Prediction of the melt flow index using partial least squares and support vector regression in high-density polyethylene (HDPE) process

被引:18
作者
Park, Tae Chang [1 ]
Kim, Tae Young [1 ]
Yeo, Yeong Koo [1 ]
机构
[1] Hanyang Univ, Dept Chem Engn, Seoul 133791, South Korea
关键词
Melt Flow Index; Partial Least Square; Support Vector Regression; Prediction;
D O I
10.1007/s11814-010-0280-x
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
In polyolefin processes the melt flow index (MFI) is the most important control variable indicating product quality. Because of the difficulty in the on-line measurement of MFI, a large number of MFI estimation and correlation methods have been proposed. In this work, mechanical predicting methods such as partial least squares (PLS) method and support vector regression (SVR) method are employed in contrast to conventional dynamic prediction schemes. Results of predictions are compared with other prediction results obtained from various dynamic prediction schemes to evaluate predicting performance. Hourly MFIs are predicted and compared with operation data for the high density polyethylene process involving frequent grade changes. We can see that PLS and SVR exhibit excellent predicting performance even for severe operating situations accompanying frequent grade changes.
引用
收藏
页码:1662 / 1668
页数:7
相关论文
共 15 条
[1]   Prediction of high weight polymers glass transition temperature using RBF neural networks [J].
Afantitis, A ;
Melagraki, G ;
Makridima, K ;
Alexandridis, A ;
Sarimveis, H ;
Iglessi-Markopoulou, O .
JOURNAL OF MOLECULAR STRUCTURE-THEOCHEM, 2005, 716 (1-3) :193-198
[2]   General melting point prediction based on a diverse compound data set and artificial neural networks [J].
Karthikeyan, M ;
Glen, RC ;
Bender, A .
JOURNAL OF CHEMICAL INFORMATION AND MODELING, 2005, 45 (03) :581-590
[3]   Prediction and quality control of the melt index during production of high-density polyethylene [J].
Lee, Eun Ho ;
Kim, Tae Young ;
Yeo, Yeong Koo .
KOREAN JOURNAL OF CHEMICAL ENGINEERING, 2008, 25 (04) :613-622
[4]   ONLINE INFERENCE OF POLYMER PROPERTIES IN AN INDUSTRIAL POLYETHYLENE REACTOR [J].
MCAULEY, KB ;
MACGREGOR, JF .
AICHE JOURNAL, 1991, 37 (06) :825-835
[5]   NONLINEAR PRODUCT PROPERTY CONTROL IN INDUSTRIAL GAS-PHASE POLYETHYLENE REACTORS [J].
MCAULEY, KB ;
MACGREGOR, JF .
AICHE JOURNAL, 1993, 39 (05) :855-866
[6]  
MIN KG, 1999, KOREAN J CHEM ENG, V5, P2437
[7]   Quality inferential control of an industrial high density polyethylene process [J].
Ogawa, M ;
Ohshima, M ;
Morinaga, K ;
Watanabe, F .
JOURNAL OF PROCESS CONTROL, 1999, 9 (01) :51-59
[8]   Prediction of pellet properties for an industrial bimodal high-density polyethylene process with Ziegler-Natta catalysts [J].
Oh, SJ ;
Lee, J ;
Park, S .
INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH, 2005, 44 (01) :8-20
[9]   Quality control of polymer production processes [J].
Ohshima, M ;
Tanigaki, M .
JOURNAL OF PROCESS CONTROL, 2000, 10 (2-3) :135-148
[10]  
Park Chan-Kyoo, 2006, [Korean Management Science Review, 경영과학], V23, P75