论文部分内容阅读
从交互式多模型估计(IMM)方法的特点出发,提出用IMM估计方法对有测量数据丢失的非线性系统进行估计.IMM模型集中包含两个模型:一个模型对应测量数据丢失情况,另一个对应测量数据未丢失.最终基于两个模型的估计进行融合得到估计结果,改善估计器在测量信息丢失情况下的稳定性.采用随机无迹卡尔曼滤波(RUKF)方法对每个模型分别进行滤波,消除标准无迹卡尔曼滤波(UKF)方法的系统误差.仿真结果表明:在测量信息丢失的情况下,提出的估计方法在稳定性与估计性能上都优于传统的基于单模型的非线性系统混合估计方法.
Based on the characteristics of the IMM (Multi-Model Estimation) method, an IMM estimation method is proposed to estimate the nonlinear system with measured data loss. The IMM model set contains two models: one model corresponding to the measurement data loss and the other corresponding The measurement data is not lost.Finally, the estimation results are fused based on the estimation of the two models to improve the stability of the estimator in the case of loss of measurement information.Using the random unscented Kalman filter (RUKF) method to filter each model separately, The system error of the standard Unscented Kalman Filter (UKF) is eliminated.The simulation results show that the proposed estimation method is superior to the traditional single-model-based nonlinear system in terms of stability and estimation performance under the condition of loss of measurement information Hybrid estimation method.