Skip to main content
SpringerLink
Log in

Detection of defective embedded bearings by sound analysis: a machine learning approach

  • Published:
Journal of Intelligent Manufacturing Aims and scope Submit manuscript

Abstract

This paper describes a machine learning solution for the detection of defective embedded bearings in home appliances by sound analysis. The bearings are installed deep into the home appliances at the beginning of the production process and cannot be physically accessed once they are fully assembled. Before a home appliance is put to sale, it is turned on and passed through a sound-based sensor that produces an acoustic signal. Home appliances with defective embedded bearings are detected by analyzing such signals. The approached task is very challenging, mainly because there is a small number of sample signals and the noise level in the measurements is quite high. In fact, it is showed that the signal-to-noise ratio is high enough to mask important components when applying traditional Fourier decomposition techniques. Hence, a different approach is needed. Experimental results are reported on both laboratory and production line signals. Despite the difficulty of the task, these results are encouraging. Several classification methods were evaluated and most of them achieved acceptable performance. An interesting finding is that, among the classifiers that showed better performance, some methods are highly intuitive and easy to implement. These methods are generally preferred in industry. The proposed solution is being implemented by the company which motivated this study.

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

Similar content being viewed by others

Notes

  1. Due to confidentiality clauses, the authors are not authorized to reveal the name of the company nor the home appliance under analysis.

  2. It is emphasized that due to confidentiality clauses, the authors are not authorized to reveal further technical details about the data acquisition system.

  3. One should note that, when using filters for feature selection, this procedure is the standard feature selection methodology: features are ranked in descending order of relevance and the user selects the features to be used (Guyon and Elisseeff 2003; Guyon et al. 2006).

  4. Note that linear functions are linear in the parameters and not in the inputs, hence they can generate nonlinear decision surfaces. For instance, a Multilayer Perceptron learns linear weights yet it generates nonlinear decision surfaces, because data is projected into a higher-dimensional space.

References

  • Al-Raheem, K. F., Roy, A., Ramachandran, K. P., Harrison, D. K., & Grainger, S. (2009). Rolling element bearing faults diagnosis based on autocorrelation of optimized: Wavelet de-noising technique. The International Journal of Advanced Manufacturing Technology, 40, 393–402.

    Article  Google Scholar 

  • Benkedjouh, T,, Medjaher, K., Zerhouni, N., & Rechak, S. (2013). Health assessment and life prediction of cutting tools based on support vector regression. Journal of Intelligent Manufacturing, 1–11.

  • Bishop, C. (2007). Pattern recognition and machine learning (1st ed.). Berlin: Springer.

    Google Scholar 

  • Dey, D., Solorio, T., Montes, M., & Escalante, H. J. (2011). Instance selection in text classification using the silhouette coefficient measure. Lecture Notes in Computer Science, vol. 7094, pp. 357–369.

  • Golub, T., Slonim, D. K., Tamayo, P., Huard, C., Gaasenbeek, M., Mesirov, J. P., et al. (1999). Molecular classification of cancer: Class discovery and class prediction by gene expression monitoring. Science, 286, 531–537.

    Article  Google Scholar 

  • Goumas, S., Zervakis, M. E., & Stavrakakis, G. S. (2002). Classification of washing machines vibration signals using discrete wavelet analysis for feature extraction. IEEE Transactions on Instrumentation and Measurement, 51(3), 497–508.

    Article  Google Scholar 

  • Guyon, I., & Elisseeff, A. (2003). An introduction to variable and feature selection. The Journal of Machine Learning Research, 3, 1157–1182.

    Google Scholar 

  • Guyon, I., Gunn, S., Nikravesh, M., & Zadej, L. A. (Eds.). (2006). Feature extraction, foundations and applications, studies in fuzziness and soft computing (Vol. 207). Berlin: Springer.

    Google Scholar 

  • Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., & Witten, I. H. (2009). The WEKA data mining software: An update. SIGKDD Explorations, 11(1), 10–18.

    Article  Google Scholar 

  • Kankar, P., Sharma, S., & Harsha, S. (2011a). Fault diagnosis of ball bearings using machine learning methods. Expert Systems with Applications, 38, 1876–1886.

    Article  Google Scholar 

  • Kankar, P., Sharma, S., & Harsha, S. (2011b). Rolling element bearing fault diagnosis using wavelet transform. Neurocomputing, 74, 1638–1645.

    Article  Google Scholar 

  • Li, H., Lian, X., Guo, C., & Zhao, P. (2013). Investigation on early fault classification for rolling element bearing based on the optimal frequency band determination. Journal of Intelligent Manufacturing, 1–10

  • Li, R., Sopon, P., & He, D. (2012). Fault features extraction for bearing prognostics. Journal of Intelligent Manufacturing, 23, 313–321.

    Article  Google Scholar 

  • Li, Y., Billington, S., Zhang, C., Kurfess, T., Danyluk, S., & Liang, S. (1999). Dynamic prognostic prediction of defect propagation on rolling element bearings. Tribology transactions, 42(2), 385–392.

    Article  Google Scholar 

  • McFadden, P., & Smith, J. (1984). The vibration produced by a single point defect in a rolling element bearing. Journal of Sound and Vibration, 96(1), 69–82.

    Article  Google Scholar 

  • McInerny, S. A., & Dai, Y. (2003). Basic vibration signal processing for bearing fault detection. IEEE Transactions on Education, 46(1), 149–156.

    Article  Google Scholar 

  • Mendel, E., Mariano, L., Drago, I., Loureiro, S., Rauber, T., Varejao, F., & Batista, R. (2008). Automatic bearing fault pattern recognition using vibration signal analysis. In Proceedings of the 2008 IEEE international symposium on industrial electronics. IEEE, pp. 955–960.

  • Mitchell, T. M. (1997). Machine learning (1st ed.). NY: McGraw-Hill Science/Engineering/Math.

    Google Scholar 

  • Montgomery, D. C. (2007). Introduction to statistical quality control. New York: Wiley.

    Google Scholar 

  • Osyk, B. A., Hung, M. S., & Madey, G. R. (1994). A neural network model for fault detection in conjunction with a programmable logic controller. Journal of Intelligent Manufacturing, 5(2), 67–78.

    Article  Google Scholar 

  • Paonea, N., Scalisea, L., Stavrakakisb, G., & Pouliezosc, A. (1999). Fault detection for quality control of household appliances by non-invasive laser doppler technique and likelihood classifier. Measurement, 25, 237–247.

    Article  Google Scholar 

  • Press, W. H., Teukolsky, S. A., Vetterling, W. T., & Flannery, B. P. (2007). Numerical recipes: The art of scientific computing (3rd ed.). Cambridge: Cambridge University Press.

    Google Scholar 

  • Samanta, B., Al Balushi, K. R., & Al Araimi, S. A. (2004). Bearing fault detection using artificial neural networks and genetic algorithm. EURASIP Journal on Applied Signal Processing, 2004, 366–377.

    Article  Google Scholar 

  • Sharma, V. S., Dhiman, S., Sehgal, R., & Sharma, S. K. (2008). Estimation of cutting forces and surface roughness for hard turning using neural networks. Journal of Intelligent Manufacturing, 19, 473–483.

    Article  Google Scholar 

  • Su, H., Chong, K. T., & Parlos, A. G. (2005). A neural network method for induction machine fault detection with vibration signal. In Proceedings of the 2005 international conference on computational science and its applications, LNCS, vol. 3481, pp. 1293–1302.

  • Sugumaran, V., & Ramachandran, K. (2011). Fault diagnosis of roller bearing using fuzzy classifier and histogram features with focus on automatic rule learning. Expert Systems with Applications, 38, 4901–4907.

    Article  Google Scholar 

  • Tandon, N., & Choudhury, A. (1999). A review of vibration and acoustic measurement methods for the detection of defects in rolling element bearings. Tribology International, 32(8), 469–480.

    Article  Google Scholar 

  • Van Kampen, N. G. (1981). Stochastic processes in physics and chemistry. Amsterdam: North-Holland.

    Google Scholar 

  • Wang, Y., & Tseng, M. (2013). A nave Bayes approach to map customer requirements to product variants. Journal of Intelligent Manufacturing, 1–9.

  • Wu, X., Kumar, V., Quinlan, J. R., Yang, J. G. Q., McLachlan, H. M. G. J., Ng, A., et al. (2008). Top 10 algorithms in data mining. Knowledge and Information Systems, 14, 1–37.

    Article  Google Scholar 

  • Wuest, T., Irgens, C., & Thoben, K. D. (2014). An approach to monitoring quality in manufacturing using supervised machine learning on product state data. Journal of Intelligent Manufacturing, 25(5), 1167–1180.

  • Yan, R., Gao, R. X., & Chen, X. (2014). Wavelets for fault diagnosis of rotary machines: A review with applications. Signal Processing, 96, 1–15.

  • Yang, Y., Liao, Y., Meng, G., & Lee, J. (2011). A hybrid feature selection scheme for unsupervised learning and its application in bearing fault diagnosis. Expert Systems with Applications, 38, 11,311–11,320.

    Article  Google Scholar 

  • Zhang, Z., Wang, Y., & Wang, K. (2013). Fault diagnosis and prognosis using wavelet packet decomposition, fourier transform and artificial neural network. Journal of Intelligent Manufacturing, 24(6), 1213–1227.

    Article  Google Scholar 

  • Zhao, X., Li, M., Xu, J., & Song, G. (2011). An effective procedure exploiting unlabeled data to build monitoring system. Expert Systems with Applications, 38, 10,199–10,204.

    Article  Google Scholar 

Download references

Acknowledgments

Mario A. Saucedo-Espinosa wish to acknowledge graduate scholarships from CONACYT and FIME, UANL. Arturo Berrones acknowledges partial financial support from projects CONACYT CB-167651 and UANL-PAICYT. The authors would like to thank Mert Çorbaci for improving the redaction of this work.

Author information

Authors and Affiliations

  1. Posgrado en Ingeniería de Sistemas, Facultad de Ingeniería Mecánica y Eléctrica, Universidad Autónoma de Nuevo León, 66450, San Nicolás de los Garza, NL, Mexico

    Mario A. Saucedo-Espinosa & Arturo Berrones

  2. Coordinación de Ciencias Computacionales, Instituto Nacional de Astrofísica, Óptica y Electrónica, 72840, Tonatzintla, Puebla, Mexico

    Hugo Jair Escalante

Authors
  1. Mario A. Saucedo-Espinosa
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Hugo Jair Escalante
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Arturo Berrones
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mario A. Saucedo-Espinosa.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Saucedo-Espinosa, M.A., Escalante, H.J. & Berrones, A. Detection of defective embedded bearings by sound analysis: a machine learning approach. J Intell Manuf 28, 489–500 (2017). https://doi.org/10.1007/s10845-014-1000-x

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10845-014-1000-x

Keywords

Search

Navigation