Interval prediction of sinter screening index based on gate recurrent unit and kernel density estimation algorithm

Abstract

Since there are many uncertain factors in the actual production process, reliable information cannot be obtained from point prediction results. Therefore, this paper proposes an interval prediction method to evaluate the screening index. Firstly, feature engineering algorithms are used to select the most suitable data and variables for modeling. Secondly, based on the sequential characteristics of the sintering process, the gated cycle unit (GRU) model is used to make point predictions on the indicators. then the kernel density estimation (KDE) algorithm is used to quantify the error of the index to obtain the interval prediction results, and the RandomizedSearchCV algorithm is used to optimize the parameters of the model. Finally, comparison shows that the GRU model has higher point prediction accuracy, and the KDE algorithm can better quantify the prediction error, and then obtain reliable interval prediction results. This method has guiding significance for the high-quality production of sinter.