An Intelligent Control Scheme for Burn-Through Point to Carbon Efficiency Optimization in Iron Ore Sintering Process

Abstract

The sintering process is an important step of preparing raw material for iron and steel smelting. It is a series of complex physico-chemical changes with high energy consumption, high pollution and large CO 2 emissions. How to reduce carbon consumption while ensuring the quality and yield of sinter ore are the problems to be solved urgently. In this paper, An intelligent control scheme for burn-through point (BTP) to carbon efficiency optimization in iron ore sintering process is presented. The comprehensive coke ratio is employed as a measure of carbon efficiency; and the BTP, a measure of the stability of the sintering process. First, a model is established to predict the comprehensive coke ratio using a back propagation neural network, and the carbon efficiency is optimized using the particle swarm optimization algorithm. This yields an optimal strand velocity. Then, the control of the BTP is taken into consideration using an expert-fuzzy control strategy. This yields another strand velocity. Finally, these two kinds of strand velocity are integrated using the fuzzy satisfaction method to produce a control input for the strand velocity. It not only improves the carbon efficiency, but also ensures the stable running of the sintering process. Part of the strategy was tested in an actual plant, and the results show the effectiveness of the scheme.