×

Knowledge extraction from deep convolutional neural networks applied to cyclo-stationary time-series classification. (English) Zbl 1458.68193

Summary: Modelling complex processes from raw time series increases the necessity to build Deep Learning (DL) architectures that can manage this type of data structure. However, as DL models become deeper, larger and more diverse datasets are necessary and knowledge extraction will become more difficult. In an attempt to sidestep these issues, in this paper a methodology based on two main steps is presented, the first being to increase size and diversity of time-series datasets for training, and the second to retrieve knowledge from the obtained model. This methodology is compared with other approaches reported in the literature and is tested under two configuration setups of Condition-Based Maintenance problems: fault diagnosis of bearing, and fault severity assessment of a helical gearbox, obtaining not only a performance improvement in comparison, but also in retrieving knowledge about how the signals are being classified.

MSC:

68T07 Artificial neural networks and deep learning
62H30 Classification and discrimination; cluster analysis (statistical aspects)
62M10 Time series, auto-correlation, regression, etc. in statistics (GARCH)
62M45 Neural nets and related approaches to inference from stochastic processes

Software:

GitHub
PDFBibTeX XMLCite
Full Text: DOI Link

References:

[1] Antoni, J.; Randall, R., The spectral kurtosis: application to the vibratory surveillance and diagnostics of rotating machines, Mech. Syst. Signal Process., 20, 2, 308-331 (2006)
[2] Arfken, G. B.; Weber, H. J., Mathematical Methods for Physicists, 6th Edition (2005), Academic Press · Zbl 1066.00001
[3] Bagnall, A.; Lines, J.; Hills, J.; Bostrom, A., Time-series classification with COTE: the collective of transformation-based ensembles, IEEE Trans. Knowl. Data Eng., 27, 9, 2522-2535 (2015)
[4] Braun, S.; Seth, B., Analysis of repetitive mechanism signatures, J. Sound Vib., 70, 4, 513-526 (1980)
[5] D. Cabrera, Cnn1d, 2018, (https://github.com/diegoroman17/cnn1d).
[6] Cabrera, D.; Sancho, F.; Li, C.; Cerrada, M.; Sánchez, R.-V.; Pacheco, F.; de Oliveira, J. V., Automatic feature extraction of time-series applied to fault severity assessment of helical gearbox in stationary and non-stationary speed operation, Appl. Soft Comput., 58, 53-64 (2017)
[7] Cabrera, D.; Sancho, F.; Sánchez, R.-V.; Zurita, G.; Cerrada, M.; Li, C.; Vásquez, R. E., Fault diagnosis of spur gearbox based on random forest and wavelet packet decomposition, Front. Mech. Eng., 10, 3, 277-286 (2015)
[8] Cerrada, M.; Sánchez, R.-V.; Li, C.; Pacheco, F.; Cabrera, D.; de Oliveira, J. V.; Vásquez, R. E., A review on data-driven fault severity assessment in rolling bearings, Mech. Syst. Signal Process., 99, 169-196 (2018)
[9] Cerrada, M.; Zurita, G.; Cabrera, D.; Sánchez, R.-V.; Artés, M.; Li, C., Fault diagnosis in spur gears based on genetic algorithm and random forest, Mech. Syst. Signal Process., 70-71, 87-103 (2016)
[10] Chinniah, Y., Analysis and prevention of serious and fatal accidents related to moving parts of machinery, Saf. Sci., 75, 163-173 (2015)
[11] Fukushima, K., Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biol. Cybern., 36, 4, 193-202 (1980) · Zbl 0419.92009
[12] Gröchenig, K., Uncertainty principles for time-frequency representations, Advances in Gabor Analysis, 11-30 (2003), Birkhäuser Boston · Zbl 1039.42004
[13] Hills, J.; Lines, J.; Baranauskas, E.; Mapp, J.; Bagnall, A., Classification of time series by shapelet transformation, Data Min. Knowl. Discov., 28, 4, 851-881 (2014) · Zbl 1298.62098
[14] Ince, T.; Kiranyaz, S.; Eren, L.; Askar, M.; Gabbouj, M., Real-time motor fault detection by 1-d convolutional neural networks, IEEE Trans. Ind. Electron., 63, 11, 7067-7075 (2016)
[15] Kasabov, N., Evolving Connectionist Systems (2007), Springer London · Zbl 1140.68434
[16] Springer Handbook of Bio-/Neuroinformatics, (Kasabov, N. (2014), Springer Berlin Heidelberg) · Zbl 1304.92001
[17] Lecun, Y.; Bottou, L.; Bengio, Y.; Haffner, P., Gradient-based learning applied to document recognition, Proc. IEEE, 86, 11, 2278-2324 (1998)
[18] Lei, Y.; Kong, D.; Lin, J.; Zuo, M. J., Fault detection of planetary gearboxes using new diagnostic parameters, Meas. Sci. Technol., 23, 5, 55605 (2012)
[19] Li, C.; Cabrera, D.; de Oliveira, J. V.; Sanchez, R.-V.; Cerrada, M.; Zurita, G., Extracting repetitive transients for rotating machinery diagnosis using multiscale clustered grey infogram, Mech. Syst. Signal Process., 76-77, 157-173 (2016)
[20] Li, C.; Ledo, L.; Delgado, M.; Cerrada, M.; Pacheco, F.; Cabrera, D.; Sánchez, R.-V.; de Oliveira, J. V., A bayesian approach to consequent parameter estimation in probabilistic fuzzy systems and its application to bearing fault classification, Knowl. Based Syst., 129, 39-60 (2017)
[21] Li, C.; Sanchez, R.-V.; Zurita, G.; Cerrada, M.; Cabrera, D.; Vásquez, R. E., Gearbox fault diagnosis based on deep random forest fusion of acoustic and vibratory signals, Mech. Syst. Signal Process., 76-77, 283-293 (2016)
[22] Linden, D.; Abramson, N., A generalization of the sampling theorem, Inform. Control, 3, 1, 26-31 (1960) · Zbl 0214.46703
[23] Monteiro, R. P.; Cerrada, M.; Cabrera, D. R.; Sánchez, R. V.; Bastos-Filho, C. J.A., Using a support vector machine based decision stage to improve the fault diagnosis on gearboxes, Comput. Intell. Neurosci., 2019, 1-13 (2019)
[24] Salvador, S.; Chan, P., Toward accurate dynamic time warping in linear time and space, Intell. Data Anal., 11, 5, 561-580 (2007)
[25] Schliebs, S.; Kasabov, N., Evolving spiking neural network—a survey, Evol. Syst., 4, 2, 87-98 (2013)
[26] Schäfer, P., The BOSS is concerned with time series classification in the presence of noise, Data Min. Knowl. Discov., 29, 6, 1505-1530 (2014) · Zbl 1405.68305
[27] Soltic, S.; Kasabov, N., Knowledge extraction from evolving spiking neural networks with rank order population coding, Int. J. Neural Syst., 20, 6, 437-445 (2010)
[28] C. Sun, A. Shrivastava, S. Singh, A. Gupta, Revisiting unreasonable effectiveness of data in deep learning era (2017).
[29] Tan, C. K.; Irving, P.; Mba, D., A comparative experimental study on the diagnostic and prognostic capabilities of acoustics emission, vibration and spectrometric oil analysis for spur gears, Mech. Syst. Signal Process., 21, 1, 208-233 (2007)
[30] Wang, L.-H.; Zhao, X.-P.; Wu, J.-X.; Xie, Y.-Y.; Zhang, Y.-H., Motor fault diagnosis based on short-time fourier transform and convolutional neural network, Chin. J. Mech. Eng., 30, 6, 1357-1368 (2017)
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.