This work presents an approach to predict the low frequency and wave frequency responses (LFR and WFR) of a floating structure using Kalman smoother adaptive filters based time domain Volterra model. This method utilized time series of a measured wave height as system input and surge motion as system output and used to generate the linear and nonlinear transfer function (TFs). Based on those TFs, predictions of surge motion in terms of LFR and WFR were carried out in certain frequency ranges of wave heights. The applicability of the proposed method is then applied in a scaled 1:100 model of a semisubmersible prototype. © (2014) Trans Tech Publications, Switzerland.