Automatic and Efficient Fault Detection in Rotating Machinery using Sound Signals

  • Muhammad Altaf
  • Muhammad UzairEmail author
  • Muhammad Naeem
  • Ayaz Ahmad
  • Saeed Badshah
  • Jawad Ali Shah
  • Almas Anjum
Original Paper


Vibration and acoustic emission have received great attention of the research community for condition-based maintenance in rotating machinery. Several signal processing algorithms were either developed or used efficiently to detect and classify faults in bearings and gears. These signals are recorded, using sensors like tachometer or accelerometer, connected directly or mounted very close to the system under observation. This is not a feasible option in case of complex machinery and/or temperature and humidity. Therefore, it is required to sense the signals remotely, in order to reduce installation and maintenance cost. However, its installation far away from the intended device may pollute the required signal with other unwanted signals. In an attempt to address these issues, sound signal-based fault detection and classification in rotating bearings is presented. In this research work, audible sound of machine under test is captured using a single microphone and different statistical, spectral and spectro-temporal features are extracted. The selected features are then analyzed using different machine learning techniques, such as K-nearest neighbor (KNN) classifier, support vector machine (SVM), kernel liner discriminant analysis (KLDA) and sparse discriminant analysis (SDA). Simulation results show successful classification of faults into ball fault, inner and outer race faults. Best results were achieved using the KLDA followed by SDA, KNN and SVM. As far as features are concerned, the average FFT outperformed all the other features, followed by average PSD, RMS values of PSD, PSD and STFT.


Acoustic signal analysis Condition-based maintenance Time domain analysis Frequency domain analysis Machine learning 



  1. 1.
    Al-Dossary, S., Hamzah, R.R., Mba, D.: Observations of changes in acoustic emission waveform for varying seeded defect sizes in a rolling element bearing. Appl. Acoust. 70(1), 58–81 (2009)Google Scholar
  2. 2.
    Al-Ghamd, A.M., Mba, D.: A comparative experimental study on the use of acoustic emission and vibration analysis for bearing defect identification and estimation of defect size. Mech. Syst. Signal Process. 20(7), 1537–1571 (2006)Google Scholar
  3. 3.
    Albarbar, A., Gu, F., Ball, A.: Diesel engine fuel injection monitoring using acoustic measurements and independent component analysis. Measurement 43(10), 1376–1386 (2010)Google Scholar
  4. 4.
    Amarnath, M., Sugumaran, V., Kumar, H.: Exploiting sound signals for fault diagnosis of bearings using decision tree. Measurement 46(3), 1250–1256 (2013)Google Scholar
  5. 5.
    Antoni, J.: Fast computation of the kurtogram for the detection of transient faults. Mech. Syst. Signal Process. 21(1), 108–124 (2007)Google Scholar
  6. 6.
    Atmaja, B.T., Arifianto, D.: Machinery fault diagnosis using independent component analysis (ica) and instantaneous frequency (if). International conference on instrumentation, communication, information technology, and biomedical engineering 2009, 1–5 (2009)Google Scholar
  7. 7.
    Baccar, D., Söffker, D.: Wear detection by means of wavelet-based acoustic emission analysis. Mech. Syst. Signal Process. 60–61, 198–207 (2015)Google Scholar
  8. 8.
    Bao, F.S., Liu, X., Zhang, C.: Pyeeg: An open source python module for eeg/meg feature extraction. Computational intelligence and neuroscience 2011, 1–7 (2011)Google Scholar
  9. 9.
    Baudat, G., Anouar, F.: Generalized discriminant analysis using a Kernel approach. Neural Comput. 12(10), 2385–2404 (2000)Google Scholar
  10. 10.
    Baydar, N., Ball, A.: A comparative study of acoustic and vibration signals in detection of gear failures using wigner–ville distribution. Mech. Syst. Signal Process. 15(6), 1091–1107 (2001)Google Scholar
  11. 11.
    Baydar, N., Ball, A.: Detection of gear failures via vibration and acoustic signals using wavelet transform. Mech. Syst. Signal Process. 17(4), 787–804 (2003)Google Scholar
  12. 12.
    Benko, U., Petrovčić, J., Juričić, D., Tavčar, J., Rejec, J.: An approach to fault diagnosis of vacuum cleaner motors based on sound analysis. Mech. Syst. Signal Process. 19, 427–445 (2005)Google Scholar
  13. 13.
    Caesarendra, W., Tjahjowidodo, T., Kosasih, B., Tieu, A.K.: Integrated condition monitoring and prognosis method for incipient defect detection and remaining life prediction of low speed slew bearings. Machines 5(2), 11 (2017)Google Scholar
  14. 14.
    Chacon, J.L.F., Kappatos, V., Balachandran, W., Gan, T.H.: A novel approach for incipient defect detection in rolling bearings using acoustic emission technique. Appl. Acoust. 89, 88–100 (2015)Google Scholar
  15. 15.
    Chandra, N.H., Sekhar, A.: Fault detection in rotor bearing systems using time frequency techniques. Mech. Syst. Signal Process. 72–73, 105–133 (2016)Google Scholar
  16. 16.
    Chang, C., Lin, J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Tech. 2(3), 27 (2011)Google Scholar
  17. 17.
    Chen, B., Yan, Z., Chen, W.: Defect detection for wheel-bearings with time-spectral kurtosis and entropy. Entropy 16(1), 607–626 (2014)MathSciNetGoogle Scholar
  18. 18.
    Chen, J., Li, Z., Pan, J., Chen, G., Zi, Y., Yuan, J., Chen, B., He, Z.: Wavelet transform based on inner product in fault diagnosis of rotating machinery: a review. Mech. Syst. Signal Process. 70–71, 1–35 (2016)Google Scholar
  19. 19.
    Clemmensen, L., Hastie, T., Witten, D., Ersbøll, B.: Sparse discriminant analysis. Technometrics 53(4), 406–413 (2011)MathSciNetGoogle Scholar
  20. 20.
    Comon, P., Jutten, C.: Handbook of Blind Source Separation: Independent component analysis and applications. Academic press, Cambridge (2010)Google Scholar
  21. 21.
    Cristianini, N., Shawe-Taylor, J.: An Introduction to Support Vector Machines and other kernel-based learning methods. Cambridge University, Cambridge (2000)zbMATHGoogle Scholar
  22. 22.
    Delgado-Arredondo, P.A., Morinigo-Sotelo, D., Alfredo, R.: Methodology for fault detection in induction motors via sound and vibration signals. Mech. Syst. Signal Process. 83, 568–589 (2017)Google Scholar
  23. 23.
    Deriche, M.: Bearing fault diagnosis using wavelet analysis. In: Proceedings of the 2005 1st international conference on computers, communications and signal processing with special track on biomedical engineering, (CCSP’05), pp. 197–201 (2005)Google Scholar
  24. 24.
    Elforjani, M., Mba, D.: Detecting natural crack initiation and growth in slow speed shafts with the acoustic emission technology. Eng. Fail. Anal. 16(7), 2121–2129 (2009)Google Scholar
  25. 25.
    Germen, E., Basaran, M., Fidan, M.: Sound based induction motor fault diagnosis using kohonen self-organizing map. Mech. Syst. Signal Process. 46(1), 45–58 (2014)Google Scholar
  26. 26.
    Giv, H.H.: Directional short-time fourier transform. J. Math. Anal. Appl. 399(1), 100–107 (2013)MathSciNetzbMATHGoogle Scholar
  27. 27.
    Gomaa, F.R., Khader, K.M., Eissa, M.A.: Fault diagnosis of rotating machinery based on vibration analysis. Int. J. Adv. Eng. Global Technol. 4(1), 1571–1586 (2016)Google Scholar
  28. 28.
    Griffin, D., Lim, J.: Signal estimation from modified short-time fourier transform. IEEE Trans. Acoust. Speech Signal Process. 32(2), 236–243 (1984)Google Scholar
  29. 29.
    Gu, D., kim, J., An, Y., Choi, B.: Detection of faults in gearboxes using acoustic emission signal. J. Mech. Sci. Technol. 25(5), 1279–1286 (2011)Google Scholar
  30. 30.
    Guo, P., Infield, D.G., Yang, X.: Wind turbine generator condition-monitoring using temperature trend analysis. IEEE Trans. Sustain. Energy 3, 124–133 (2012)Google Scholar
  31. 31.
    Han, L., Hong, J., Wang, D.: Fault diagnosis of aeroengine bearings based onwavelet package analysis. Tuijin Jishu/ J. Propuls. Technol. 30(3), 328–341 (2009)Google Scholar
  32. 32.
    Henriquez, P., Alonso, J.B., Ferrer, M.A., Travieso, C.M.: Review of automatic fault diagnosis systems using audio and vibration signals. IEEE Trans. Syst. Man Cybern. Syst. 44(5), 642–652 (2014)Google Scholar
  33. 33.
    James, C.J., Lowe, D.: Extracting multisource brain activity from a single electromagnetic channel. Artif. Intell. Med. 28(1), 89–104 (2003)Google Scholar
  34. 34.
    Jedliński, Ł., Jonak, J.: Early fault detection in gearboxes based on support vector machines and multilayer perceptron with a continuous wavelet transform. Appl. Soft Comput. 30, 636–641 (2015)Google Scholar
  35. 35.
    Kaewkongka, T., Au, Y., Rakowski, R., Jones, B.: A comparative study of short time fourier transform and continuous wavelet transform for bearing condition monitoring. Int. J. COMADEM 6, 41–48 (2003)Google Scholar
  36. 36.
    Kim, B., Lee, S., Lee, M., Ni, J., Song, J., Lee, C.: A comparative study on damage detection in speed-up and coast-down process of grinding spindle-typed rotor-bearing system. J. Mater. Process. Technol. 187–188, 30–36 (2007)Google Scholar
  37. 37.
    Kumar, M., Mukherjee, P.S., Misra, N.M.: dvancement and current status of wear debris analysis for machine condition monitoring: a review. Ind. Lubr. Tribol. 65(1), 3–11 (2012)Google Scholar
  38. 38.
    Lei, X., Sandborn, P.A.: PHM-based wind turbine maintenance optimization using real options. Int. J. Progn. Health Manag. 7, 1–14 (2016)Google Scholar
  39. 39.
    Li, C.J., Ma, J.: Wavelet decomposition of vibrations for detection of bearing-localized defects. NDT & E Int. 30(3), 143–149 (1997)Google Scholar
  40. 40.
    Lipar, P., Cudina, M., Steblaj, P., Prezelj, J.: Automatic recognition of machinery noise in the working environment. Strojniski vestnik - Journal of Mechanical Engineering 61(12), 698–708 (2015)Google Scholar
  41. 41.
    Liu, F., Shen, C., He, Q., Zhang, A., Liu, Y., Kong, F.: Wayside bearing fault diagnosis based on a data-driven doppler effect eliminator and transient model analysis. Sensors 14(5), 8096–8125 (2014)Google Scholar
  42. 42.
    Liu, X., Shi, J., Sha, X., Zhang, N.: A general framework for sampling and reconstruction in function spaces associated with fractional fourier transform. Signal Process. 107, 319–326 (2015)Google Scholar
  43. 43.
    Lu, W., Jiang, W., Yuan, G., Yan, L.: A gearbox fault diagnosis scheme based on near-field acoustic holography and spatial distribution features of sound field. J. Sound Vib. 332(10), 2593–2610 (2013)Google Scholar
  44. 44.
    Mba, D., Rao, R.B.K.N.: Development of acoustic emission technology for condition monitoring and diagnosis of rotating machines: bearings, pumps, gearboxes, engines, and rotating structures. Shock Vib. Digest 38(1), 3–16 (2006)Google Scholar
  45. 45.
    McFadden, P., Smith, J.: Vibration monitoring of rolling element bearings by the high-frequency resonance technique-a review. Tribology Int. 17(1), 3–10 (1984)Google Scholar
  46. 46.
    Nelwamondo, F.V., Marwala, T., Mahola, U.: Early classifications of bearing faults using hidden markov models, gaussian mixture models, mel-frequency cepstral coefficients and fractals. Int. J. Innov. Comput. Inf. Control 2, 1281–1299 (2005)Google Scholar
  47. 47.
    Oppenheim, A.V., Schafer, R.W.: Discrete-Time Signal Processing, 3rd edn. Prentice Hall Press, Upper Saddle River (2009)zbMATHGoogle Scholar
  48. 48.
    Othman, M.S., Nuawi, M.Z., Mohamed, R.: Experimental comparison of vibration and acoustic emission signal analysis using kurtosis-based methods for induction motor bearing condition monitoring. Prz. Elektrotechn. 92(11), 208–212 (2016)Google Scholar
  49. 49.
    Pandya, D., Upadhyay, S., Harsha, S.: Fault diagnosis of rolling element bearing with intrinsic mode function of acoustic emission data using APF-KNN. Expert Syst. Appl. 40(10), 4137–4145 (2013)Google Scholar
  50. 50.
    Portnoff, M.: Time-frequency representation of digital signals and systems based on short-time Fourier analysis. IEEE Trans. Acoust. Speech Signal Process. 28(1), 55–69 (1980)zbMATHGoogle Scholar
  51. 51.
    Qian, S., Chen, D.: Decomposition of the Wigner–Ville distribution and time-frequency distribution series. IEEE Trans. Signal Process. 42(10), 2836–2842 (1994)Google Scholar
  52. 52.
    Qin, Q.H., Sun, B.: Advances in Engineering Mechanics and Materials, Chapter Analyzing Emission Sounds: A Way for Early Detection of Bearing Faults in Rotating Machines. Nova Science Publishers Inc, New York (2014)Google Scholar
  53. 53.
    Rai, A., Upadhyay, S.: A review on signal processing techniques utilized in the fault diagnosis of rolling element bearings. Tribol. Int. 96, 289–306 (2016)Google Scholar
  54. 54.
    Saimurugan, M., Nithesh, R.: Intelligent fault diagnosis model for rotating machinery based on fusion of sound signals. Int. J. Prognostics Health Manag. 7, 10 (2016)Google Scholar
  55. 55.
    Sakurada, M., Yairi, T.: Anomaly detection using autoencoders with nonlinear dimensionality reduction. In: Proceedings of the MLSDA 2014 2Nd Workshop on Machine Learning for Sensory Data Analysis, MLSDA’14, pp. 4:4–4:11 (2014)Google Scholar
  56. 56.
    Scheer, C., Reimche, W., wilhelm Bach, F.: Early fault detection at gear units by acoustic emission and wavelet analysis. J. Acoust. Emiss. 25, 331–341 (2007)Google Scholar
  57. 57.
    Scholkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines. Regularization, Optimization, and Beyond. MIT, Cambridge (2001)Google Scholar
  58. 58.
    de Souza Pacheco, W., Pinto, F.A.N.C.: Bearing fault detection using beamforming technique and artificial neural networks. In: Advances in Condition Monitoring of Machinery in Non-Stationary Operations: Proceedings of the 3rd International Conference on Condition Monitoring of Machinery in Non-Stationary Operations CMMNO 2013, pp. 73–80 (2014)Google Scholar
  59. 59.
    Staszewski, W., Worden, K., Tomlinson, G.: Time-frequency analysis in gearbox fault detection using the wigner-ville distribution and pattern recognition. Mech. Syst. Signal Process. 11(5), 673–692 (1997)Google Scholar
  60. 60.
    Tagawa, T., Tadokoro, Y., Yairi, T.: Structured denoising autoencoder for fault detection and analysis. In: Proceedings of the 6th Asian Conference on Machine Learning, vol. 39, pp. 96–111 (2015)Google Scholar
  61. 61.
    Theodoridis, S., Koutroumbas, K.: Pattern Recognition. Academic, Boston (2010)zbMATHGoogle Scholar
  62. 62.
    Turner, C., Joseph, A.: A wavelet packet and mel-frequency cepstral coefficients-based feature extraction method for speaker identification. Procedia Comput. Sci. 61, 416–421 (2015)Google Scholar
  63. 63.
    Verma, N.K., Gupta, V., Sharma, M., Sevakula, R.K.: Intelligent condition based monitoring of rotating machines using sparse auto-encoders. 2013 IEEE Conference on Prognostics and Health Management (PHM) pp. 1–7 (2013)Google Scholar
  64. 64.
    Vilela, R., Metrolho, J.C., Cardoso, J.C.: Machine and industrial monitorization system by analysis of acoustic signatures. In: Proceedings of the 12th IEEE Mediterranean Electrotechnical Conference, vol. 1, pp. 277–279 (2004)Google Scholar
  65. 65.
    Wang, Y., Xiang, J., Markert, R., Liang, M.: Spectral kurtosis for fault detection, diagnosis and prognostics of rotating machines: A review with applications. Mech. Syst. Signal Process. 66–67, 679–698 (2016)Google Scholar
  66. 66.
    Xiao-wen, D., Ping, Y., Jin-sheng, R., Yi-wei, Y.: Rolling bearings time and frequency domain fault diagnosis method based on kurtosis analysis. 2014 IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC) pp. 1–6 (2014)Google Scholar
  67. 67.
    Xie, Y., Zhang, T.: Fault diagnosis for rotating machinery based on convolutional neural network and empirical mode decomposition. Shock Vib. 2017, 12 (2017)Google Scholar
  68. 68.
    Yan, B., Weidong, Q.: Aero-engine sensor fault diagnosis based on stacked denoising autoencoders. In: Proceedings of the 35th Chinese Control Conference, (CCC’16), pp. 6542–6546 (2016)Google Scholar
  69. 69.
    Zhang, Z., Wang, Y., Wang, K.: Fault diagnosis and prognosis using wavelet packet decomposition, fourier transform and artificial neural network. J. Intell. Manuf. 24(6), 1213–1227 (2013)Google Scholar
  70. 70.
    Zhong, Z.M., Chen, J., Zhong, P., Wu, J.B.: Application of the blind source separation method to feature extraction of machine sound signals. Int. J. Adv. Manuf. Technol. 28(9), 855–862 (2006)Google Scholar

Copyright information

© Australian Acoustical Society 2019

Authors and Affiliations

  1. 1.COMSATS University IslamabadWahPakistan
  2. 2.University of South AustraliaAdelaideAustralia
  3. 3.Department of Mechanical Engineering, International Islamic UniversityIslamabadPakistan
  4. 4.Electronic Section, British Malaysian InstituteKuala LumpurMalaysia
  5. 5.EME, NUSTRawalpindiPakistan

Personalised recommendations