A Two-Stage Online Prediction Method for a Blast Furnace Gas System and Its Application

Abstract

The byproduct gas in steel industry is one of the most significant energy resources of an enterprise. Due to the large quantity of yield, fluctuation, and various categories of users encountered in a blast furnace gas (BFG) system, it is very difficult to accurately predict the amount of gas to be generated and forecast the users' consumption demand. In this paper, a two-stage online prediction method based on an improved echo state network (ESN) is proposed to realize forecasting in the BFG system. In this method, one completes the prediction realized at the levels of BFG generation and consumption using a class of ESN with input compensation and parameter optimization. At the second stage, to predict gas holder level of the BFG system, the energy flows being predicted at the first stage are denoised, and their correlation with the holder level are determined by using a concept of grey correlation with time delay. Then the effect factors exhibiting high correlation levels are extracted to construct the model of the gas holder. The prediction system designed in this manner is applied in the Energy Center of Baosteel Co., Ltd, China. The results demonstrate that the prediction system exhibits high accuracy and can provide an effective guidance for balancing and scheduling of the byproduct energy.