Practical Application of Model Identification based on ARX Models with Transfer Functions

A novel method for identification of ARX models based on transfer functions has been proposed. The identification approach converts transfer functions to ARX models with no approximation, except for zero-order hold. Model parameters of the transfer functions are estimated directly. To achieve high performance in process control, especially in MPCs, identification of process model is of great importance. However, step testing for model identification is a time-consuming task. Model identification techniques are necessary to save time for step tests. Therefore, a closed-loop identification method of multi-variable systems is useful and helpful for time-saving. In this paper, the proposed method was extended to a closed-loop identification technique and is applied to an industrial chemical plant.