Particle Filter based Neural Network Modeling of Nonlinear Systems for State Space Estimation
The system identification/modeling problem looks for a suitably parameterized model, representing a given process. The parameters of the model are adjusted to optimize a performance function based on error between the given process output and identified process output. The linear system identification field is well established with many classical approaches whereas most of those methods cannot be applied for nonlinear systems. The problem becomes tougher if the system is completely unknown with only the output time series is available. It has been reported that the capability of Artificial Neural Network to approximate all linear and nonlinear input-output maps makes it predominantly suitable for the identification of nonlinear systems, where only the output time series is available. 1245.The work reported here is an attempt of modeling certain nonlinear systems using recurrent neural networks with Extended Kalman Filtering (EKF) and Particle Filtering (PF) approaches 19. An assessment on the model performances in the mean square error (MSE) sense has also been done for both.
EKF MSE Particle Filter State Space modeling RNN Monte Carlo Integration SIR
M.V Rajesh Archana R A Unnikrishnan R Gopikakaumari
Federal Institute of Science & Technology, Mookkannur, Angamali, Kerala, India-682 021 Federal Institute of Science & Technology, Mookkannur, Angamali, Kerala, India Naval Physical & Oceanographic Laboratory, (DRDO-Govt. of India), Cochin, Kerala, India-682021 Cochin University of Science & Technology, CUSAT(PO), Kerala, India-682022
国际会议
2009年中国控制与决策会议(2009 Chinese Control and Decision Conference)
广西桂林
英文
1477-1482
2009-06-17（万方平台首次上网日期，不代表论文的发表时间）