An approach to phase space reconstruction from multivariate data based on data fusion

Abstract

To cope with the problem of phase space reconstruction from univariate time series and multivariate time series, the novel approach to phase space reconstruction from multivariate data based on data fusion is presented in this paper. According to Bayes estimation theory, the phase points in the same phase space reconstructed from multivariate data are fused, then an optimal fusion phase space could be determined. The approach is applied to multivariate phase space reconstructions of Lorenz system and Rssler system, respectively. Compared with the figures reconstructed from univariate datas, the information reconstructed from multivariate data includes the main characters of all univariate data and represents the comprehensive information of system attractor, which makes the phase space reconstructed more abundant. At last, the approach is applied to multivariate phase space reconstruction of oil film whirling in the rotor system. The information reconstructed includes all the characters of the system, which improves the veracity for fault diagnosis. So all the analysis further shows that the approach presented here is effective.