Nonlinear System Identification Based on Combined Signal Sources

doi:10.16182/j.issn1004731x.joss.21-0589

Abstract

Abstract:

Aiming at the interference of noise in the nonlinear system, the identification modeling method of the neuro-fuzzy Hammerstein output error nonlinear system is considered. The combined signal sources are used to realize the parameter identification separation of the linear block and the nonlinear block. The correlation analysis method and the recursive least square identification method based on auxiliary model technique are derived to estimate the parameters of dynamic linear block and nonlinear block, which can effectively suppress the interference of system output noise. Compared with least square algorithm, polynomial model and multi-innovation method, the simulation results demonstrate that the proposed approach has the advantages of fast convergence speed of parameter estimation, high identification accuracy and small modeling error, which verifies the effectiveness of the proposed approach.

Key words: Hammerstein nonlinear system, identification modeling, combined signal sources, correlation analysis method

CLC Number:

Tian Zheng, Feng Li, Naibao He, Ya Gu. Nonlinear System Identification Based on Combined Signal Sources[J]. Journal of System Simulation, 2022, 34(11): 2377-2385.

Figures/Tables 8

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Table 1

Fig. 7

References 31

[1]	Li Feng, Jia Li, Peng Daogang, et al. Neuro-fuzzy Based Identification Method for Hammerstein Output Error Model with Colored Noise[J]. Neurocomputing (S0925-2312), 2017, 244: 90-101.
[2]	Lakhdar A, Yahya C. Modeling of a Distillation Column Based on NARMAX and Hammerstein Models[J]. International Journal of Modeling, Simulation and Scientific Computing (S1793-9623), 2017, 8(3): 227-240.
[3]	Fouad Giri, Er-Wei Bai. Block-Oriented Nonlinear System Identification[M]. Berlin Heidelberg: Springer-Verlag, 2010.
[4]	桂卫华, 宋海鹰, 阳春华. Hammerstein-Wiener模型最小二乘向量机辨识及其应用[J]. 控制理论与应用, 2008, 25(3): 393-397.
	Gui Weihua, Song Haiying, Yang Chunhua. Hammerstein-Wiener Model Identified by Least-Squares-Support-Vector Machine and Its Application[J]. Control Theory and Applications, 2008, 25(3): 393-397.
[5]	Raphael Q, Claudio G. MPC Relevant Identification Method for Hammerstein and Wiener models[J]. Journal of Process Control (S0959-1524), 2019, 80: 78-88.
[6]	Vojislav F. Recursive Identification of Block-Oriented Nonlinear Systems in the Presence of Outliers[J]. Journal of Process Control (S0959-1524), 2019, 78: 1-12.
[7]	Li Junhong, Zheng Weixing, Gu Juping, et al. A Recursive Identification Algorithm for Wiener Nonlinear Systems with Linear State-Space Subsystem[J]. Circuits Systems and Signal Processing (S0278-081X), 2018, 37(6): 2347-2393.
[8]	Qi Zhidong, Sun Qi, Ge Weiping, et al. Nonlinear Modeling of PEMFC Based on Fractional Order Subspace Identification[J]. Asian Journal of Control (S1561-8625), 2020, 22(5): 1892-1900.
[9]	Cheng C M, Dong X J, Peng Z K, et al. Kautz Basis Expansion-based Hammerstein System Identification through Separable Least Squares Method[J]. Mechanical Systems and Signal Processing (S0888-3270), 2019, 121: 929-941.
[10]	Jeremy G, James W. Frequency Domain Estimation of Parallel Hammerstein Systems Using Gaussian Process Regression[J]. IFAC PapersOnLine (S2405-8963), 2018, 51(15): 1014-1019.
[11]	Lang Lijun, Chen Junru, Gao Jun, et al. Accelerating Frequency Domain Dielectric Spectroscopy Measurements on Insulation of Transformers Through System Identification[J]. IET Science, Measurement & Technology (S1751-8822), 2018, 12(2): 247-254.
[12]	Li Shurong, Ge Yulei, Shi Yuhuan. An Iterative Dynamic Programming Optimization Based on Biorthogonal Spatial-Temporal Hammerstein Modeling for the Enhanced Oil Recovery of ASP Flooding[J]. Journal of Process Control (S0959-1524), 2019, 73: 75-88.
[13]	Chidume C, Adamu A, Okereke L. Iterative Algorithms for Solutions of Hammerstein Equations in Real Banach Spaces[J]. Fixed Point Theory and Applications (S1687-1820), 2020, 3: 567-572.
[14]	Chen Xinming, Chen Hanfu. Recursive Identification for MIMO Hammerstein Systems[J]. IEEE Transactions on Automatic Control (S0018-9286), 2011, 56(4): 895-902.
[15]	李峰, 谢良旭, 李博, 等. 基于组合式信号的Hammerstein OE模型辨识[J]. 江苏理工学院学报, 2019, 25(6): 66-72.
	Li Feng, Xie Liangxu, Li Bo, et al. Combined Signals Based on Identification Method of the Hammerstein OE Model[J]. Journal of Jiangsu Institute of Technology, 2019, 25(6): 66-72.
[16]	Kajal K, Utkal M, Vineet P, et al. Identification Scheme for Fractional Hammerstein Models with the Delayed Haar Wavelet[J]. IEEE-CAA Journal of Automatica Sinica (S2329-9266), 2020, 7(3): 822-892.
[17]	Ding Feng, Wang Xuehai, Chen Qijia, et al. Recursive Least Squares Parameter Estimation for a Class of Output Nonlinear Systems Based on the Model Decomposition[J]. Circuits Systems and Signal Processing (S0278-081X), 2016, 35(9): 3323-3338.
[18]	Ding Jie, Chen Jiazhong, Lin Jinxing, et al. Particle Filtering Based Parameter Estimation for Systems with Output-error Type Model Structures[J]. Journal of the Franklin Institute (S0016-0032), 2019, 36(10): 5521-5540.
[19]	Ding Feng. Hierarchical Multi-innovation Stochastic Gradient Algorithm for Hammerstein Nonlinear System Modeling[J]. Applied Mathematical Modelling (S0307-904X), 2013, 37(4): 1694-1704.
[20]	Jia Li, Li Xunlong, Chui Minsen. The Identification of Neuro-fuzzy Based MIMO Hammerstein Model with Separable Input Signals[J]. Neurocomputing (S0925-2312), 2016, 174: 530-541.
[21]	Ding Feng, Shi Yang, Chen Tongwen. Auxiliary Model-Based Least-Squares Identification Methods for Hammerstein Output-Error System[J]. Systems and Control Letters (S0167-6911), 2007, 56(5): 373-380.
[22]	Wang Dongqing, Ding Feng. Parameter Estimation Algorithms for Multivariable Hammerstein CARMA Systems[J]. Information Sciences (S0020-0255), 2016, 355/356: 237-248.
[23]	Lang Ziqiang. On Identification of the Controlled Plants Described by the Hammerstein Systems[J]. IEEE Transactions on Automatic Control (S0018-9286), 2002, 39(3): 569-573.
[24]	Martin E, Lennart L. Linear Approximations of Nonlinear FIR Systems for Separable Input Processes[J]. Automatica (S0005-1098), 2005, 41(3): 459-473.
[25]	Li Feng, Jia Li, Peng Daogang. Identification method of neuro-fuzzy-based Hammerstein model with colored noise[J]. IET Control Theory and Applications (S1751-8644), 2017, 11(17): 3026-3037.
[26]	Wang Jeenshing, Chen Yenping. A Hammerstein Recurrent Neurofuzzy Network with an Online Minimal Realization Learning Algorithm[J]. IEEE Transactions on Fuzzy Systems (S1063-6706), 2008, 16(6): 1597-1612.
[27]	Tang Yinggan, Li Zhonghui, Guan Xinping. Identification of Nonlinear System Using Extreme Learning Machine Based Hammerstein Model[J]. Communication in Nonlinear Science and Numerical Simulation (S1007-5704), 2014, 19(9): 3171-3183.
[28]	Bai Erwei, Li Kang. Convergence of the Iterative Algorithm for a General Hammerstein System Identification[J]. Automatica (S0005-1098), 2010, 46: 1891-1896.
[29]	Chen Jing, Wang Xiuping. Identification of Hammerstein Systems with Continuous Nonlinearity[J]. Information Processing Letters (S0020-0190), 2015, 115: 822-827.
[30]	Shen Qianyan, Ding Feng. Multi-innovation Parameter Estimation for Hammerstein MIMO Output-error Systems Based on the Key-term Separation[J]. IFAC-PapersOnLine (S2405-8963), 2015, 48(8): 457-462.
[31]	Ding Feng, Wang Yanjiao, Dai Jiyang, et al. A Recursive Least Squares Parameter Estimation Algorithm for Output Nonlinear Autoregressive Systems Using the Input-output Data Filtering[J]. Journal of the Franklin Institute (S0016-0032), 2017, 354(15): 6938-6955.

方法	阶次	MSE	MAE
多项式法	9	1.8×10^‒3	1.165 5
	10	7.9×10^‒4	0.812 5
	11	4.6×10^‒4	0.416 5
	12	3.7×10^‒3	1.398 7
本文所提方法		2.298 6×10^‒4	0.227 4