Full Text:   <1117>

Summary:  <839>

CLC number: TP273

On-line Access: 2014-01-29

Received: 2013-03-26

Revision Accepted: 2013-05-14

Crosschecked: 2014-01-15

Cited: 2

Clicked: 3244

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
1. Reference List
Open peer comments

Journal of Zhejiang University SCIENCE C 2014 Vol.15 No.2 P.147-152

http://doi.org/10.1631/jzus.C1300072


Stochastic gradient algorithm for a dual-rate Box-Jenkins model based on auxiliary model and FIR model


Author(s):  Jing Chen, Rui-feng Ding

Affiliation(s):  School of Science, Jiangnan University, Wuxi 214122, China; more

Corresponding email(s):   chenjing1981929@126.com

Key Words:  Parameter estimation, Auxiliary model, Dual-rate system, Stochastic gradient, Box-Jenkins model, FIR model


Jing Chen, Rui-feng Ding. Stochastic gradient algorithm for a dual-rate Box-Jenkins model based on auxiliary model and FIR model[J]. Journal of Zhejiang University Science C, 2014, 15(2): 147-152.

@article{title="Stochastic gradient algorithm for a dual-rate Box-Jenkins model based on auxiliary model and FIR model",
author="Jing Chen, Rui-feng Ding",
journal="Journal of Zhejiang University Science C",
volume="15",
number="2",
pages="147-152",
year="2014",
publisher="Zhejiang University Press & Springer",
doi="10.1631/jzus.C1300072"
}

%0 Journal Article
%T Stochastic gradient algorithm for a dual-rate Box-Jenkins model based on auxiliary model and FIR model
%A Jing Chen
%A Rui-feng Ding
%J Journal of Zhejiang University SCIENCE C
%V 15
%N 2
%P 147-152
%@ 1869-1951
%D 2014
%I Zhejiang University Press & Springer
%DOI 10.1631/jzus.C1300072

TY - JOUR
T1 - Stochastic gradient algorithm for a dual-rate Box-Jenkins model based on auxiliary model and FIR model
A1 - Jing Chen
A1 - Rui-feng Ding
J0 - Journal of Zhejiang University Science C
VL - 15
IS - 2
SP - 147
EP - 152
%@ 1869-1951
Y1 - 2014
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/jzus.C1300072


Abstract: 
Based on the work in Ding and Ding (2008), we develop a modified stochastic gradient (SG) parameter estimation algorithm for a dual-rate box-Jenkins model by using an auxiliary model. We simplify the complex dual-rate box-Jenkins model to two finite impulse response (FIR) models, present an auxiliary model to estimate the missing outputs and the unknown noise variables, and compute all the unknown parameters of the system with colored noises. Simulation results indicate that the proposed method is effective.

基于辅助模型和有限脉冲响应模型的双率Box-Jenkins系统随机梯度辨识算法

研究目的:对具有双率特性的Box-Jenkins模型提出基于辅助模型的修正随机梯度算法。将复杂的Box-Jenkins模型简化为两个有限脉冲模型,并利用辅助模型辨识出系统损失的输出数据和未知噪声向量,接着利用修正的随机梯度算法辨识出系统的参数。仿真结果验证了方法的有效性。
研究手段:利用有限脉冲响应模型将复杂的Box-Jenkins模型转化成两个有限脉冲响应模型。双率系统的输出存在丢失情况,而传统的多项式转换技术是通过多项式转换技巧转换系统模型使其适合双率情形,但这样会导致待辨识参数维数的增大。本文通过损失数据估计方法插补丢失的输出数据,使其适合单率情形。损失数据估计方法的基本思想是,通过前一时刻参数和前一时刻信息向量辨识出当前时刻损失的输出,进而利用当前时刻信息向量刷新未知参数,两者交替进行。该方法不会增加待辨识参数维数,因而辨识效果较好。
重要结论:1. 采用有限脉冲方法,将复杂的Box-Jenkins模型转化成两个简单的有限脉冲模型。2. 利用损失数据估计方法辨识出系统丢失的数据和未知的噪声向量。3. 利用辨识出的数据能计算出带有有色噪声干扰的原系统的参数。4. 不会造成待辨识参数维数增大。

关键词:参数估计,辅助模型,双率系统,随机梯度,Box-Jenkins模型

Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article

Reference

[1]BuHamra, S., Smaoui, N., Gabr, M., 2003. The Box-Jenkins analysis and neural networks: prediction and time series modelling. Appl. Math. Model., 27(10):805-815.

[2]Cattivelli, F.S., Lopes, C.G., Sayed, A.H., 2008. Diffusion recursive least-squares for distributed estimation over adaptive networks. IEEE Trans. Signal Process., 56(5):1865-1877.

[3]Chen, J., 2014. Several gradient parameter estimation algorithms for dual-rate sampled systems. J. Frank. Inst., 351(1):543-554.

[4]Chen, J., Ding, F., 2011. Modified stochastic gradient algorithms with fast convergence rates. J. Vibr. Contr., 17(9):1281-1286.

[5]Chen, J., Lu, X.L., Ding, R.F., 2012. Parameter identification of systems with preload nonlinearities based on the finite impulse response model and negative gradient search. Appl. Math. Comput., 219(5):2498-2505.

[6]Deboucha, A., Taha, Z., 2010. Identification and control of a small-scale helicopter. J. Zhejiang Univ.-Sci. A (Appl. Phys. & Eng.), 11(12):978-985.

[7]Ding, F., 2013a. Coupled-least-squares identification for multivariable systems. IET Contr. Theory Appl., 7(1):68-79.

[8]Ding, F., 2013b. Hierarchical multi-innovation stochastic gradient algorithm for Hammerstein nonlinear system modeling. Appl. Math. Model., 37(4):1694-1704.

[9]Ding, F., 2013c. Decomposition based fast least squares algorithm for output error systems. Signal Process., 93(5):1235-1242.

[10]Ding, F., 2014. Combined state and least squares parameters estimation algorithms for dynamic systems. Appl. Math. Model., 38(1):403-412.

[11]Ding, F., Liu, X.G., Chu, J., 2013. Gradient-based and least-squares-based iterative algorithms for Hammerstein systems using the hierarchical identification principle. IET Contr. Theory Appl., 7(2):176-184.

[12]Ding, J., Ding, F., 2008. The residual based extended least squares identification method for dual-rate systems. Comput. Math. Appl., 56(6):1479-1487.

[13]Forssell, U., Ljung, L., 2000. Identification of unstable systems using output error and Box-Jenkins model structures. IEEE Trans. Autom. Contr., 45(1):137-141.

[14]Kadu, S.C., Bhushan, M., Gudi, R., 2008. Optimal sensor network design for multirate systems. J. Proc. Contr., 18(6):594-609.

[15]Liu, Y.J., Xiao, Y.S., Zhao, X.L., 2009. Multi-innovation stochastic gradient algorithm for multiple-input single-output systems using the auxiliary model. Appl. Math. Comput., 215(4):1477-1483.

[16]Liu, Y.J., Yu, L., Ding, F., 2010a. Multi-innovation extended stochastic gradient algorithm and its performance analysis. Circ. Syst. Signal Process., 29(4):649-667.

[17]Liu, Y.J., Wang, D.Q., Ding, F., 2010b. Least-squares based iterative algorithms for identifying Box-Jenkins models with finite measurement data. Digit. Signal Process., 20(5):1458-1467.

[18]Nakamori, S., Hermoso-Carazo, A., Linares-Pérez, J., 2007. Suboptimal estimation of signals from uncertain observations using approximations of mixtures. Digit. Signal Process., 17(1):4-16.

[19]Sägfors, M.F., Toivonen, H.T., 1997. H and LQG control of asynchronous sampled-data systems. Automatica, 33(9):1663-1668.

[20]Shi, Y., Ding, F., Chen, T., 2006. Multirate crosstalk identification in xDSL systems. IEEE Trans. Commun., 54(10):1878-1886.

[21]Vörös, J., 2010. Modeling and identification of systems with backlash. Automatica, 46(2):369-374.

[22]Wang, D.Q., Yang, G.W., Ding, R.F., 2010. Gradient-based iterative parameter estimation for Box-Jenkins systems. Comput. Math. Appl., 60(5):1200-1208.

[23]Wu, P., Yang, C.J., Song, Z.H., 2009. Subspace identification for continuous-time errors-in-variables model from sampled data. J. Zhejiang Univ.-Sci. A (Appl. Phys. & Eng.), 10(8):1177-1186.

[24]Zong, C.F., Song, P., Hu, D., 2011. Estimation of vehicle states and tire-road friction using parallel extended Kalman filtering. J. Zhejiang Univ.-Sci. A (Appl. Phys. & Eng.), 12(6):446-452.

Open peer comments: Debate/Discuss/Question/Opinion

<1>

Please provide your name, email address and a comment





Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - Journal of Zhejiang University-SCIENCE