Application of Support Vector Machine in the Vibration Signal Measuring-Channel Modeling

Abstract:

Article Preview

Measurement accuracy of rotor unbalance in different speeds is affected by the nonlinearity of the vibration signal processing channel. Support Vector regression (SVR) is proposed to use for channel modeling and compensation, which performance is far superior to the traditional look-up table method. First the amplitude-frequency and phase-frequency characteristics models based on SVM regression are made using frequency response data of standard signal passing to measuring-channel as training samples, then the measurement signal is compensated according to the model obtained. Simulation and experimental results show that this method has higher accuracy, better generalization ability than the traditional BP neural network modeling method.

Info:

Periodical:

Edited by:

Chunliang Zhang and Paul P. Lin

Pages:

267-270

Citation:

C. J. Li et al., "Application of Support Vector Machine in the Vibration Signal Measuring-Channel Modeling", Applied Mechanics and Materials, Vols. 226-228, pp. 267-270, 2012

Online since:

November 2012

Export:

Price:

$38.00

[1] C.J. Li: CH. Patent ZL200910197621. 2. (2009).

[2] L.J. Cao and Francis E.H. Tay: Support vector machine with adaptive parameters in financial time series forecasting [J]. IEEE Trans, Neural Netw, Vol. 14 (2003) No. 6, p.1506–1518.

DOI: https://doi.org/10.1109/tnn.2003.820556

[3] Norikazu Takahashi, J. Guo and Tetsuo Nishi: Global Convergence of SMO Algorithm for Support Vector Regression [J]. IEEE Trans, Neural Netw, Vol. 19 (2008) No. 6, pp.971-982.

DOI: https://doi.org/10.1109/tnn.2007.915116

[4] X.Q. WANG,Y.W. LIU,D.P. YANG, et al: Tracking control of real-time force for prosthetic hand based on EMG [J] (In Chinese). Journal of Shenyang University of Technology, Vol. 34 (2008) No. 1, pp.63-67.

[5] W.S. Chen and J.G. M: Support vector regression model for complex target RCS predicting [J]. BIAI, Systems Engineering and Electronics, Vol. 20 (2012) No. 1, pp.65-68.