 .

[17]  Qionghai Dai,et al.  Non-uniform image deblurring using an optical computing system , 2013, Comput. Graph..

[18]  Wei Li,et al.  Fault Diagnosis of Rolling Bearings Based on Improved Kurtogram in Varying Speed Conditions , 2019, Applied Sciences.

[19]  Jing Yuan,et al.  Wavelet transform based on inner product in fault diagnosis of rotating machinery: A review , 2016 .

[20]  Yuichi Matsuda,et al.  Camera vibration measurement using blinking light-emitting diode array. , 2017, Optics express.

[21]  David Pearce MacAdam,et al.  Digital Image Restoration by Constrained Deconvolution , 1970 .

[22]  Wei Chen,et al.  Intelligent fault diagnosis of rotating machinery using support vector machine with ant colony algorithm for synchronous feature selection and parameter optimization , 2015, Neurocomputing.

[23]  Hai Qiu,et al.  Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics , 2006 .

[24]  Jianbo Yu,et al.  Local and Nonlocal Preserving Projection for Bearing Defect Classification and Performance Assessment , 2012, IEEE Transactions on Industrial Electronics.

[25]  Ahlad Kumar,et al.  Deblurring of motion blurred images using histogram of oriented gradients and geometric moments , 2017, Signal Process. Image Commun..

[26]  Martin Casdagli,et al.  An analytic approach to practical state space reconstruction , 1992 .

[27]  Robert Goutte,et al.  Digital deconvolution of degraded images by a space-invariant motion blur , 1980 .

[28]  Albert S. Kobayashi,et al.  Handbook on experimental mechanics , 1987 .

[29]  P. Xu.  Differential phase space reconstructed for chaotic time series , 2009 .

[30]  Jan Flusser,et al.  Space-Variant Restoration of Images Degraded by Camera Motion Blur , 2008, IEEE Transactions on Image Processing.

[31]  Krzysztof Patorski,et al.  Handbook of the moiré fringe technique , 1993 .

[32]  Peter W. Tse,et al.  Order spectrogram visualization for rolling bearing fault detection under speed variation conditions , 2019, Mechanical Systems and Signal Processing.

[33]  Vincenzo Caglioti,et al.  Recovering ball motion from a single motion-blurred image , 2009, Comput. Vis. Image Underst..

[34]  Klaus Diepold,et al.  Comparison of motion de-blur algorithms and real world deployment , 2006 .

[35]  Minvydas Ragulskis,et al.  Applicability of time-average moiré techniques for chaotic oscillations. , 2007, Physical review. E, Statistical, nonlinear, and soft matter physics.