Abstract
In this paper, the estimation problem is considered for both sample delay and coefficients of ARMAX model. An extended recursive least squares algorithm is derived by minimizing a quadratic cost function. However, the solution of the optimization problem returns a real value for the sample delay. To overcome this difficulty, the rounding properties are used to transform the integer nonlinear problem into a real optimization problem. In addition, consistency of the estimates with their convergence rates are established under the persistent excitation condition. Finally, experimental results on semi-batch reactor are presented to illustrate the performance of the proposed method.
Similar content being viewed by others
References
M. Almalki, E. Alaidarous, D. Maturi, M. Raja, M. Shoaib, A Levenberg–Marquardt backpropagation neural network for the numerical treatment of squeezing flow with heat transfer model. IEEE Access 8, 227340–227348 (2020)
S. Bedoui, K. Abderrahim, ARMAX time delay systems identification based on least square approach, in Proceedings of the\(17^{th}\)IFAC Symposium on System Identification, China (2015)
S. Bedoui, M. Ltaief, K. Abderrahim, A new recursive algorithm for simultaneous identification of discrete time delay systems, in Proceedings of the 16th IFAC Symposium on System Identification (SYSID 2012), Brussel, Belgium (2012)
S. Bedoui, M. Ltaief, K. Abderrahim, New results on discrete time delay systems. Int. J. Autom. Comput. IJAC 9(6), 570–577 (2012)
S. Bedoui, M. Ltaief, K. Abderrahim, Using a recursive least square algorithm for identification of interconnected linear discrete-time delay multivariable systems, in Proceedings of the 17th IEEE International Conference on Methods & Models in Automation & Robotics (MMAR2012), Miedzyzdroje, Poland (2012)
A.L. Bruce, A. Goel, D.S. Bernstein, Convergence and consistency of recursive least squares with variable-rate forgetting. Automatica 119, 109052 (2020)
J. Chen, F. Ding, Modified stochastic gradient identification algorithms with fast convergence rates. J. Vib. Control 17(9), 1281–1286 (2011)
W. Chen, G. Han, W. Qiu, D. Zheng, Modeling of outlet temperature of the first-stage cyclone preheater in cement firing system using data-driven ARMAX models, in 2019 IEEE 3rd Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC), pp. 472–477 (2019)
F. Ding, Y. Shi, T. Chen, Performance analysis of estimation algorithms of nonstationary ARMA processes. IEEE Trans. Signal Process. 54(3), 1041–1053 (2006)
O. Erkaymaz, Resilient back-propagation approach in small-world feed-forward neural network topology based on Newman–Watts algorithm. Neural Comput. Appl. 32(20), 16279–16289 (2020)
W. Gao, M. L. Zhou, Y. C. Li, T. Zhang, An adaptive generalized predictive control of time varying delay system, in Proceedings of the Second World Conference on Machine Learning and Cybernetics, Xi’an, Shanghai, pp. 878–881 (2004)
L. Guo, Self-convergence of weighted least-squares with applications to stochastic adaptive control. IEEE Trans. Autom. Control 41(1), 79–89 (1996)
L. Guo, H.F. Chen, Identification and Stochastic Adaptive Control. Systems & Control: Foundations & Applications (1991)
J. Herrera, A. Ibeas, M. de la Sen, Identification and control of integrative MIMO systems using pattern search algorithms: an application to irrigation channels. Eng. Appl. Artif. Intell. 26(1), 334–346 (2013)
D. Huang, L. Guo, Estimation of nonstationary ARMAX models based on the Hannan–Rissanen method. Ann. Stat. 1729–1756 (1990)
L. Huang, H. Hjalmarsson, A multi-time-scale generalization of recursive identification algorithm for ARMAX systems. IEEE Trans. Autom. Control 60(8), 2242–2247 (2015)
R. Hübner, A. Schöbel, When is rounding allowed in integer nonlinear optimization? Eur. J. Oper. Res. 237(2), 404–410 (2014)
I.D. Landau, Commande des systèmes-conception, identification et mise en oeuvre. Hermès Sience Publications (2002)
X. Liu, X. Yang, W. Xiong, A robust global approach for LPV-FIR model identification with time-varying time delays. J. Frankl. Inst. 355(15), 7401–7416 (2018)
L. Ljung, System identification in a noise free environment. In Adaptive Systems in Control and Signal Processing 1989, pp. 411–420. Elsevier (1990)
S. Majhi, D. Atherton, Modified smith predictor and controller for processes with time delay. IEEE Proc. Control Theory Appl. 146(5), 359–366 (1999)
A. Messaoud, S. Ben Atia, R. Ben Abdennour, An unknown input multiobserver based on a discrete uncoupled multimodel for uncertain nonlinear systems: experimental validation on a transesterification reactor. ISA Trans. 93, 302–311 (2019)
O. Nelles, Nonlinear System Identification: From Classical Approach to Neural Networks and Fuzzy Models. Springer (2001)
G.C.S. Neto, D.S. Chui, F.P. Martins, A.T. Fleury, F. Furnari, F.C. Trigo, Identification of co emissions dynamics in a natural gas furnace through flame images, ARMAX models, and Kalman filtering. J. Braz. Soc. Mech. Sci. Eng. 43(5), 1–13 (2021)
A. Niederlinski, Theory and practice of recursive identification, the MIT Press, Cambridge, Massachusetts, London, England, 1983. price:£ 45.00. no. of pages: 529. Optim. Control Appl. Methods 6(1), 71–72 (1985)
B. Petschel, K. Soltani Naveh, P. McAree, Convergence properties of the Kalman inverse filter. J. Dyn. Syst. Meas. Control 140(6) (2018)
T. Söderström, P. Stoica, System Identification. Prentice Hall International, Series in Systems and Control Engineering (1989)
H. Wang, L. Xie, Convergence analysis of a least squared algorithm of linear switched identification. J. Control Decis. 7(4), 379–396 (2020)
A.G. Wu, F.Z. Fu, R.Q. Dong, Convergence analysis of weighted stochastic gradient identification algorithms based on latest-estimation for ARX models. Asian J. Control 21(1), 509–519 (2019)
Y. Xiao, F. Ding, Y. Zhou, M. Li, J. Dai, On consistency of recursive least squares identification algorithms for controlled auto-regression models. Appl. Math. Model. 32, 2207–2215 (2008)
L. Xu, F. Ding, Parameter estimation algorithms for dynamical response signals based on the multi-innovation theory and the hierarchical principle. IET Signal Process. 11(2), 228–237 (2016)
L. Yin, H. Gao, Moving horizon estimation for ARMAX processes with additive output noise. J. Frank. Inst. 356(4), 2090–2110 (2019)
L. Yin, S. Liu, H. Gao, Regularised estimation for ARMAX process with measurements subject to outliers. IET Control Theory Appl. 12(7), 865–874 (2018)
Z. Yue, Z. Songzheng, L. Tianshi, Bayesian regularization BP Neural Network model for predicting oil–gas drilling cost, in 2011 International Conference on Business Management and Electronic Information, vol. 2, pp. 483–487. IEEE (2011)
G. Zheng, A. Polyakov, A. Levant, Delay estimation via sliding mode for nonlinear time-delay systems. Automatica 89, 266–273 (2018)
Acknowledgements
This work was supported by the ministry of Higher Education and Scientific Research in Tunisia.
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendices
Appendix
A Round Operator and Rounding Property
Definition 1
Operator round(d) is given by
where int(d) denotes the integer part of d.
Definition 2
We say that a function \(\displaystyle {f:{\mathbb {R}^n} \rightarrow \mathbb {R}}\) has the rounding property if the following holds [17].
For any optimal solution \({x^*}\) to the continuous relaxation (CP) of integer nonlinear unrestricted optimization problem: \(\displaystyle { \min \left\{ {f(x):x \in {\mathbb {R}^n}} \right\} } \) there exists an optimal solution x of (IP): \(\displaystyle { \min \left\{ {f(x):x \in {\mathbb {Z}^n}} \right\} }\) such that
Notes that rounding the known optimal solution x of the continuous relaxation (CP) yield an optimal solution for an integer problem (IP) in case where \(n = 1\) and the objective function f(.) is convex [17].
1.1 B The Computation Expression of \(\bar{\rho }_k\)
Let us consider
In the same way, to appear the estimated generalized vector parameters \({{\hat{\vartheta }}}\) and the generalized vector parameters \({{\vartheta }}\), we added and subtracted each element of Eq. (57), the appropriate term
Adding and subtracting the term \(\displaystyle {{\vartheta }_{k}\phi _k ({{\hat{\vartheta }}})}\) from (58), we obtain
where
Hence,
So,
where
Rights and permissions
Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Bedoui, S., Abderrahim, K. Convergence Analysis of Forgetting Factor Least Squares Algorithm for ARMAX Time-Delay Models. Circuits Syst Signal Process 42, 405–430 (2023). https://doi.org/10.1007/s00034-022-02128-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00034-022-02128-x