×

A linear programming approach to online set membership parameter estimation for linear regression models. (English) Zbl 1362.93148

Summary: This paper presents a new technique for online set membership parameter estimation of linear regression models affected by unknown-but-bounded noise. An orthotopic approximation of the set of feasible parameters is updated at each time step. The proposed technique relies on the solution of a suitable linear program, whenever a new measurement leads to a reduction of the approximating orthotope. The key idea for preventing the size of the linear programs from steadily increasing is to propagate only the binding constraints of these optimization problems. Numerical studies show that the new approach outperforms existing recursive set approximation techniques, while keeping the required computational burden within the same order of magnitude.

MSC:

93E10 Estimation and detection in stochastic control theory
93C05 Linear systems in control theory
90C05 Linear programming
62J05 Linear regression; mixed models

Software:

CPLEX
PDFBibTeX XMLCite
Full Text: DOI

References:

[1] Ljung, System Identification: Theory for the User (1999) · Zbl 0615.93004 · doi:10.1002/047134608X.W1046
[2] Åström, Adaptive Control (2013)
[3] Isermann, Fault-Diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance (2006) · doi:10.1007/3-540-30368-5
[4] Bertsekas, Recursive state estimation for a set-membership description of uncertainty, IEEE Transactions on Automatic Control 16 pp 117– (1971) · doi:10.1109/TAC.1971.1099674
[5] Schweppe, Uncertain Dynamic Systems (1973)
[6] Kurzhanski, From Data to Model pp 135– (1989) · doi:10.1007/978-3-642-75007-6_4
[7] Walter, Estimation of parameter bounds from bounded-error data: a survey, Mathematics in Computer and Simulation 32 pp 449– (1990) · doi:10.1016/0378-4754(90)90002-Z
[8] Milanese, Estimation theory for nonlinear models and set membership uncertainty, Automatica 27 pp 403– (1991) · Zbl 0729.93074 · doi:10.1016/0005-1098(91)90090-O
[9] Special issue on: Bounded-error estimation - part 1, International Journal of Adaptive Control and Signal Processing 8 (1) pp 1– (1994)
[10] Special issue on: Bounded-error estimation - part 2, International Journal of Adaptive Control and Signal Processing 9 (1) pp 1– (1995)
[11] Milanese, Bounding Approaches to System Identification (1996) · doi:10.1007/978-1-4757-9545-5
[12] Special issue on: The set membership modelling of uncertainties in dynamical systems, Mathematical and Computer Modelling of Dynamical Systems 11 (2) pp 123– (2005) · Zbl 1080.93502 · doi:10.1080/13873950500067296
[13] Special issue on: Bounding methods for state and parameter estimation, International Journal of Adaptive Control and Signal Processing 25 (3) pp 189– (2011) · doi:10.1002/acs.1232
[14] Cheng Y Wang Y Sznaier M Ozay N Lagoa C A convex optimization approach to model (in)validation of switched ARX systems with unknown switches Decision and Control (CDC), 2012 IEEE 51st Annual Conference on Maui (Hawaii) 2012 6284 6290
[15] Ozay, Convex certificates for model (in)validation of switched affine systems with unknown switches, IEEE Transactions on Automatic Control 59 (11) pp 2921– (2014) · Zbl 1360.93080 · doi:10.1109/TAC.2014.2351714
[16] Ozay, Set membership identification of switched linear systems with known number of subsystems, Automatica 51 pp 180– (2015) · Zbl 1309.93048 · doi:10.1016/j.automatica.2014.10.101
[17] Cerone, Bounded error identification of Hammerstein systems through sparse polynomial optimization, Automatica 48 (10) pp 2693– (2012) · Zbl 1271.93161 · doi:10.1016/j.automatica.2012.06.078
[18] Cerone, Computational load reduction in bounded error identification of Hammerstein systems, IEEE Transactions on Automatic Control 58 (5) pp 1317– (2013) · doi:10.1109/TAC.2012.2223334
[19] Cerone, A unified framework for solving a general class of conditional and robust set-membership estimation problems, IEEE Transactions on Automatic Control 59 (11) pp 2897– (2014) · Zbl 1360.93330 · doi:10.1109/TAC.2014.2351695
[20] Casini, Input design in worst-case system identification with quantized measurements, Automatica 48 (12) pp 2997– (2012) · Zbl 1255.93045 · doi:10.1016/j.automatica.2012.08.016
[21] Casini, Feasible parameter set approximation for linear models with bounded uncertain regressors, IEEE Transactions on Automatic Control 59 (11) pp 2910– (2014) · Zbl 1360.93179 · doi:10.1109/TAC.2014.2351855
[22] Cerone, A convex relaxation approach to set-membership identification of LPV systems, Automatica 49 (9) pp 2853– (2013) · Zbl 1364.93824 · doi:10.1016/j.automatica.2013.05.028
[23] Pshenichnyi, Minimax approach to the estimation of linear regression parameters, Engineering Cybernetics 21 (2) pp 77– (1983)
[24] Belforte, Two new estimation algorithms for linear models with unknown but bounded measurement noise, IEEE Transactions on Automatic Control 38 (8) pp 1273– (1993) · Zbl 0784.93035 · doi:10.1109/9.233166
[25] Cerone, Improved parameters bounds for set-membership EIV problems, International Journal of Adaptive Control and Signal Processing 25 (3) pp 208– (2011) · Zbl 1222.93054 · doi:10.1002/acs.1218
[26] Fogel, On the value of information in system identification - bounded noise case, Automatica 18 pp 229– (1982) · Zbl 0433.93062 · doi:10.1016/0005-1098(82)90110-8
[27] Belforte, Parameter estimation algorithms for a set-membership description of uncertainty, Automatica 26 pp 887– (1990) · Zbl 0701.93092 · doi:10.1016/0005-1098(90)90005-3
[28] Deller, Unifying the landmark developments in optimal bounding ellipsoid identification, International Journal of Adaptive Control and Signal Processing 8 (1) pp 43– (1994) · Zbl 0800.93256 · doi:10.1002/acs.4480080105
[29] Vicino, Sequential approximation of feasible parameter sets for identification with set membership uncertainty, IEEE Transactions on Automatic Control 41 pp 774– (1996) · Zbl 0867.93026 · doi:10.1109/9.506230
[30] Chisci, Block recursive parallelotopic bounding in set membership identification, Automatica 34 (1) pp 15– (1998) · Zbl 0908.93021 · doi:10.1016/S0005-1098(97)00160-X
[31] Kostousova, State estimation for dynamic systems via parallelotopes optimization and parallel computations, Optimization Methods and Software 9 (4) pp 269– (1998) · Zbl 0919.93017 · doi:10.1080/10556789808805696
[32] Bravo, Bounded error identification of systems with time-varying parameters, IEEE Transactions on Automatic Control 51 (7) pp 1144– (2006) · Zbl 1366.93121 · doi:10.1109/TAC.2006.878750
[33] Blesa, Identification for passive robust fault detection using onotope-based set-membership approaches, International Journal of Adaptive Control and Signal Processing 25 (9) pp 788– (2011) · Zbl 1234.93105 · doi:10.1002/acs.1242
[34] Casini, On worst-case approximation of feasible system sets via orthonormal basis functions, IEEE Transactions on Automatic Control 48 (1) pp 96– (2003) · Zbl 1364.93154 · doi:10.1109/TAC.2002.806658
[35] Ferreres, Estimation of output error models in the presence of unknown but bounded disturbances, International Journal of Adaptive Control and Signal Processing 11 (2) pp 115– (1997) · Zbl 0872.93020 · doi:10.1002/(SICI)1099-1115(199703)11:2<115::AID-ACS426>3.0.CO;2-4
[36] Karmarkar, A new polynomial-time algorithm for linear programming, Combinatorica 4 (4) pp 373– (1984) · Zbl 0557.90065 · doi:10.1007/BF02579150
[37] Boyd, Convex Optimization (2004) · doi:10.1017/CBO9780511804441
[38] Casini M Garulli A Vicino A A constraint selection technique for recursive set membership identification Proc. of 19th IFAC World Congress Cape Town, South Africa 2014 1790 1795
[39] Broman, A compact algorithm for the intersection and approximation of n-dimensional polytopes, Mathematics and Computers in Simulation 32 pp 469– (1990) · doi:10.1016/0378-4754(90)90003-2
[40] Blesa, Robust fault detection using polytope-based set-membership consistency test, IET Control Theory Applications 6 (12) pp 1767– (2012) · doi:10.1049/iet-cta.2010.0610
[41] IBM IBM ILOG Cplex Optimizer http://www-01.ibm.com/software/integration/optimization/cplex-optimizer/
[42] Casini M Garulli A Vicino A A constraint selection technique for set membership estimation of time-varying parameters Proc. of 53rd IEEE Conference on Decision and Control Los Angeles, CA 2014 1029 1034
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.