摘要
残碱和黑液波美度是评价纸浆洗涤质量的两个重要指标,但二者在线直接测量难度大,笔者基于集散控制系统采集的大量现场数据和用机理模型得到的模拟数据,建立了二者的稳态神经网络模型,通过最小二乘法进行在线校正,建立了一套新型残碱和黑液波美度的软测量方法。计算机仿真和现场数据比较结果证明了该软测量方法的有效性。
The most important quality indices of evaluating pulp washing performance are residual alkali in the washed pulp and the Baume degree of the extracted black liquor.Considering the fact of direct on-line instrument measuring of them is very difficult,an adaptive soft-sensing instrument for measuring residual soda and Baume degree is proposed.Voluminous plant operation data collected by DCS and simulated results from a theoretical model are pooled together and used to build the adaptive soft-sensing instrument based on the BP neural network and least square method.Application of the soft-sensing technique in pulp washing control system shows that the control system can run smoothly over a long period on site.
出处
《中国造纸》
CAS
北大核心
2011年第6期47-52,共6页
China Pulp & Paper
基金
国家自然科学基金项目(30972322)资助
关键词
残碱
黑液波美度
软测量
神经网络
最小二乘法
pulp washing process
soft sensor
neural network
least square method
DCS
