Abstract
Aiming at the limitation that the single channel source of rolling bearing contains incomplete fault information and the strong correlation and coupling relationship between different channels, a multi-channel fusion diagnosis method for rolling bearing based on multi-domain tensor feature and support tensor machine is proposed. In order to fuse the bearing fault information contained in multi-channel vibration signals, firstly, multi-domain features such as time domain features, wavelet domain features, entropy domain features and trigonometric function features of each channel signal are extracted respectively, and the third-order tensor with channel, feature and time as dimensions is constructed. Then, the CP rank is determined by the kernel consistent diagnosis method, and the high-order fault state information contained in the multi-domain tensor is extracted by the low rank tensor approximation method based on CP decomposition to obtain the multi-domain tensor characteristics of multi-channel rolling bearing. Finally, the multi-domain tensor feature is input into the support tensor machine for bearing fault diagnosis. The example of bearing fault diagnosis shows that the multi-channel fusion diagnosis method based on multi-domain tensor feature and support tensor machine proposed in this paper can make full use of the high-order structural features of multi-channel information source, fuse multi-channel information to more comprehensively characterize the fault state of bearing, and obtain higher diagnosis accuracy than single channel information source.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Li, N.P., Gebraeel, N., Lei, Y.G., et al.: Remaining useful life prediction based on a multi-sensor data fusion model. Reliab. Eng. Syst. Saf. 208, 107249 (2020)
Safizadeh, M.S., Latifi, S.K.: Using multi-sensor data fusion for vibration fault diagnosis of rolling element bearings by accelerometer and load cell. Inf. Fusion 18, 1–8 (2014)
Zhang, X.W., Li, H.S.: Research on transformer fault diagnosis method and calculation model by using fuzzy data fusion in multi-sensor detection system. Optik 176, 716–723 (2019)
Zhu, D.C., Zhang, Y.X., Pan, Y.Y., et al.: Fault diagnosis for rolling element bearings based on multi-sensor signals and CNN. J. Vibr. Shock 39(04), 172–178 (2020)
Hao, S.J., Ge, F.X., Li, Y.M., et al.: Multisensor bearing fault diagnosis based on one-dimensional convolutional long short-term memory networks. Measurement 159, 107802 (2020)
Azamfar, M., Singh, J., Bravo-Imaz, I., et al.: Multisensor data fusion for gearbox fault diagnosis using 2-D convolutional neural network and motor current signature analysis. Mech. Syst. Signal Process. 144, 106861 (2020)
Zhao, H.S., Zhang, W.: Fault diagnosis method for rolling bearings based on segment tensor rank-(L, L, 1) decomposition. Mech. Syst. Signal Process. 132, 762–775 (2019)
Rébillat, M., Mechbal, N.: Damage localization in geometrically complex aeronautic structures using canonical polyadic decomposition of Lamb wave difference signal tensors. Struct. Health Monit. 19, 305–321 (2019)
Li, Y., Gong, X.L., Zhao, Q.H.: Hyperspectral image classification based on tensor-based radial basis kernel function and support vector machine. Chin. J. Sci. Inst. 41(12), 253–262 (2020)
Kolda, T.G., Bader, B.W.: Tensor decompositions and applications. SIAM Rev. 51(3), 455–500 (2009)
Sidiropoulos, N.D., de Lathauwer, L., Fu, X., et al.: Tensor decomposition for signal processing and machine learning. IEEE Trans. Signal Process. 65(13), 3551–3582 (2017)
Hu, C.F., Wang, Y.X.: Research on multi-channel signal denoising method for multiple faults diagnosis of rolling element bearings based on tensor factorization. J. Mech. Eng. 55(12), 50–57 (2019)
Feng, L.L., Liu, Y.P., Chen, L.X., et al.: Robust block tensor principal component analysis. Signal Process. 166, 107271 (2020)
Lei, Y.G., Xu, X.F., Cai, X., et al.: Research on data quality assurance for health condition monitoring of machinery. J. Mech. Eng. 57(04), 1–9 (2021)
Eckart, C., Young, G.: The approximation of one matrix by another of lower rank. Psychometrika 1(3), 211–218 (1936)
Bro, R., Kiers, H.A.L.: A new efficient method for determining the number of components in PARAFAC models. J. Chemom. 17(5), 274–286 (2003)
Liu, K.F., So, H.C., Costa, J.P., et al.: Core consistency diagnostic aided by reconstruction error for accurate enumeration of the number of components in parafac models. In: IEEE International Conference on Acoustics, pp. 6635–6639 (2013)
Javed, K., Gouriveau, R., Zerhouni, N.: A feature extraction procedure based on trigonometric functions and cumulative descriptors to enhance prognostics modeling. In:2013 IEEE Conference on IEEE Prognostics and Health Management (PHM), pp. 1–7 (2013)
Acknowledgements
This research was financially supported by the National Key R&D Program of China (No. 2019YFB2004600) and the National Natural Science Foundation of China (No. 52005335).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Jiang, H., Li, S., Shao, Y., Xu, A., Yuan, J., Zhao, Q. (2022). A Multi-channel Fusion Method Based on Tensor for Rolling Bearing Fault Diagnosis. In: Zhang, H., et al. Neural Computing for Advanced Applications. NCAA 2022. Communications in Computer and Information Science, vol 1638. Springer, Singapore. https://doi.org/10.1007/978-981-19-6135-9_10
Download citation
DOI: https://doi.org/10.1007/978-981-19-6135-9_10
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-19-6134-2
Online ISBN: 978-981-19-6135-9
eBook Packages: Computer ScienceComputer Science (R0)