【摘要】 运用扩维技术以及扩展卡尔曼滤波算法的跟踪辨识特性同步实现对多变量混沌序列的精确预测和混沌系统主动态方程的参数辨识。利用典型混沌方程与所观测时间序列的吸引子特性比较,较准确地确定系统初始状态。对理想R?ssler三个变量的时间序列和大连市气温降雨二变量时间序列进行仿真并与递推最小二乘法进行比较,结果表明该方法的有效性。更多还原

【Abstract】 Application of vector-dimension-augmenting technique and the real-time capability of expanded Kalman filter on synchronously predicting the multivariate chaotic time series and adjusting the parameters of governing system equations were proposed. Comparison of strange attractor’s characteristics between typical chaotic equations and observed time series was made to better define the initial system state. Simulation examples from the typical R?ssler equation and the practically observed values of rainfall and temperature of Dalian are used to show the validity of the proposed method.更多还原