Severity Analysis of Motorcycle Faults Based on Acoustic Signals

  • Veerappa B. Pagi
  • Ramesh S. WadawadagiEmail author
  • Basavaraj S. Anami
Conference paper
Part of the Lecture Notes in Networks and Systems book series (LNNS, volume 14)


Numerous techniques have been proposed for detection and localization of fault sources in motorcycles based on acoustic signatures. However, these systems are inadequate to assess the severity of faults present in motorcycles. In this paper, a mechanism to estimate the degree of fault severity based on acoustic signals is presented. The process involves three stages: fault detection, fault source localization and fault severity analysis. The distribution of energies in first five subbands of a wavelet packet is considered as features set for signal processing and analysis. The model is tested against several classifiers including ANN, DTW, k-NN and k-Means. Essentially, same set of features and classifiers are employed at each stage of the process. The augmented decision vector output of the first and second stage are provided as inputs to the second and third stage, respectively. Three levels of fault severity are evaluated: high, medium and low. The classification accuracy up to 92% is observed for fault detection and localization stage, whereas, 90% accuracy is observed for severity analysis. The proposed work finds interesting applications in allied areas such as fault severity analysis of engines, machinery, musical instruments and electronic gadgets.


Fault severity analysis Acoustic fault diagnosis Wavelet packet energy Feature extraction Learning models 


  1. 1.
    Hamburger C (1995) Quasimonotonicity, regularity and duality for nonlinear systems of partial differential equations. Ann Mat Pura Appl 169:321–354 MathSciNetCrossRefzbMATHGoogle Scholar
  2. 2.
    Lin J (2001) Feature extraction of machine sound using wavelet and its application in fault diagnosis. J NDT E INT 34:25–30Google Scholar
  3. 3.
    Amir et al (1999) A wavelet packet algorithm for classification and detection of moving vehicles. J Multidimen Syst Signal Process 12:9–31Google Scholar
  4. 4.
    Lin J, Zuo MJ (2003) Gearbox fault diagnosis using adaptive wavelet filter. Mech Syst Signal Process 17(6):1259–1269CrossRefGoogle Scholar
  5. 5.
    Hao ZY, Han J (2004) Identification of diesel front sound source based on continuous wavelet transform. J Zhejiang Univ Sci A Springer J 5(9):1069–1075Google Scholar
  6. 6.
    Junhong Z, Bing H (2005) Analysis of engine front noise using sound intensity techniques. Mech Syst Signal Process 17:213–221CrossRefGoogle Scholar
  7. 7.
    Xiaochun S, Hongying H (2006) Diesel engine fault diagnosis and classification. In: 8th international conference on signal processing, vol 1, pp 16–20Google Scholar
  8. 8.
    Cheng J, Yu D, Yang Y (2006) A fault diagnosis approach for gears based on IMF AR model and SVM. EURASIP J Adv Signal Process (Hindawi Publishing Corporation)Google Scholar
  9. 9.
    Wu J-D, Liu C-H (2008) Investigation of engine fault diagnosis using discrete wavelet transform and neural network. Expert Syst Appl 35:1200–1213 (Elsevier)Google Scholar
  10. 10.
    Wu JD, Chang EC, et al (2009) Fault classification of a scooter engine platform using wavelet transform and artificial neural network. In: Proceedings of the international multi conference of engineers and computer scientists (IMECS), pp 18–20Google Scholar
  11. 11.
    Paulraj MP, Yaacob S, Mohd Zubir MZ (2009) Entropy based feature extraction for motorbike engine faults diagnosing system using entropy and functional link neural network in wavelet domain. In: Proceedings of the 5th international conference on man-machine systems (ICoMMS), pp 1–5Google Scholar
  12. 12.
    Liao W, Han P, Liu X (2009) Fault diagnosis for engine based on EMD and wavelet packet BP neural network. In: 3rd International symposium intelligent information technology application, pp 672–676Google Scholar
  13. 13.
    Aljaafreh A, Dong L (2010) An evaluation of feature extraction methods for vehicle classification based on acoustic signals. In: International conference in networking, sensing and control (ICNSC), pp 464–469Google Scholar
  14. 14.
    Anami BS, Pagi VB, Magi SM (2011) Wavelet based acoustic analysis for determining health condition of motorized two-wheelers. Appl Acoust 72(7):464–469 ElsevierCrossRefGoogle Scholar
  15. 15.
    Wu J (2012) Fault analysis of engine timing gear and valve clearance using discrete wavelet and a support vector machine. Int J Comput Theory Eng 4(3):386–390Google Scholar
  16. 16.
    Li P, Jiang Y, Xiang J Experimental investigation for fault diagnosis based on a hybrid approach using wavelet packet and support vector classification. Sci World JGoogle Scholar
  17. 17. (For recording environment setup)
  18. 18.
    Akansu AN, Serdijn WA, Selesnick IW (2010) Emerging applications of wavelets: a review. Phys Commun 3(1):1–18Google Scholar
  19. 19.
    Rajpoot N. Texture classification using discriminant wavelet packet subbands. In: Proceedings of the 45th midwest symposium on circuits and systems, pp 300–303Google Scholar
  20. 20.
    Sang YF, Wang D, Wu JC (2010) Entropy-based method of choosing the decomposition level in wavelet threshold de-noising. J Entropy Inf StudGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2018

Authors and Affiliations

  • Veerappa B. Pagi
    • 1
    • 2
  • Ramesh S. Wadawadagi
    • 1
    • 2
    Email author
  • Basavaraj S. Anami
    • 1
    • 2
  1. 1.Basaveshwara Engineering CollegeBagalkotIndia
  2. 2.KLE’s Institute of TechnologyHubliIndia

Personalised recommendations