Skip to main content
SpringerLink
Log in

Time–frequency envelope analysis-based sub-band selection and probabilistic support vector machines for multi-fault diagnosis of low-speed bearings

  • Original Research
  • Published:
Journal of Ambient Intelligence and Humanized Computing Aims and scope Submit manuscript

Abstract

This paper proposes a highly reliable multi-fault diagnosis scheme for low-speed rolling element bearings using an effective time–frequency envelope analysis and a Bayesian inference based one-against-all support vector machines (probabilistic-OAASVM) classifier. The proposed method first performs a wavelet packet transform based envelope analysis on an acoustic emission signal to select sub-bands of the signal that contain the most intrinsic and pertinent information about the defects. Frequency- and time-domain fault features are extracted only from selected sub-bands for fault classification. Traditional one-against-all SVMs (OAASVM), a widely used multi-class pattern recognition technique, employ an arbitrary combination of a series of binary classifiers yielding overlapped feature spaces, where a data sample can be unclassifiable. To address this limitation, we formulate the feature space of OAASVM as an appropriate Gaussian process prior (GPP) and interpret OAASVM results as a posterior probability estimation procedure using Bayesian inference under this GPP. The efficacy of the proposed probabilistic-OAASVM classifier is verified for low-speed rolling element bearings under various conditions. Experimental results indicate that the proposed method outperforms the state-of-the-art algorithms for multi-fault classification of low-speed bearings, yielding a 4.95–20.67% improvement in the average classification accuracy.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16

Similar content being viewed by others

References

  • Abe S (2015) Fuzzy support vector machines for multilabel classification. Pattern Recognit 48:2110–2117. doi:10.1016/j.patcog.2015.01.009

    Article  ADS  Google Scholar 

  • Aydin I, Karakose M, Akin E (2011) A multi-objective artificial immune algorithm for parameter optimization in support vector machine. Appl Soft Comput 11:120–129. doi:10.1016/j.asoc.2009.11.003

    Article  Google Scholar 

  • Chakrabartty S, Cauwenberghs G (2007) Support vector machine: quadratic entropy based robust multi-class probability regression. J Mach Learn Res 8:813–839

    Google Scholar 

  • Chen X, Zhou J, Xiao J, Zhang X, Xiao H, Zhu W, Fu W (2014) Fault diagnosis based on dependent feature vector and probability neural network for rolling element bearings. Appl Math Comput 247:835–847. doi:10.1016/j.amc.2014.09.062

    Article  Google Scholar 

  • Chih-Wei H, Chih-Jen L (2002) A comparison of methods for multiclass support vector machines. IEEE Trans Neural Networks 13:415–425. doi:10.1109/72.991427

    Article  Google Scholar 

  • de Bessa IV, Palhares RM, D’Angelo MFSV, Chaves Filho JE (2016) Data-driven fault detection and isolation scheme for a wind turbine benchmark. Renew Energy 87(Part 1):634–645. doi:10.1016/j.renene.2015.10.061

    Article  Google Scholar 

  • Dong G, Chen J, Zhao F (2015) A frequency-shifted bispectrum for rolling element bearing diagnosis. J Sound Vib, 339:396–418. doi:10.1016/j.jsv.2014.11.015

    Article  ADS  Google Scholar 

  • Finogeev AG, Parygin DS, Finogeev AA (2017) The convergence computing model for big sensor data mining and knowledge discovery. Hum Centr Comput Inf Sci 7:11. doi:10.1186/s13673-017-0092-7

    Article  Google Scholar 

  • Hamadache M, Lee D, Veluvolu KC (2015) Rotor speed-based bearing fault diagnosis (RSB-BFD) under variable speed and constant load. IEEE Trans Ind Electron 62:6486–6495. doi:10.1109/TIE.2015.2416673

    Article  Google Scholar 

  • He Y, Zhang X (2012) Approximate entropy analysis of the acoustic emission from defects in rolling element bearings. J Vib Acoust 134:061012–061012. doi:10.1115/1.4007240

    Article  Google Scholar 

  • Hyun-Chul K, Ghahramani Z (2006) Bayesian Gaussian process classification with the EM-EP algorithm. IEEE Trans Pattern Anal Mach Intell 28:1948–1959. doi:10.1109/TPAMI.2006.238

    Article  Google Scholar 

  • Islam MMM, Khan SA, Kim J-M (2015) Multi-fault diagnosis of roller bearings using support vector machines with an improved decision strategy. In: Huang D-S, Han K (eds) Advanced intelligent computing theories and applications: 11th international conference, ICIC 2015, Fuzhou, China, August 20–23, 2015. Proceedings, Part III. Springer International Publishing, Cham, pp 538–550. doi:10.1007/978-3-319-22053-6_57

    Chapter  Google Scholar 

  • Islam MMM, Khan SA, Kim J-M (2017) Reliable bearing fault diagnosis using Bayesian inference-based multi-class support vector machines. J Acoust Soc Am 141:EL89–EL95. doi:10.1121/1.4976038

    Article  PubMed  Google Scholar 

  • Jeong I-K, Kang M, Kim J, Kim J-M, Ha J-M, Choi B-K (2015) Enhanced DET-based fault signature analysis for reliable diagnosis of single and multiple-combined bearing defects. Shock Vib 2015:10. doi:10.1155/2015/814650

    Article  Google Scholar 

  • Kandukuri ST, Klausen A, Karimi HR, Robbersmyr KG (2016) A review of diagnostics and prognostics of low-speed machinery towards wind turbine farm-level health management. Renew Sustain Energy Rev 53:697–708. doi:10.1016/j.rser.2015.08.061

    Article  Google Scholar 

  • Kang M, Kim J, Choi B-K, Kim J-M (2015a) Envelope analysis with a genetic algorithm-based adaptive filter bank for bearing fault detection. J Acoust Soc Am 138:EL65–EL70. doi:10.1121/1.4922767

    Article  PubMed  Google Scholar 

  • Kang M, Kim J, Wills LM, Kim JM (2015b) Time-varying and multiresolution envelope analysis and discriminative feature analysis for bearing fault diagnosis. IEEE Trans Ind Electron 62:7749–7761. doi:10.1109/TIE.2015.2460242

    Article  Google Scholar 

  • Kang M, Islam MR, Kim J, Kim JM, Pecht M (2016) A hybrid feature selection scheme for reducing diagnostic performance deterioration caused by outliers in data-driven diagnostics. IEEE Trans Ind Electron 63:3299–3310. doi:10.1109/TIE.2016.2527623

    Article  Google Scholar 

  • Khoobjou E, Mazinan AH (2017) On hybrid intelligence-based control approach with its application to flexible robot system. Hum Centr Comput Inf Sci 7:5. doi:10.1186/s13673-017-0086-5

    Article  Google Scholar 

  • Lalani S, Doye D (2017) Discrete wavelet transform and a singular value decomposition technique for watermarking based on an adaptive fuzzy inference system. J Inf Process Syst 13:340–347

    Google Scholar 

  • Li R, He D (2012) Rotational machine health monitoring and fault detection using EMD-based acoustic emission feature quantification. IEEE Trans Instrum Meas 61:990–1001. doi:10.1109/TIM.2011.2179819

    Article  ADS  Google Scholar 

  • Murphy KP (2012) Machine learning: a probabilistic perspective. MIT, Cambridge, pp 290–295

    Google Scholar 

  • Nasiri JA, Moghadam Charkari N, Jalili S (2015) Least squares twin multi-class classification support vector machine. Pattern Recognit, 48:984–992. doi:10.1016/j.patcog.2014.09.020

    Article  ADS  Google Scholar 

  • Rasmussen CE, Williams C (2006) Relationships between GPs and other models. MIT, Cambridge. http://www.gaussianprocess.org/gpml/chapters/RW6.pdf

  • Skolidis G, Sanguinetti G (2011) Bayesian multitask classification with Gaussian process priors. IEEE Trans Neural Netw 22:2011–2021. doi:10.1109/TNN.2011.2168568

    Article  PubMed  Google Scholar 

  • Smola AJ, Schölkopf B, Müller K-R (1998) The connection between regularization operators and support vector kernels. Neural Netw 11:637–649. doi:10.1016/S0893-6080(98)00032-X

    Article  PubMed  Google Scholar 

  • Sollich P (2000) Probabilistic methods for support vector machines. In: Advances in neural information processing systems, MIT Press, pp 349–355

  • Wang D, Tse PW, Tsui KL (2013) An enhanced Kurtogram method for fault diagnosis of rolling element bearings. Mech Syst Sig Process 35:176–199. doi:10.1016/j.ymssp.2012.10.003

    Article  ADS  Google Scholar 

  • Yala N, Fergani B, Fleury A (2017) Towards improving feature extraction and classification for activity recognition on streaming data. J Ambient Intell Hum Comput 8:177–189. doi:10.1007/s12652-016-0412-1

    Article  Google Scholar 

Download references

Acknowledgements

This work was supported by the Korea Institute of Energy Technology Evaluation and Planning (KETEP) and the Ministry of Trade, Industry & Energy (MOTIE) of the Republic of Korea (No. 20162220100050, No. 20161120100350, and No. 20172510102130). It was also funded in part by The Leading Human Resource Training Program of Regional Neo industry through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT and future Planning (NRF-2016H1D5A1910564), and in part by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2016R1D1A3B03931927).

Author information

Authors and Affiliations

  1. School of Electrical, Electronics, and Computer Engineering, University of Ulsan, Ulsan, South Korea

    M. M. Manjurul Islam & Jong-Myon Kim

Authors
  1. M. M. Manjurul Islam
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jong-Myon Kim
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Jong-Myon Kim.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Islam, M.M.M., Kim, JM. Time–frequency envelope analysis-based sub-band selection and probabilistic support vector machines for multi-fault diagnosis of low-speed bearings. J Ambient Intell Human Comput 15, 1527–1542 (2024). https://doi.org/10.1007/s12652-017-0585-2

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12652-017-0585-2

Keywords

Search

Navigation