基于LS-SVM和单纯形的烟气含氧量软测量  

Soft Measurements of Flue-gas Oxygen Content Based on LS-SVM (Least Square Supportive Vector Machine) and a Simplex Algorithm

作　　者：刘长良[1] 李淑娜[1] 

机构地区：[1]华北电力大学自动化学院,河北保定071003

出　　处：《热能动力工程》2010年第3期292-296,357,共6页Journal of Engineering for Thermal Energy and Power

基　　金：国家高技术研究发展计划(863)基金资助项目(2007AA041106)

摘　　要：烟气含氧量是影响火电厂燃烧经济性的一个重要因素。由于受到多个因素的影响,导致了火电厂烟气含氧量测量存在一定的困难性。软测量模型是以容易测得的二次变量为基础,利用二次变量和难测得的待测过程变量之间的数学关系,对待测过程变量进行测量而建立的模型。本研究选用合适的二次变量,提出了基于最小二乘支持向量机的火电厂烟气含氧量软测量模型。并把单纯形寻优算法应用在最小二乘支持向量机的两个必需确定的参数优化问题中,结合现场数据对模型进行预测检验。仿真结果表明,该方法能够比较准确地对火电厂烟气含氧量进行测量,对于实现火电厂经济燃烧有着重大的意义。Flue gas oxygen content is an important factor influencing the combustion efficiency of a thermal power plant. To measure the flue gas oxygen content in a thermal power plant is somewhat difficult as it is influenced by multiple factors. A soft measurement model was established based on the easily measured secondary variables and by utilizing the mathematical relationship between the secondary variables and the process variables to be measured which present difficulties for measurement. The appropriate seco...

关 键 词：LS-SVM 单纯形 烟气含氧量 软测量 寻优算法 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置]