基于KPLS-LSSVM的航煤闪点和干点软测量应用研究  

Soft sensor modeling of aviation kerosene flash and dry points based on KPLS-LSSVM

作　　者：赵超[1] 王贵评 戴坤成[1] 黄云云[1] 

机构地区：[1]福州大学石油化工学院,福建福州350108

出　　处：《计算机与应用化学》2016年第2期157-162,共6页Computers and Applied Chemistry

基　　金：国家自然科学基金项目(60804027;61374133);高校博士点专项科研基金(20133314120004)

摘　　要：软测量技术是解决流程工业中一类难以在线测量变量估计问题的有效方法。本文提出了一种基于核偏最小二乘方法(KPLS)和最小二乘支持向量机(LS-SVM)的航煤闪点和干点软测量建模方法,采用核偏最小二乘方法对输入变量进行数据压缩,消除变量之间的相关性,简化最小二乘支持向量机模型结构,并通过混沌粒子群—模拟退火方法(CPSO-SA)对最小二乘支持向量机的参数进行优化选择。将优化结果应用于CDU航煤闪点和干点软测量建模,结果表明:该方法具有学习速度快、跟踪性能好以及泛化能力强等优点,为分馏过程在线质量控制的实施奠定了基础。Soft sensor technique provides an effective method to estimate variables which are difficult to be measured on-line in process industry. A soft sensor based on Kernel partial least squares （KPLS） and Least Square SVM was proposed to estimate aviation kerosene flash and dry points in crude oil unit of refinery. The KPLS method could not only solve the linear correlation of the input and compress data but also simply the LSSVM structure. The Chaotic particle swarm optimization simulated annealing （CPSO-SA） was used to select the optimal parameters of LSSVM model. Soft sensor modeling result indicates that this method features high learning speed, good approximation and well generalization ability. It provides good basis for on-line quality control of crude oil unit.

关 键 词：航煤闪点和干点 核偏最小二乘法 最小二乘支持向量机 混沌粒子群—模拟退火 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]