Skip to main content
SpringerLink
Log in

Fault diagnosis method of belt conveyor idler based on sound signal

  • Original Article
  • Published:
Journal of Mechanical Science and Technology Aims and scope Submit manuscript

Abstract

Damage to a belt conveyor idler will increase the downtime and maintenance cost, so it is very important to diagnose its fault. At present, the fault diagnosis of the idler of a belt conveyor is mostly based on vibration and temperature signal. However, contact fault diagnosis approaches are severely limited when sensors are inconvenient to install or when vibration and temperature signals cannot be returned. In this special case, the non-contact fault diagnosis method, represented by measuring acoustic signals, becomes a necessary means. To effectively extract mechanical state information from sound signals of belt conveyors and identify typical mechanical faults, we propose a fault detection method based on sample center distance weighted (support vector data description (SVDD)) and multi-frame fusion (Mel-frequency cepstral coefficient (MFCC)) features. Aiming at the disadvantage that single frame MFCC features and traditional SVDD are susceptible to noise, multi-frame fusion MFCC optimization features are used as samples, and the weighted SVDD model based on sample center distance is used for fault detection. Finally, the overall recognition accuracy of the experiment is greatly improved. It is proved that MFCC features of multi-frame fusion sound signal and weighted SVDD fault detection based on sample center distance can effectively determine whether there is a fault in the of belt conveyor idler.

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

Similar content being viewed by others

Abbreviations

Y :

Nuclear parameter

C :

Penalty parameters

f Mil :

Mel frequency

f :

Sound frequency

H(z):

High pass filter

μ :

Coefficient, between 0.9 and 1.0

z :

Z-transformation

X(k):

Frequency domain signal

x(n):

Time-domain signal

H m(k):

Mel bandpass filter transfer function

f(m):

Mel filter center frequency

E(m):

Log energy of the filter output

C(n):

Meir frequency cepstral coefficient

L :

Number of filters

d (x i, x ki ):

The distance between point xi and its KTH nearest neighbor

s i :

Sample weight coefficient

X :

Training sample

x i :

A single sample of a training sample

s i :

Sample weight coefficient

α :

Sample center

D(x i):

Sample center distance

D avr :

Mean center distance of all samples

ξ i :

Relaxation factor

D max :

Maximum distance between sample centers

D min :

Sample center distance minimum

References

  1. H. Shiri et al., Inspection robotic UGV platform and the procedure for an acoustic signal-based fault detection in belt conveyor idler, Energies, 14(22) (2021) 1–17.

    Article  Google Scholar 

  2. P. Kulinowski, P. Kasza and J. Zarzycki, Identification of the operating parameters of the friction drum drive in industrial conditions, Eksploatacja I Niezawodnosc-Maintenance and Reliability, 23(1) (2021) 94–102.

    Article  Google Scholar 

  3. P. Kulinowski, P. Kasza and J. Zarzycki, Influence of design parameters of idler bearing units on the energy consumption of a belt conveyor, Sustainability, 13(1) (2021) 1–13.

    Article  Google Scholar 

  4. X. Hua, L. Wang and Y. Zhang, Analysis and diagnosis of shielded cable faults based on finite-element method and time-reversal time-frequency domain reflectometry, IEEE Transactions on Industrial Electronics, 69(4) (2022) 4205–4214.

    Article  Google Scholar 

  5. X. Li et al., Multi-sensor gearbox fault diagnosis by using featurefusion covariance matrix and multi-Riemannian kernel ridge regression, Reliability Engineering and System Safety, 216 (2021).

  6. J. Senanayaka, K. V. Huynh and K. G. Robbersmyr, Multiple classifiers and data fusion for robust diagnosis of gearbox mixed faults, IEEE Transactions on Industrial Informatics, 15(8) (2019) 4569–4579.

    Article  Google Scholar 

  7. X. Fu and X. Pang, Robust fault estimation and fault-tolerant control for nonlinear markov jump systems with time-delays, Automatika, 62(1) (2021) 21–31.

    Article  Google Scholar 

  8. S. Delvecchio, P. Bonfiglio and F. Pompoli, Vibro-acoustic condition monitoring of internal combustion engines: a critical review of existing techniques, Mechanical Systems and Signal Processing, 99(15) (2017) 661–683.

    Google Scholar 

  9. K. A. Secic et al., Vibro-acoustic methods in the condition assessment of power transformers: a survey, IEEE Access, 7 (2019) 83915–83931.

    Article  Google Scholar 

  10. B. A. Qiu and L. L. Li, Application of acoustic array technology in abnormal noise fault diagnosis of radar transmission system, B. Duan, K. Umeda and W. Hwang (eds.), Proceedings of the Seventh Asia International Symposium on Mechatronics. Lecture Notes in Electrical Engineering, Springer, Singapore, 589 (2020) 801–811.

    Chapter  Google Scholar 

  11. X. T. Bai et al., Localization of double spalling on the outer rings of paired ball bearings by time-delay sound analysis, Measurement Science and Technology, 32(9) (2021) 1–14.

    Article  Google Scholar 

  12. C. Sobie, C. Freitas and M. Nicolai, Simulation-driven machine learning: Bearing fault classification, Mechanical Systems and Signal Processing, 99 (2017) 403–419.

    Article  Google Scholar 

  13. G. Y. Yu, G. Yan and B. Ma, Feature enhancement method of rolling bearing acoustic signal based on RLS-RSSD, Measurement, 192 (2022).

  14. P. Henriquez et al., Review of automatic fault diagnosis systems using audio and vibration signals, IEEE Transactions on Systems Man Cybernetics-Systems, 44(5) (2014) 642–652.

    Article  Google Scholar 

  15. Z. Cheng et al., Improved autoencoder for unsupervised anomaly detection, International Journal of Intelligent Systems, 36(12) (2021) 7103–7125.

    Article  Google Scholar 

  16. A. Skoczylas et al., Belt conveyors rollers diagnostics based on acoustic signal collected using autonomous legged inspection robot, Applied Sciences, 11 (5) (2021).

  17. I. A. Basheer and M. Hajmeer, Artificial neural networks: fundamentals, computing, design, and application, J. of Microbiological Methods, 43(1) (2000) 3–31.

    Article  Google Scholar 

  18. Y. LeCun, Y. Bengio and G. Hinton, Deep learning, Nature, 521(7553) (2015) 436–444.

    Article  Google Scholar 

  19. Z. Wu, D. Rincon and P. D. Christofides, Process structure-based recurrent neural network modeling for model predictive control of nonlinear processes, J. of Process Control, 89 (2020) 74–84.

    Article  Google Scholar 

  20. M. Song, H. Song and S. Xiao, A study on fault diagnosis method of rolling bearing based on wavelet packet and improved BP neural network, FMSP, 274 (2017).

  21. H. Qiu et al., Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics, J. of Sound and Vibration, 289(4–5) (2006) 1066–1090.

    Article  Google Scholar 

  22. J. Lee et al., Fault detection and diagnosis of railway point machines by sound analysis, Sensors, 16(4) (2016) 549.

    Article  Google Scholar 

  23. M. Cha, J. S. Kim and J. Baek, Density weighted support vector data description, Expert Systems with Applications, 41(7) (2014) 3343–3350.

    Article  Google Scholar 

  24. Z. Wang et al., Solving one-class problem with outlier examples by SVM, Neurocomputing, 149 (2015) 100–105.

    Article  Google Scholar 

  25. D. M. J. Tax and R. P. W. Duin, Support vector data description, Machine Learning, 54(1) (2004) 45–66.

    Article  MATH  Google Scholar 

  26. T. L. New, S. W. Foo and L. C. De Silva, Speech emotion recognition using hidden markov models, Speech Communication, 41(4) (2003) 603–623.

    Article  Google Scholar 

  27. W. Huang and L. Shen, Weighted support vector regression algorithm based on data description, 2008 ISECS International Colloquium on Computing, Communication, Control, and Management (2018) 250–254.

  28. L. D. Wang et al., Wavelet transform-based weighted nu-twin support vector regression, International Journal of Machine Learning and Cybernetics, 11(1) (2020) 95–110.

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by the National Natural Science Foundation of China (51575512, 52074272) and the Priority Academic Program Development of Jiangsu Higher Education Institutions. This work was also supported by the Graduate Innovation Program of China University of Mining and Technology (2022 WLKXJ071) and the Postgraduate Research & Practice Innovation Program of Jiangsu Province (KYCX22_2511).

Author information

Authors and Affiliations

  1. School of Mechatronic Engineering, China University of Mining and Technology, Xuzhou, 221116, China

    Yahui Zhang, Siyan Li, Aimin Li, Gaoxiang Zhang & Mingzhuang Wu

Authors
  1. Yahui Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Siyan Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Aimin Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Gaoxiang Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Mingzhuang Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Aimin Li.

Additional information

Yahui Zhang is currently a Ph.D. student in Mechanical Engineering at China University of Mining and Technology. His research interests include intelligent fault diagnosis technology and equipment for belt conveyors, driverless path planning technology for construction vehicles, and design and optimization of detection robots.

Siyan Li is currently a Ph.D. student in Mechanical Engineering at China University of Mining & Technology, Xuzhou, China. His research interests include intelligent detection and transportation system for coal equipment and unmanned route planning technology for construction vehicles.

Aimin Li is a Professor at the China University of Mining and Technology. He received his Ph.D. in the School of Mechanical and Electrical Engineering from China University of Mining and Technology. His research interests include intelligent fault diagnosis of belt conveyors, intelligent detection and transportation system of coal equipment, driverless path planning technology for engineering vehicles, and design and optimization of detection robots.

Gaoxiang Zhang is currently studying mechanical engineering at the School of Mechanical and Electrical Engineering, China University of Mining and Technology (Xuzhou). His research interests include intelligent fault diagnosis of belt conveyor, design and optimization of detection robot, and unmanned driving of coal mine machinery.

Mingzhuang Wu is currently working toward a Ph.D. in Mechanical Engineering at China University of Mining & Technology, Xuzhou,China. His research interests include magnetorheological fluid transmission and control, cement shotcrete structure design and control systems.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, Y., Li, S., Li, A. et al. Fault diagnosis method of belt conveyor idler based on sound signal. J Mech Sci Technol 37, 69–79 (2023). https://doi.org/10.1007/s12206-022-1208-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-022-1208-1

Keywords

Search

Navigation