Advertisement

Vibration signal prediction model for the miniature transducer using deep learning network

  • Yen-Ta Chiang
  • Yu-Ting TsaiEmail author
Conference paper
Part of the Mechanisms and Machine Science book series (Mechan. Machine Science, volume 73)

Abstract

This work presents a deep artificial neural network (DNN) using input/output measurements of the miniature transducer. The DNN consists of a convolution network with one-dimensional convolution layers, pooling layers and full connection layers with ReLU activation function. In the training process, the coefficients of each layer are adapted to minimize the loss function as the least-square function. In the experiment tests, the numerous type of signals used for training and validation tests. As a result, the proposed model can fit the output response of the miniature transducer in high accuracy.

Keywords

deep learning network miniature transducer 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Notes

Acknowledgments

The authors would like to thank the Ministry of Science and Technology of Taiwan for financial support under Contract Nos. MOST 107-2221-E-035-061-.

References

  1. 1.
    Torsten, Söderström, Stoica, P.: System identification. New York: Prentice Hall. ISBN 978-0138812362 (1989).Google Scholar
  2. 2.
    Huang C. H., Pawar S. J., Hong Z. J., Huang J. H.: Insert earphone modeling and measurement by IEC-60711 coupler. IEEE Trans. Ultrason. Ferroelectr. Freq. Control, 58(2), 461–469 (2011).Google Scholar
  3. 3.
    Jensen J., Agerkvist F. T., Harte J. M.: Nonlinear Time-Domain Modeling of Balanced-Armature Receivers. J. Audio Eng. Soc., 59(3), 91–101 (2011).Google Scholar
  4. 4.
    Fukushima K.: Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern., 36(4), 193-202 (1980).Google Scholar
  5. 5.
    Lecun Y., Bottou L., Bengio Y., Haffner P.: Gradient-based learning applied to document recognition, Proc. IEEE, 86(11), 2278–2324 (1998).Google Scholar
  6. 6.
    Rumelhart D. E., Hinton G. E., Williams R. J.: Learning representations by backpropagating errors. Nature, 323(6088), 533-536 (1986).Google Scholar
  7. 7.
    API first for data science (Pivotal Engineering Journal), http://engineering.pivotal.io/post/api-first-for-data-science/ last accessed 2019/03/28.
  8. 8.
    Krizhevsky A., Sutskever I., Hinton G. E.: ImageNet classification with deep convolutional neural networks. Commun. ACM VO, 60(6), 84-93 (2017).Google Scholar
  9. 9.
    Fred A., Agarap M.: Deep Learning using Rectified Linear Units (ReLU). arXiv:1803.08375v2, 7 (2019).
  10. 10.
    Kingma D. P., Ba J.: Adam: A Method for Stochastic Optimization. CoRR, abs/1412.6 (2014).Google Scholar
  11. 11.
    GRAS RA0045 Externally Polarized Ear Simulator According to IEC 60318-4 (60711). http://www.gras.dk/products/product/248-RA0045. last accessed 2018/04/20.
  12. 12.
    TensorFlow. https://www.tensorflow.org/. last accessed 2019/02/12.

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.Master’s Degree Program of electro-acousticFeng Chia UniversityTaichungTaiwan

Personalised recommendations