Accuracy Analysis of Polynomial Model and Auto Regressive Model for Data-driven Fault Detection

The key of data-driven fault detection method lies in the full and effective understanding of the detected data, and the fitting for the detected data is an effective means to realize the parameterization of the data model. In this paper, the polynomial model and the autoregressive model are used to estimate and predict the non-stationary data and the stationary data respectively, so as to achieve the data-driven fault detection. The estimation accuracy of the parameter model is analyzed. The relationship between the prediction accuracy and the prediction duration, the polynomial fitting window, the fitting order are given theoretically. Finally, numerical simulation results are given, which can provide some support for data-driven fault detection to some extent.