基于混合滤波最大期望算法的高速列车建模

Hybrid Filter Based Expectation Maximization Algorithm for High-speed Train Modeling

针对高速列车非线性单质点模型的特殊结构及含有隐含变量问题,提出一种基于混合滤波的最大期望辨识方法.借助递阶辨识理论,将高铁列车状态空间模型分解为线性子系统模型和非线性子系统模型.进而,分别利用卡尔曼滤波和粒子滤波对速度和位移状态进行联合估计.最后,使用最大期望方法辨识高铁列车子系统模型参数,解决了隐含变量辨识问题.和传统方法相比,本文所提出方法计算量小,且具有较高的辨识精度.仿真对比实验结果验证了该方法的有效性.

For the special high-speed train model structure with hidden variables in the form of the single masspoint,a hybrid filter based expectation maximization(EM)algorithm is proposed.By employing the hierarchical identification theory,the high-speed train state-space model is decomposed into a linear subsystem and a nonlinear subsystem.Furthermore,the Kalman filter and the particle filter are provided to estimate the velocity and displacement,respectively.Finally,the parameters of subsystems are identified by using the EM algorithm.Compared to the classical methods,the proposed algorithm can produce high accuracy estimation with less computational effort.The simulation results verify the effectiveness of the algorithm.