乙苯化工过程的分布式无迹卡尔曼滤波方法

Distributed Untraced Kalman Filter Method for Ethylbenzene Chemical Process

乙苯化工过程由一系列连续搅拌釜式反应器和分离器组成的大规模非线性系统,针对这一类系统提出了一种基于分布式无迹卡尔曼滤波的状态估计方案。该方法通过将系统分解,对每个子系统设计局部无迹卡尔曼滤波,它接收局部测量值,并与其他滤波器协同计算局部状态估计值的方法完成整个系统的状态估计。给出了详细的分布式无迹卡尔曼滤波的设计方法和估计算法。在不同的噪声下对分布式和集中式无迹卡尔曼进行了比较分析。仿真结果表明,分布式无迹卡尔曼滤波可以很好地处理强噪声,正常噪声下比集中式无迹卡尔曼滤波有更稳定的性能,但在理想噪声下集中式无迹卡尔曼滤波有更好的表现。

Ethylbenzene chemical process is a large-scale nonlinear system composed of a series of continuous stirred tank reactors and separators.A state estimation scheme based on distributed unscented Kalman filter was proposed for this kind of system.In this method,the system was decomposed and the local unscented Kalman filter was designed for each subsystem.It received the local measured values and calculates the local state estimates with other filters to complete the state estimation of the whole system.The detailed design method and estimation algorithm of distributed unscented Kalman filter were given.The distributed and centralized unscented Kalman filter were compared and analyzed under different noise conditions.The simulation results show that distributed unscented Kalman filter can deal with strong noise well,and has more stable performance than centralized unscented Kalman filter under normal noise,but centralized unscented Kalman filter has better performance under ideal noise.