论文信息 - Application of gradient radial basis function network in the modeling of MEMS gyro's random drift

Application of gradient radial basis function network in the modeling of MEMS gyro's random drift

In this paper the random drift of a micro-electro-mechanical system (MEMS) gyro is analyzed and modeled in order to improve its performance. The analysis, which is based on run test, shows that the drift is not a weak stationary random process. Thus, a model based on gradient radial basis function neural network is applied to deal with the non-stationary process. The experiments show that the model is suitable for the random drift.

Wang Jun-pu | Tian Wei-feng | Wang Hao | Jin Zhi-hua

[1] J. Bendat,et al. Random Data: Analysis and Measurement Procedures , 1971 .

[2] Chng Eng Siong,et al. Gradient radial basis function networks for nonlinear and nonstationary time series prediction , 1996, IEEE Trans. Neural Networks.

[3] H. Saunders. Literature Review : RANDOM DATA: ANALYSIS AND MEASUREMENT PROCEDURES J. S. Bendat and A.G. Piersol Wiley-Interscience, New York, N. Y. (1971) , 1974 .

[4] Mohinder S. Grewal,et al. Global Positioning Systems, Inertial Navigation, and Integration , 2000 .

[5] Salvatore Baglio,et al. Theoretical study, modeling and realization of resonant gyroscopes with optical output , 2002, Proceedings of IEEE Sensors.

[6] Hugh F. Durrant-Whyte,et al. Achieving integrity in an INS/GPS navigation loop for autonomous land vehicle applications , 1998, Proceedings. 1998 IEEE International Conference on Robotics and Automation (Cat. No.98CH36146).

[7] Gwilym M. Jenkins,et al. Time series analysis, forecasting and control , 1972 .

[8] W. H. Williams,et al. Probability Theory and Mathematical Statistics , 1964 .