Parameter Estimation for Nonlinear Functions Related to System Responses

International Journal of Control Automation and Systems, Journal Year: 2023, Volume and Issue: 21(6), P. 1780 - 1792

Published: May 6, 2023

Language: Английский

---

Joint two‐stage multi‐innovation recursive least squares parameter and fractional‐order estimation algorithm for the fractional‐order input nonlinear output‐error autoregressive model

International Journal of Adaptive Control and Signal Processing, Journal Year: 2023, Volume and Issue: 37(7), P. 1650 - 1670

Published: April 3, 2023

Summary This paper mainly investigates the issue of parameter identification for fractional‐order input nonlinear output error autoregressive (IN‐OEAR) model. In order to avoid problem large computation redundant estimation, form system can be expressed by a linear combination unknown parameters through key term separation. Through employing hierarchial principle, IN‐OEAR model is decomposed into two sub‐models with smaller number parameters. On basis recursive methods, least squares sub‐algorithm and gradient stochastic are proposed estimate fractional‐order, respectively. With aim achieving more accurate estimates, two‐stage multi‐innovation algorithm means theory. The numerical simulation results test effectiveness methods.

Language: Английский

---

Multivariable CAR-like System Identification with Multi-innovation Gradient and Least Squares Algorithms

International Journal of Control Automation and Systems, Journal Year: 2023, Volume and Issue: 21(5), P. 1455 - 1464

Published: March 17, 2023

Language: Английский

---

Hierarchical gradient‐ and least‐squares‐based iterative estimation algorithms for input‐nonlinear output‐error systems from measurement information by using the over‐parameterization

International Journal of Robust and Nonlinear Control, Journal Year: 2023, Volume and Issue: 34(2), P. 1120 - 1147

Published: Oct. 17, 2023

Abstract This article investigates the parameter identification problems of stochastic systems described by input‐nonlinear output‐error (IN‐OE) model. IN‐OE model consists two submodels, one is an input nonlinear and other a linear The difficulty in that information vector contains unknown variables, which are noise‐free (true) outputs system, approach taken here to replace terms with auxiliary Based on over‐parameterization hierarchical principle, gradient‐based iterative algorithm least‐squares‐based proposed estimate parameters systems. Finally, numerical simulation examples given demonstrate effectiveness algorithms.

Language: Английский

---

An identification algorithm of generalized time-varying systems based on the Taylor series expansion and applied to a pH process

Journal of Process Control, Journal Year: 2023, Volume and Issue: 128, P. 103007 - 103007

Published: June 20, 2023

Language: Английский

---

Recursive identification methods for general stochastic systems with colored noises by using the hierarchical identification principle and the filtering identification idea

Annual Reviews in Control, Journal Year: 2024, Volume and Issue: 57, P. 100942 - 100942

Published: Jan. 1, 2024

Language: Английский

---

Decomposition and composition modeling algorithms for control systems with colored noises

International Journal of Adaptive Control and Signal Processing, Journal Year: 2023, Volume and Issue: 38(1), P. 255 - 278

Published: Oct. 19, 2023

Summary This article proposes a novel identification framework for estimating the parameters of controlled autoregressive moving average (CARARMA) models with colored noise. By means building an auxiliary model and using hierarchical principle, this investigates highly‐efficient parameter estimation algorithm. In order to meet need identifying systems large‐scale parameters, whole CARARMA system is separated into two sets decomposition composition recursive algorithm (i.e., generalized extended least squares or decomposition‐based algorithm) presented. Moreover, analyzes convergence proposed The performance analysis shows that can reduce complexity compared without decomposition.

Language: Английский

---

Parameter estimation of fractional‐order Hammerstein state space system based on the extended Kalman filter

International Journal of Adaptive Control and Signal Processing, Journal Year: 2023, Volume and Issue: 37(7), P. 1827 - 1846

Published: May 4, 2023

Summary This paper addresses the combined estimation issues of parameters and states for fractional‐order Hammerstein state space systems with colored noises. An extended estimator is derived by using parameter estimates to replace unknown system in Kalman filter. The hierarchical identification principle introduced solve measurement By introducing forgetting factor, an filtering‐based factor stochastic gradient algorithm presented estimate states, fractional‐order. A numerical example respectively demonstrate feasibility proposed algorithm. It can be seen that errors are relatively small, which reflects algorithms have good effect.

Language: Английский

---

Filtered generalized iterative parameter identification for equation‐error autoregressive models based on the filtering identification idea

International Journal of Adaptive Control and Signal Processing, Journal Year: 2024, Volume and Issue: 38(4), P. 1363 - 1385

Published: Jan. 28, 2024

Summary By using the collected batch data and iterative search, based on filtering identification idea, this article investigates proposes a filtered multi‐innovation generalized projection‐based method, gradient‐based least squares‐based method for equation‐error autoregressive systems described by models. These methods can be extended to other linear nonlinear scalar multivariable stochastic with colored noises.

Language: Английский

---

Maximum likelihood based multi‐innovation stochastic gradient identification algorithms for bilinear stochastic systems with ARMA noise

International Journal of Adaptive Control and Signal Processing, Journal Year: 2023, Volume and Issue: 37(10), P. 2690 - 2705

Published: July 13, 2023

Summary This paper considers the parameter estimation problem for bilinear stochastic systems with autoregressive moving average (ARMA) noise using gradient method. First, identification model is derived by eliminating state variables. Based on obtained model, a multi‐innovation generalized extended (MI‐GESG) algorithm proposed theory. Furthermore, to enhance accuracy, maximum likelihood based MI‐GESG (ML‐MI‐GESG) developed principle. Finally, an illustrative simulation example provided testify algorithms. The results show effectiveness of algorithms identifying systems.

Language: Английский

---