热力发电Issue(1)：77-81,5.DOI:10.3969/j.issn.1002-3364.2015.01.077
基于LSGSVM和GM的球磨机料位动态软测量
LSGSVM and GM based dynamic soft sensor for coal level of ball mills
摘要
Abstract
A least squares support vector machine (LS-SVM)and grey model (GM)based dynamic soft sen-sor method for ball mills was proposed.By analyzing the factors affecting the coal level,the auxiliary varia-bles of the soft sensor model were determined.The LS-SVM based soft sensor static model was estab-lished,of which the results were compared with that of the actual values.Thus the time measurement er-rors sequence was obtained and then modeled and predicted by the GM.Finally,the predictive error results were combined with the static model to realize dynamic correction.Application example shows this method can reflect the trend and dynamic characteristics of coal level effectively,which has a higher accuracy and applicability than the single LS-SVM model.关键词
钢球磨煤机/料位/动态软测量/最小二乘支持向量机/灰色模型Key words
ball mill/fill level/dynamic soft sensor/least squares support vector machine/grey model分类
能源科技引用本文复制引用
王恒,花国然,贾民平,陈左亮..基于LSGSVM和GM的球磨机料位动态软测量[J].热力发电,2015,(1):77-81,5.基金项目
国家自然科学基金资助项目(50775035) （50775035）
江苏省自然科学基金资助项目(BK2011391) （BK2011391）
