MIMO最小二乘支持向量机污水处理在线软测量研究  

Online soft measurement for wastewater treatment based on MIMO least squares support vector machine

作　　者：黄银蓉[1] 张绍德[1] 

机构地区：[1]安徽工业大学电气信息学院,安徽马鞍山243002

出　　处：《自动化与仪器仪表》2010年第4期15-17,共3页Automation & Instrumentation

摘　　要：污水处理系统是一个包含海量信息的非线性复杂系统。针对污水处理出水水质BOD(生物化学需氧量)、COD(化学需氧量)、TN(总含氮量)等难以在线实时检测等问题,建立了基于在线MIMO-LSSVM(多输入多输出最小二乘支持向量机)和PSO(微粒子群算法)的污水处理软测量模型。仿真结果表明,建立的软测量模型精度高、速度快,能很好地实现污水处理出水指标COD、BOD、TN等参数的实时测量和估计,为污水处理的实时在线控制创造必要的前提条件。Wasterwater treatment system is a complex non-linear system containing a huge amount of information.The wastewater quality parameters （such as BOD,COD,TN and so on） can not be monitored online or realtime,which has affected the effectiveness of wastewater treatment.In this paper,soft-measurement technology based on particle swarm optimization algorithm （PSO） and Online MIMO Least Squares Support Vector Machine to online-measurement of wastewater treatment is established,which has been applied to the online and realtime measurement for the real wastewater treatment processes and satisfactory results are obtained.

关 键 词：最小二乘支持向量机(LSSVM) 微粒子群算法(PSO) 污水指标 软测量 

分 类 号：TP18[自动化与计算机技术—控制理论与控制工程]