In this paper, multichannel Kalman filters for estimation of offshore platform (OP) coordinates are designed. The complete OP motion is assumed to be composed of the low-frequency motion caused by the wind and undercurrent, and the high-frequency motion caused by the sea. The mathematical model of the low-frequency OP motion is given by the normal differential equation system, and the high-frequency OP motion is represented by a moving-average multivariable autoregression model. The parameter estimation problem for the model of the low-frequency OP motion, on which the in-service control is performed, is solved through two jointly operating Kalman filters: the first one is for the estimation of the parameters of the low-frequency motion model, and the second one is for the parameter estimation for the high-frequency model. The parameters of the first filter are automatically adapted to variations of the second filter, i.e., they are adapted to disturbances from the sea. Two algorithms for the OP motion parameter estimation (parallel and with preliminary data compression), employed for several measuring channels data estimation, are developed, and simulated on a computer. Some recommendations on their use are given. (C) 2003 ISA-The Instrumentation, Systems, and Automation Society.