Research on Blast Furnace Gas Flow Prediction Method Based on LSTM

Abstract

The reliability prediction of time series of blast furnace gas flow is beneficial to the stable running of blast furnace condition. Aiming at the problem of gas flow time series prediction, this paper proposes a single-step prediction and multi-step prediction based on LSTM algorithm. Firstly, the original data is preprocessed, such as outlier processing and denoising processing of Fourier Transform, so as to reduce the prediction error. Secondly, it will finish single-step prediction and multi-step prediction by adopting LSTM algorithm. Finally, it evaluates the performance of LSTM prediction model. The experiments show that the accuracy of LSTM prediction is high, but the single-step prediction takes a long time; however, in the process of blast furnace gas flow prediction, the time parameter is an indispensable characteristic. Considering comprehensively, the LSTM multi-step prediction shows a better prediction effect, which provides a reliable reference for the stable operation of blast furnace.