Online identification of Hammerstein systems with B‐spline networks
Top Cited Papers
- 27 March 2024
- journal article
- research article
- Published by Wiley in International Journal of Adaptive Control and Signal Processing
- Vol. 38 (6) , 2074-2092
Abstract
Summary: Nonlinear systems widely exist in real‐word applications and the research for these systems has enjoyed a long and fruitful history, including the system identification community. However, the modeling for nonlinear systems is often quite challenging and still remains many unresolved questions. This article considers the online identification issue of Hammerstein systems, whose nonlinear static function is modeled by a B‐spline network. First, the identification model of the studied system is constructed using the bilinear parameter decomposition model. Second, the online recursive algorithms are proposed to find the estimates using the moving data window and the particle swarm optimization procedure, and show that these estimates converge to their true values with a low computational burden. Numerical examples are also given to test the effectiveness of the proposed algorithms.Keywords
Funding Information
- Basic and Applied Basic Research Foundation of Guangdong Province (2023A1515011245, 2021A1515012635)
- National Natural Science Foundation of China (61903095, T2341019)
This publication has 83 references indexed in Scilit:
- Parameter estimation of fractional‐order Hammerstein state space system based on the extended Kalman filterInternational Journal of Adaptive Control and Signal Processing, 2023
- Joint two‐stage multi‐innovation recursive least squares parameter and fractional‐order estimation algorithm for the fractional‐order input nonlinear output‐error autoregressive modelInternational Journal of Adaptive Control and Signal Processing, 2023
- Filtered multi‐innovation‐based iterative identification methods for multivariate equation‐error ARMA systemsInternational Journal of Adaptive Control and Signal Processing, 2023
- Second‐order optimization methods for time‐delay Autoregressive eXogenous models: Nature gradient descent method and its two modified methodsInternational Journal of Adaptive Control and Signal Processing, 2022
- Two‐stage gradient‐based iterative algorithms for the fractional‐order nonlinear systems by using the hierarchical identification principleInternational Journal of Adaptive Control and Signal Processing, 2022
- A novel nonlinear optimization method for fitting a noisy Gaussian activation functionInternational Journal of Adaptive Control and Signal Processing, 2021
- Auxiliary model‐based multi‐innovation recursive identification algorithms for an input nonlinear controlled autoregressive moving average system with variable‐gain nonlinearityInternational Journal of Adaptive Control and Signal Processing, 2021
- Identification and U‐control of a state‐space system with time‐delayInternational Journal of Adaptive Control and Signal Processing, 2021
- Maximum likelihood hierarchical least squares‐based iterative identification for dual‐rate stochastic systemsInternational Journal of Adaptive Control and Signal Processing, 2020
- The filtering‐based maximum likelihood iterative estimation algorithms for a special class of nonlinear systems with autoregressive moving average noise using the hierarchical identification principleInternational Journal of Adaptive Control and Signal Processing, 2019