Abstract: Multivariable nonlinear dynamic processes can generally be descreibed as the nonlinear ARMAX models. In this paper, we present a new algorithm for model structure determination and parameter estimation of this sort of system. The structure and parameters can be obtained simultaneously and recursively. It is based on the "innovation" idea and certain information criteria, Using the technique of matrix operation, it is possible to combine innovation calculation with structure determination and parameters estimation. The amount of computation is thus reduced considerably. This procedure assures the optimal system description be obtained. The identification of a simulated system shows the correctness and effectiveness of this new algorithm.