基于LS-SVM的烧结矿化学成分软测量模型研究与应用  

Research and Application of Soft Sensoring Model of Chemical Composition in Sintering Process Based on LS-SVM

作　　者：宋强[1] 王爱民[2] 

机构地区：[1]安阳工学院机械工程系,河南安阳455000 [2]安阳师范学院计算机与工程学院,河南安阳455000

出　　处：《计算机测量与控制》2009年第11期2134-2136,2144,共4页Computer Measurement &Control

摘　　要：由于烧结过程所具有的大时滞性和动态时变性,采取一些依赖于对象数学模型的传统控制理论和方法难以解决烧结矿化学成分的波动问题;因此,烧结矿化学成分的预测和控制长期以来一直是钢铁企业中的一个难点;为此,根据烧结过程所具有的特点,提出了基于最小二乘支持向量机的烧结矿化学成分的软测量模型的研究,利用支持向量机建立烧结矿化学成分的预报模型;通过对现场实际数据进行仿真表明,该方法鲁棒性强,准确性高,泛化能力广,具有很强的实用性和推广价值。Since the sintering process often has large time delay and dynamic time--varilability, it is hard to perform control tasks of total sintering process by using conventional control models. This problem has been considered as one of the key difficulties in the production process of steel enterprises. Prediction models of sintering process based on SVM is proposed to judge the trend of the chemical composition. The application result shows that the prediction with this method can achieve higher robust, better utility and application value.

关 键 词：烧结矿化学成分 最小二乘支持向量机 预测 样本数据 烧结过程 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]