In recent years, extensive works on genetic algorithms have been reported covering various applications. Genetic algorithms (GAs) have received significant interest from researchers and have been applied to various optimization problems. They offer many advantages such as global search characteristics, and this has led to the idea of using this programming method in modelling dynamic non-linear systems. In this paper, a methodology for model structure selection based on a genetic algorithm was developed and applied to non-linear discrete-time dynamic systems. First the effect of different combinations of GA operators on the performance of the model developed is studied. A proposed algorithm called modified GA, or MGA, is presented and a comparison between a simple GA and a modified GA is carried out. The performance of the proposed algorithm is also compared to the model developed using the orthogonal least squares (OLS) algorithm. The adequacy of the developed models is tested using one-step-ahead prediction and correlation-based model validation tests. The results show that the proposed algorithm can be employed as an algorithm to select the structure of the proposed model.
BillingsS. A.Identification of nonlinear systems: A survey. Proc. Instn Electl Engrs, Part D, 1980, 127 (6), 272–284.
3.
HaberR.KeviczkyL.Identification of Nonlinear Dynamic Systems, Identification and System Parameter Estimation (Ed. Rajbman), 1978 (North-Holland, Amsterdam, The Netherlands).
4.
JacobyS. L. S.KowalikJ. S.PizzoJ. T.Iterative Methods for Non-linear Optimization Problem, 1972 (Prentice-Hall, Englewood Cliffs, New Jersey).
5.
BackT.HammelU.SchwefelH. P.Evolutionary computation: Comments on the history and current state. IEEE Trans. Evolutionary Comput., 1997, 1 (1), 15–28.
6.
HollandJ. H.Adaptation in Natural and Artificial Systems, 1975 (University of Michigan Press, Ann Arbour, Michigan).
7.
GoldbergD. E.Genetic Algorithms in Search, Optimization and Machine Learning, 1989 (Addison-Wesley, Reading, Massachusetts).
KristinssonK.DumontG. A.System identification and control using genetic algorithms. IEEE Trans. Systems, Man and Cybernetics, 1992, 22 (5), 1033–1046.
10.
ZiboZ.NaghdyF.Application of genetic algorithms to system identification. In Proceedings of IEEE International Conference onEvolutionary Computation, 1995, Vol. 2, pp. 777–787.
11.
TanK. C.LiY.Murray-SmithD. J.SharmanK. C.System identification and linearisation using genetic algorithms with simulated annealing. In Proceedings of the First IEE/IEEE International Conference onGenetic Algorithms in Engineering System: Innovations and Application, 1995, pp. 164–169.
12.
JeongI. K.LeeJ. J.Adaptive simulated annealing genetic algorithm for system identification. Enging Applic. Artif. Intel., 1996, 9 (5), 523–532.
13.
ShetaA. F.De JongK.Parameter estimation of nonlinear systems in noisy environments using genetic algorithms. In Proceedings of the IEEE International Symposium onIntelligent Control, Dearborn, Michigan, 15–18 September, 1996, pp. 360–365.
14.
HongX.BillingsS. A.Parameter estimation based on stacked regression on evolutionary algorithms. IEE Proc. Control Theory and Applic., 1999, 146 (5), 406–414.
15.
HaberR.UnbehauenH.Structure identification of nonlinear dynamics systems—a survey on input/output approaches. Automatica, 1990, 26 (4), 651–677.
16.
DesrochersA.MohseniS.On determining the structure of a non-linear system. Int. J. Control, 1984, 40 (5), 923–938.
17.
VeresS. M.Structure Selection of Stochastic Dynamic Systems, 1990 (Gordon and Breach, New York).
18.
ChenS.BillingsS. A.LuoW.Orthogonal least square methods and their application to non-linear system identification. Int. J. Control, 1989, 50 (5), 1873–1896.
19.
LiC. J.JeonY. C.Genetic algorithm in identifying nonlinear auto regressive with exogenous input models for nonlinear input models for nonlinear systems. In Proceedings of the American Control Conference, San Francisco, California, 1993, pp. 2305–2309.
20.
KorenbergM.BillingsS.A.LiuY. P.McIlroyP. J.Orthogonal parameter estimation algorithm for non-linear stochastic systems. Int. J. Control, 1988, 48 (1), 193–210.
21.
LjungL.System Identification Theory for the User, 1999 (Prentice-Hall, Englewood Cliffs, New Jersey).
22.
ChenS.BillingsS. A.Representations of non-linear systems: The NARMAX model. Int. J. Control, 1989, 49 (3), 1013–1032.
23.
TsangK. M.Spectral analysis for nonlinear systems. PhD thesis, University of Sheffield, 1988.
24.
ChenS.BillingsS. A.LuoW.Orthogonal least square methods and their application to non-linear system identification. Int. J. Control, 1989, 50 (5), 1873–1896.
25.
GrefenstetteJ. J.Optimization of control parameters for genetic algorithms. IEEE Trans. Systems, Man and Cybernetics, 1986, 16 (1), 122–128.
26.
QingshengR.JinZ.ZhongxingY.Analysis of common genetic operators. In Proceedings of the 5th International Conference onSignal Processing, 2000, 1684–1687.
27.
EshelmanL. J.CarunaR. A.ShafferJ. D.Biases in crossover landscape. In Proceedings of the Third International Conference onGenetic Algorithms (Ed. SchafferJ.), 1989, pp. 10–19 (Morgan Kaufman, Los Altos, California).
28.
SyswerdaG.Uniform crossover in genetic algorithms. In Proceedings of the Third International Conference onGenetic Algorithms (Ed. SchafferJ.), 1989, pp. 2–9 (Morgan Kaufman, Los Altos, California).
29.
YupingW.HailinL.LeungY.-W.An effective uniform genetic algorithm for hard optimization problems. In Proceedings of the 3rd World Congress onIntelligent Control and Automation, 28 June-2 July, 2000, pp. 656–660.
30.
FogelD. B.Evolutionary optimization. In Proceedings of the 1992 Conference Record of the Twenty-Sixth Asilomar Conference onSignals, Systems and Computers, 1992, Vol. 1, No. 1, pp. 409–414.
31.
HusseinS. B.JamaluddinH.MailahM.ZalzalaA. M. S.A hybrid intelligent active force controller for robot arms using evolutionary neural networks. In Proceedings of the 2000 Congress onEvolutionary Computation, 2000, Vol. 1, pp. 117–124.
32.
PapadapoulousS.MackR. J.MassaraR. E.A hybrid genetic algorithms method for optimizing analog circuits. In Proceedings of the 43rd IEEE Symposium onCircuits and Systems, Lansing, Michigan, 8–11 August 2000, pp. 140–143.
33.
BillingsS. A.VoonW. S. F.Correlation based model validity tests for non-linear models. Int. J. Control, 1986, 44 (1), 235–244.
34.
LuhG. C.WuC. Y.Non-linear system identification using genetic algorithms. Proc. Instn Mech. Engrs, Part I: J. Systems and Control Engineering, 1999, 213 (12), 105–118.
35.
BoxG. E. P.JenkinsG. M.ReinselG. C.Time Series Analysis Forecasting and Control, 1994 (Prentice-Hall, Englewood Cliffs, New Jersey).
