Prediction of FeO Content in Sintering Process Based on Heat Transfer Mechanism and Data-driven Model

摘要

The FeO content in sinter is one of the important indexes for evaluating the quality of sinter. However, due to the high temperature and harsh environments, which makes the FeO content cannot be detected online in real time. To solve this problem, a method combining heat transfer mechanism and data-driven model is proposed to realize online prediction of FeO content. Firstly, a temperature distribution mechanism model of sintering process is established, in which the sinter is divided into three categories by the maximum temperature. Then, three long short-term memory models are constructed under different conditions to predict the FeO content respectively. The validity and feasibility of the proposed model are verified by a sintering plant application, and the prediction results can provide reliable FeO content information for the sintering site.