Research on the pulverized coal injection decision based on multi-objective optimization of blast furnace

In order to reduce the energy consumption and carbon emission in the blast furnace ironmaking and save the cost, a multi-objective optimization scheme based on the pulverized coal injection is proposed. With the pulverized coal injection as the decision variable, fuel ratio and pulverized coal ratio are the optimization target, the bosh gas index and hourly iron production are the constraint condition. A multi-objective planning model was built based on convolutional neural network and long short term memory network with attention mechanism. At the same time, the temperature index of center and edge coal gas and its ratio were used to monitor the state of blast furnace, the NSGA-II-DE algorithm was used to find the Pareto optimal solution of the model. The results show that under the premise of ensuring the smooth running and production capacity of the blast furnace, the optimal pulverized coal injection made out, greatly reducing ironmaking energy consumption and carbon emissions. The average energy saving is about 5.23×10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">11</sup> KJ/ year and the CO<inf xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</inf> emission reduction is about 4.41×10<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">4</sup> t/ year, and the annual cost reduction is about 91 million yuan/year. The scheme has certain guiding significance for the actual production of blast furnaces.