Decomposition-Based Gradient Iterative Estimation for Input Nonlinear Model by Using the Kalman Filter
This paper considers the joint iterative estimation of the parameters and states for Hammerstein nonlinear state space systems. By applying the model decomposition technique, the unknown parameters to be estimated are distributed into two regression identification models. Furthermore, under the framework of the gradient iterative algorithm and the hierarchical identification theory, a decomposition-based gradient iterative algorithm is proposed to estimate the unknown parameters of nonlinear system. Finally, a numerical simulation example is given to validate the effectiveness of the algorithm.
KeywordsInput nonlinear model Kalman filter Model decomposition Gradient iterative
This work was supported in part by the National Natural Science Foundation of China under Grants 61803183 and 61773182, the Natural Science Foundation of Jiangsu Province under Grants BK20180591 and BK20170198, and the Fundamental Research Funds for the Central Universities under Grant JUSRP11923.
- 2.Houda, S., Samira, K.: Identification of nonlinear dynamic systems described by Hammerstein state-space models with discontinuous nonlinearities. Int. J. Model. Ident. Control 3, 127–135 (2017)Google Scholar
- 7.Mehmood, A., Chaudhary, N.I., Zameer, A.: Backtracking search optimization heuristics for nonlinear hammerstein controlled auto regressive auto regressive systems. ISA Trans. (2019)Google Scholar
- 11.Ma, J., Wu, O., Huang, B., et al.: Expectation maximization estimation for a class of input nonlinear state space systems by using the Kalman smoother. Signal Process. 148, 295–303 (2017)Google Scholar
- 18.A novel data filtering based multi-innovation stochastic gradient algorithm for hammerstein nonlinear system. Digit. Signal Process. 46, 215–225 (2015)Google Scholar