Track/vehicle system identification by a revised group method of data handling (GMDH)
Toshio Yoshimura, Desh Deepak, Hitoshi Takagi · International Journal of Systems Science · 1985
This paper is devoted to the identification of a track/vehicle system of Indian Railways. The model is assumed to be completely unknown except for the sequences of input and output. The model structure is determined using a revised group method of data handling (GMDH) algorithm which is based on Akaike's information criterion (AIC) as a criterion to select the optimal partial descriptions. Numerical results show that the model identification by the proposed method is effective.