基于粒子群算法的水泥烧成系统成本优化控制  

Cost Optimal Control of Cement Sintering System Based on Particle Swarm Algorithm

作　　者：朱贺 刘传玉 汪峥[1] 张成伟 

机构地区：[1]东南大学自动化学院,江苏南京210096 [2]南京凯盛国际工程有限公司,江苏南京210036

出　　处：《工业控制计算机》2022年第10期124-126,130,共4页Industrial Control Computer

摘　　要：在水泥烧成系统中,游离氧化钙(f-CaO)是衡量水泥熟料质量的重要检测指标。针对实际生产中人工采样化验实时性差的问题,采用支持向量机(SVM)的软测量方法建立了游离氧化钙的预测模型。在此基础上,以游离氧化钙和主要过程指标作为约束,以最大化产量和最小化能耗为目标,建立了水泥烧成系统成本优化数学模型,并借助粒子群算法求解实时控制量。软测量模型可以及时反映生产工况,实时控制量可以更好地指导中控室人员进行操作,以确保产品质量,提高经济效益。Free Calcium Oxide(f-CaO) is an important detection indicator to measure the clinker quality in the cement sintering system. Aiming at the problem of poor real-time performance of manual sampling in actual production, the soft-sensor method of support vector machine(SVM) is used to establish the prediction model of f-CaO in this paper. On this basis,taking f-CaO and main process indicators as constraints, maximizing output and minimizing energy consumption as target, a cost optimization mathematical model of cement sintering system is established. The particle swarm optimization algorithm is used to solve the real-time control variable. Soft-sensor model can reflect production conditions in time.

关 键 词：游离氧化钙 支持向量机 软测量 成本优化 粒子群算法 

分 类 号：TQ172.62[化学工程—水泥工业] TP18[化学工程—硅酸盐工业]