基于燃料比最优的高炉喷煤设定值多目标优化

为了降低高炉炼铁的能耗,节约成本,将高炉炼铁过程信息、专家经验与智能模型相结合,提出基于燃料比最优的高炉喷煤设定值多目标优化方案。以燃料比最优为优化目标,炉温预测指标为约束条件,喷煤量为决策变量,采用基于K-均值聚类的径向基神经网络建立多目标优化模型,并通过基于NSGA-Ⅱ算法的多目标优化方法,获取尽可能使多个目标同时达到最优的Pareto最优解。结果表明,该优化方案可以在保证炉温良好的前提下,决策出使燃料比达到最优的喷煤设定值,大大降低能耗,节约成本。不仅为高炉实际生产提供操作指导,也为高炉冶炼的优化运行奠定了基础。

Multi-objective Optimization of Blast Furnace Coal Injection Setting Based on Optimal Fuel Ratio

In order to reduce the energy consumption and cost of blast furnace ironmaking, the blast furnace ironmaking process information, expert experience and intelligent model are combined to propose a multi-objective optimization research plan of blast furnace coal injection setting based on optimal fuel ratio.Using the data information of the blast furnace ironmaking process, the fuel ratio as the optimal target, the furnace temperature prediction index as the constraint condition, the coal powder quantity as the decision variable, the radial basis neural network based on K-means clustering was used to establish the multi-objective optimization model, and the multi-objective optimization method based on NSGA-II algorithm was used to obtain the Pareto optimal solution that maximizes multiple targets at the same time. The results show that under the premise of ensuring good furnace temperature, the optimization scheme can determine the coal injection setting value to optimize the fuel ratio, which greatly reduces energy consumption and saves cost. It not only provides operational guidance for the actual production of blast furnaces, but also lays the foundation for the lower adjustment of blast furnace ironmaking.