Nonlinear model identification of an experimental ball-and-tube system using a genetic programming approach

Prediction and simulation errors in parameter estimation for nonlinear systems

“…Because the model parametersâ s andb s were estimated by minimising MSEðyÀŷ s Þ, it is natural to compareŷ s in (16) with y in (13). Because the model structure is the same in this case, minimisation of MSEðyÀŷ s Þ will be unbiased, as verified in some of the examples in the paper.…”

“…Evolutionary algorithms (EA) seem to be a natural choice to solve MOPs since they can find multiple solutions in one simulation run and are able to solve complex problems being less susceptible to those involving discontinuities and multimodality [24] and more recently have been applied to NARX (Nonlinear AutoRegressive with eXogenous input) model identification [25,14,16].…”

“…On the other hand, if the parameters should be estimated by minimising MSEðyÀŷ s Þ, we should then compare the regressors in the model (16) with the data as produced by the model. Assuming the ideal case in whichŷ s ¼ỹ we should then compare (16) with (23).…”

“…GAs as optimisation tools have been used to great advantage in other studies on system identification [12][13][14][15][16][17]. It is worth pointing out that in such references only prediction error was used in the fitness function.…”

Yapay Ari Koloni̇si̇ Algori̇tmasi İle Opti̇mi̇ze Edi̇len Hammerstein Model Kullanarak Si̇stemleri̇n Ki̇mli̇klendi̇ri̇lmesi̇

“…Autoregressive, Autoregressive Moving Average (ARMA) models or finite impulse response (FIR) and infinite impulse response (IIR) models are used for linear system identification in literature. Also Volterra, Bilinear and polynomial autoregressive (PAR) models are used for nonlinear system identification [15][16][17][18][19][20][21][22][23][24][25].…”