Real-time product quality control for batch processes based on stacked least-squares support vector regression models

2012 ◽  
Vol 36 ◽  
pp. 217-226 ◽  
Author(s):  
Shuning Zhang ◽  
Fuli Wang ◽  
Dakuo He ◽  
Runda Jia
Keyword(s):  
Quality Control ◽  
Product Quality ◽  
Least Squares ◽  
Support Vector Regression ◽  
Real Time ◽  
Regression Models ◽  
Batch Processes ◽  
Support Vector ◽  
Product Quality Control

Industrial experiences with product quality control in semi-batch processes

2002 ◽  
Vol 26 (2) ◽  
pp. 205-212 ◽  
Author(s):  
Yasuaki Yabuki ◽  
Tooru Nagasawa ◽  
John F MacGregor
Keyword(s):  
Quality Control ◽  
Product Quality ◽  
Batch Processes ◽  
Product Quality Control

Application of partial least squares methods to a terephthalic acid manufacturing process for product quality control

2003 ◽  
Vol 20 (6) ◽  
pp. 977-984 ◽  
Author(s):  
In-Su Han ◽  
Minjin Kim ◽  
Chang-Hyun Lee ◽  
Woonou Cha ◽  
Byoung-Kyoung Ham ◽  
...  
Keyword(s):  
Quality Control ◽  
Product Quality ◽  
Least Squares ◽  
Partial Least Squares ◽  
Manufacturing Process ◽  
Terephthalic Acid ◽  
Product Quality Control

Online Quality Prediction of Strip Hot-Dip Galvanizing Based on Support Vector Regression

2010 ◽  
Vol 145 ◽  
pp. 153-158
Author(s):  
Fei He ◽  
Zhi Guo Liang ◽  
Min Li ◽  
Jin Wu Xu
Keyword(s):  
Product Quality ◽  
Support Vector Regression ◽  
Real Time ◽  
Zinc Coating ◽  
Support Vector ◽  
Online Support ◽  
Quality Model ◽  
Training Time ◽  
Online Support Vector Regression ◽  
Time Update

In order to predict product quality and optimize production process, the product quality model needs to be built. According to the fact that the common methods always cost long training time and can not realize real-time update, an online product quality model based on the online support vector regression is here proposed. The real field data of zinc coating weights from strip hot-dip galvanizing are used for validation. The results show that the models based on the online support vector regression have a higher prediction precision and shorter training time than traditional support vector regression, which is convenient to complete the real-time update. The zinc coating weights forecasting model based on the online support vector regression for multi-group data has an average of the relative prediction error of 4.35%, thus for the model will be used as an analysis tools for the quality control.

Sign in / Sign up

Export Citation Format

Share Document