Skip to main content
SpringerLink
Log in

Deep convolutional neural network with new training method and transfer learning for structural fault classification of vehicle instrument panel structure

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

Abstract

Structural defect have been detected by attaching sensors to all possible defect locations. A new method is proposed to enable the identification of structural defect locations with minimal data collection points using a deep convolutional neural network. Transfer learning was used to improve the accuracy of a hard-to-classify task by using a pre-trained model from an easy-to-classify task. To reduce the number of data collection points, it is necessary to learn the spatial information of the structure. To this end, a structure fault classification-deep convolutional neural network (SFC-DCNN) is proposed. It is an end-to-end convolutional neural network. The time-domain input data and convolutional neural network filter have 2 dimensions. With the proposed method, the accuracy of classifying the location of structural defects in a vehicle’s instrument panel structure was verified with a single vibration measurement point where the location is independent of the structural fault location.

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

FE:

Finite element FC: Fully connected

Conv:

Convolution

SNR:

Signal to noise ratio

DNN:

Deep neural network

References

  1. O. Abdeljaber, O. Avci, S. Kiranyaz, M. Gabbouj and D. J. Inman, Real-time vibration-based structural damage detection using one-dimensional convolutional neural networks, Journal of Sound and Vibration, 388 (2017) 154–170.

    Article  Google Scholar 

  2. K. B. Lee, S. Cheon and C. O. Kim, A convolutional neural network for fault classification and diagnosis in semiconductor manufacturing processes, IEEE Trans. Semiconductor Manufacturing, 30 (2017) 135–142.

    Article  Google Scholar 

  3. W. Zhang, C. Li, G. Peng, Y. Chen and Z. Zhang, A deep convolutional neural network with new training methods for bearing fault diagnosis under noisy environment and different working load, Mech. Syst. Signal Processing, 100 (2018) 439–453.

    Article  Google Scholar 

  4. Y. Yao, H. Wang, S. Li, Z. Liu, G. Gui, Y. Dan and J. Hu, End-to-end convolutional neural network model for gear fault diagnosis based on sound signals, Appl. Sci., 8 (2018) 1584.

    Article  Google Scholar 

  5. V. Nair and G. E. Hinton, Rectified linear units improve restricted boltzmann machines, Proceedings of the 27th International Conference on Machine Learning (2010) 807–814.

  6. K. Simonyan and A. Zisserman, Very deep convolutional networks for large-scale image recognition, ICLR (2015).

  7. N. Srivastava and G. E. Hinton, Dropout: a simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, 15 (2014) 1929–1958.

    MathSciNet  MATH  Google Scholar 

  8. S. J. Nowlan and G. E. Hinton, Simplifying neural networks by soft weight-sharing, Neural Computation, 4 (1992) 473–493.

    Article  Google Scholar 

  9. F. Jia, Y. Lei, N. Lu and S. Xing, Deep normalized convolutional neural network for imbalanced fault classification of machinery and its understanding via visualization, Mechanical Systems and Signal Processing, 110 (2018) 349–367.

    Article  Google Scholar 

  10. Z. Shang, X. Liao, R. Geng, M. Gao and X. Liu, Fault diagnosis method of rolling bearing based on deep belief network, Journal of Mechanical Science and Technology, 32 (2018) 5139–5145.

    Article  Google Scholar 

Download references

Acknowledgments

This work was supported by Mid-career Researcher Program through NRF of Korea grant funded by the MEST (No. 2019R1A2B5B02069400).

Author information

Authors and Affiliations

  1. Mechanical Engineering, Inha University, Incheon, Korea

    Sang-Yun Lee & Sang-Kwon Lee

Authors
  1. Sang-Yun Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Sang-Kwon Lee
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Sang-Kwon Lee.

Additional information

Sang-Yun Lee is a Ph.D. candidate of the School of Mechanical Engineering, Inha University, Incheon, Korea. He also works for GM Technical Center Korea as a vehicle noise and vibration simulation engineer. His research interests include deep learning for anomaly detection of structure, structure borne noise of vehicle interior and driveline induced vehicle noise vibration using multi-physics analysis.

Sang-Kwon Lee has Ph.D. in ISVR of University of Southampton in UK in 1998. He has been a Professor in Inha University since 1999. His research interesting is automotive noise and vibration control, and health monitoring based on machine learning. He has work experience in Hynuday Motor Company 10 years since 1984 and Samsung Motor Company.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lee, SY., Lee, SK. Deep convolutional neural network with new training method and transfer learning for structural fault classification of vehicle instrument panel structure. J Mech Sci Technol 34, 4489–4498 (2020). https://doi.org/10.1007/s12206-020-1009-3

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12206-020-1009-3

Keywords

Search

Navigation