期刊
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
卷 174, 期 -, 页码 15-21出版社
ELSEVIER
DOI: 10.1016/j.chemolab.2018.01.008
关键词
Soft sensor; Deep learning; Semi-supervised learning; Ensemble learning; Industrial polymerization process; Melt index
类别
资金
- Zhejiang Provincial Natural Science Foundation of China [LY18F030024]
- Foundation of Key Laboratory of Advanced Process Control for Light Industry (Jiangnan University), Ministry of Education, China [APCLI1603]
- Ministry of Science and Technology, R.O.C. [MOST 106-2622-E-007-007-CC2]
For predicting the melt index (MI) in industrial polymerization processes, traditional data-driven empirical models do not utilize the information in a large amount of the unlabeled data. To overcome this data-rich-but information-poor (DRIP) problem in polymer industries, an ensemble deep kernel learning (EDKL) model is proposed. With an unsupervised learning stage, the deep brief network is adopted to extract useful information from the available data. Then, a kernel learning regression model is formulated to obtain a nonlinear relationship between the extracted features and MI values. Moreover, a bagging-based ensemble strategy is integrated into the deep kernel learning method to enhance the reliability of the prediction model. The industrial MI prediction results demonstrate the advantages of the developed EDKL model as compared with conventional supervised soft sensors (e.g., partial least squares and support vector regression) that only use the limited labeled data.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据