摘要
针对软测量模型存在的失效问题,提出一种基于增量支持向量机的建模方法.随着时间的推移,每次在模型中增加一个样本进行增量学习的同时,采用启发式策略去掉工作集中一个老的样本,从而可以在软测量模型中不断增加能够代表新工况信息样本的同时控制工作样本集的规模.将所提出的软测量建模方法用于二甲苯(PX)吸附分离过程纯度的预测,结果表明所提出的建模方法以及样本替换策略可以有效地增强软测量模型适应工况变化的能力,提高其预测的精度.
In order to overcome model failure problem, a soft sensor modeling method based on incremental support vector machines （ISVM） is presented. In ISVM, an incremental sample which represents new operational condition is introduced to the model, whereas an old sample is discarded from the model to control the size of working set. The proposed method is applied to predict the purity of para-xylene （PX） in a PX fractionation by adsorption process. Simulation results show that the proposed soft sensor model actually increases the adaptive abilities to various operation conditions and solves the model failure problem caused by change of operation conditions or load.
出处
《控制与决策》
EI
CSCD
北大核心
2005年第10期1102-1106,共5页
Control and Decision
基金
国家杰出青年科学基金项目(NOYSFC
60025308)
浙江省"151"人才重点项目
关键词
支持向量机
增量学习
软测量
PX吸附分离过程
Support vector machines
Incremental learning
Soft sensor
Para-xylene fractionation by adsorption process
