A method of modeling for nonlinear process dynamics using the discrete volterra series model has been developed. It involves the parameter estimation of a volterra series model by an adaptive digital filter method and calculation of several IAEs between process output and model output in sequentially combinating a volterra series structured order and input series order. The optimum structure of a volterra series model which has minimum IAE is determined by comparing with several IAEs. It was applied to the bottom temperature control loop of the demethanizer distillation column in an ethylene plant to confirm the design philosophy. The actual result indicates that the proposed method in this study has the advantage of modeling for nonlinear process dynamics.