基于粒子群算法的钢水脱氧合金化配料的优化研究  

Particle Swarm Optimization Algorithm Based on the Optimization of Molten Steel Deoxidation Alloying Batching

作　　者：朱丽平[1] ZHU Liping(Xi’an Aeronautical Polytechnic Institute,Xi'an 710089,China)

机构地区：[1]西安航空职业技术学院,陕西西安710089

出　　处：《工业加热》2021年第10期28-30,共3页Industrial Heating

摘　　要：目前大多数的钢铁企业在脱氧合金化冶炼过程中,均按照不同元素的固定收得率或者是经验值来计算各合金的加入量,其特点是效率差、准确率低.因此对脱氧合金化过程中,当前炉次的合金配料进行自动优化以及成本的精准把控尤为重要.通过建立了基于粒子群优化的多目标规划模型,得到了不同钢种的合金配料方案,并随机抽取了30组完整数据对模型进行检验,结果显示模型可在保证钢材质量的前提下,有效降低配料成本。At present,most iron and steel enterprises calculate the addition amount of each alloy according to the fixed yield or experience value of different elements in Deoxidation alloying smelting process,which is characterized by low efficiency and low accuracy.Therefore,it is very important to optimize the alloy burden and control the cost.By establishing a multi objective programming model based on Particle swarm optimization,the alloy proportioning schemes of different steel grades were obtained,and 30 sets of complete data were randomly selected to test the model,the results show that the model can effectively reduce the burden cost under the premise of guaranteeing the quality of steel.

关 键 词：RBF神经网络 转炉终点 粒子群优化 合金配料 

分 类 号：TF713.6[冶金工程—钢铁冶金] O29[理学—应用数学]