Abstract: Development of suitable nonlinear model is the critical step in the application of nonlinear model based controllers to distillation column. Selecting the proper model structure to capture the data relation in terms of regressors is the important aspect in nonlinear modeling. In this study, the wavenet based Nonlinear Auto-regressive with Exogenous inputs (NARX) model is developed using input and output regressors. The model validation and regressor analysis shown that the selected regressors have the potential of capturing the nonlinearity of the process.