Prediction and scheduling for blast furnace gas generation based on time series feature extraction

Due to the significant time lag and under-regulation, predicting the blast furnace gas generation and formulating its scheduling strategy is complex. This paper proposes a blast furnace gas generation prediction method based on time series feature extraction and designs a blast furnace gas scheduling strategy based on the prediction results. Firstly, Pearson correlation analysis is used to identify the parameters that have a significant correlation with the blast furnace gas generation, and the selected parameters are decomposed into several intrinsic mode components with different frequency characteristics using the complete ensemble empirical mode decomposition; Then, the principal component analysis method is used to extract the principal components of several intrinsic modal components, and these principal components are employed as the inputs of long short-term memory neural network to predict the blast furnace gas generation; Finally, according to the prediction results designs the scheduling strategy of blast furnace gas. The experiment and contrast experiments are carried out with the industrial field data, and experimental results illustrate that the proposed method is correct and effective.