In this paper, a two-tier model-based fault detection and diagnosis method for a distillation column is developed. It employs the nonlinear model developed earlier to monitor the distillation process and a corresponding linear model to identify an abnormal source when large deviations of measured values occur. The inner distillation fault parameters are estimated through linear least-square method based on the linear model. The proposed method is applied to the stripping tower in the Tennessee Eastman process simulator. Case studies demonstrate that the two-tier diagnosis structure effectively captures the variation of fault parameters and is more efficient than a pure nonlinear model-based structure.