基于模糊线性规划对钢水脱氧合金化配料方案的优化研究  

Optimization of the dosing scheme for deoxidized alloying of molten steel based on fuzzy programming

作　　者：张天圆 朱家明[1] 汪惠玉 汪雯清 ZHANG Tianyuan;ZHU Jiaming;WANG Huiyu;WANG Wenqing(School of Statistics and Applied Mathematics,Anhui University of Finance and Economics Bengbu 233030,China;School of Accounting,Anhui University of Finance and Economics,Bengbu 233030,China)

机构地区：[1]安徽财经大学统计与应用数学学院,安徽蚌埠233030 [2]安徽财经大学会计学院,安徽蚌埠233030

出　　处：《青海大学学报》2019年第5期73-81,共9页Journal of Qinghai University

基　　金：国家自然科学基金项目(11601001);安徽省教学研究项目(2018jyxm1305)

摘　　要：为了确定炼钢中的脱氧合金化的优化方案,减少合金材料消耗的经济成本,通过建立元素收得率模型,并采用遗传算法优化阈值和权值的BP神经网络模型对元素收得率进行预测,然后以三角模糊数确定的隶属函数,构建模糊线性规划模型来计算出合理的材料添加量。结果表明:筛选出的合金配料方案比原先方案节约17.23%的经济成本,对炼钢生产中提高钢种品质和节约生产成本具有一定的参考价值。In order to determine the optimal dosing scheme for deoxidation alloying in steelmaking and reduce the economic cost of alloy material consumption,the elemental yield model was built,and the BP neural network model with genetic algorithm was applied to optimize the threshold and weight to predict the element yield. The membership function determined by the triangular fuzzy number was used to construct the fuzzy linear programming model to calculate the reasonable material addition amount. The optimized alloying scheme saves 17.23% economic cost compared with the original scheme,and has certain reference value for improving steel quality and saving production cost in steelmaking production.

关 键 词：脱氧合金化 元素收得率 BP神经网络 模糊规划 MATLAB 

分 类 号：TF711[冶金工程—钢铁冶金] TF721