一种基于支持向量机增量学习的软测量建模方法  

Soft Sensor Modeling Based on Support Vector Machines Incremental Learning

作　　者：张英[1] 苏宏业[1] 褚健[1] 

机构地区：[1]浙江大学先进控制研究所工业控制技术国家重点实验室,浙江杭州310027

出　　处：《化工自动化及仪表》2005年第3期22-24,共3页Control and Instruments in Chemical Industry

基　　金：国家杰出青年科学基金资助项目(60025308)

摘　　要：针对软测量模型在现场的失效问题,提出一种基于支持向量增量学习的软测量建模方法,将增量样本中违背Karush-Kuhn-Tucker条件的样本引入到工作样本集中,同时将非支持向量中到特征空间超球球心距离较小的样本剔除出工作样本集。并将提出的方法用于对二甲苯吸附分离过程中产品纯度的预测中。In order to overcome model failure problem, a soft sensor method based on support vector machines incremental learning is presented. Non-support vectors in working set are replaced by the samples which violate the Ka-rush-Kuhn-Tucker conditions in the incremental set. The proposed soft sensor model is applied to predict the purity of para-xylene (PX) in a PX fractionation by adsorption process. Simulation results indicate that the proposed soft sensor model increases the adaptive abilities to various operation conditions and solves the model failure problem.

关 键 词：支持向量机 数据域描述 增量学习 软测量 对二甲苯 

分 类 号：TP273[自动化与计算机技术—检测技术与自动化装置]