基于RPLS的造纸废水处理过程软测量建模  

Soft Sensor Modeling of Papermaking Effluent Treatment Processes Using RPLS

作　　者：杨浩[1] 莫卫林 熊智新[1] 黄明智[2] 刘鸿斌[1] 

机构地区：[1]南京林业大学江苏省制浆造纸科学与技术重点实验室,江苏南京210037 [2]中山大学水资源与环境系,广东广州510275

出　　处：《中国造纸》2016年第10期31-35,共5页China Pulp & Paper

基　　金：南京林业大学高层次人才科研启动基金(No.16310-5996);江苏省制浆造纸科学与技术重点实验室开放基金项目(201010);江苏高校优势学科建设工程资助项目(PAPD)

摘　　要：偏最小二乘(PLS)软测量预测模型在预测造纸废水处理过程中的出水化学需氧量(COD_(Cr))和固体悬浮物(SS)时,易受过程非线性特性和系统外部干扰等因素的影响而失效。针对以上问题,研究了递归偏最小二乘(RPLS)算法的造纸废水处理过程软测量建模。计算结果表明,采用PLS模型预测出水CODCr时,平均绝对百分比误差(MAPE)、均方根误差(RMSE)和相关系数(R^2)分别为5.3832%、4.6878和0.5892;采用RPLS模型预测时,MAPE、RMSE、R^2分别为1.3861%、1.8792和0.9221。采用PLS模型预测SS时,MAPE、RMSE和R^2分别为2.5962%、0.7412和0.6651;采用RPLS模型时MAPE、RMSE、R2分别为0.6795%、0.2198和0.9627。以上结果表明,RPLS预测模型比PLS预测模型具有更好的预测性能和更高的精度。Soft sensor modeling methods based on partial least squares （PLS） and recursive PLS （RPLS）were used to predict effluent chemi- cal oxygen demand（ CODcr ） and effluent suspended solids （SS） in a papermaking wastewater treatment process. PLS is unsuitable for the systems with non-linear characteristics and external disturbances. The results showed that the mean absolute percentage error（ MAPE）, root mean square error（RMSE） , and squared correlation coefficient（ R2 ） for CODcr using PLS were 5. 3832% , 4.6878, and 0.5892, respective- ly, and they were 1. 3861%, 1. 8792, and 0.9221, respectively using RPLS. In terms of SS, the MAPE, RMSE, and R2 were 2, 5962%, 0.7412, and 0.6651, respectively when using PLS, and the three indices using RPLS were 0.6795%, 0.2198, and 0. 9627, respectively. These results indicated that the RPLS model had better prediction performance and higher accuracy compared to the PLS model.

关 键 词：递归偏最小二乘 偏最小二乘 软测量建模 造纸废水处理 

分 类 号：X793[环境科学与工程—环境工程]