期刊
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
卷 17, 期 12, 页码 8357-8366出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TII.2020.3046013
关键词
Data models; Valves; Transient analysis; Training; Indexes; Predictive models; Transportation; Active learning; data-driven modeling; dynamic process; multiphase flow; probabilistic model
类别
资金
- National Natural Science Foundation of China [62022073, 61873241]
- Ministry of Science and Technology, Taiwan [MOST 108-2221-E-007-068-MY3]
This article presents an active learning method for exploring information and gradually improving model quality, helping to describe process characteristics of dynamic multiphase flows. The method is especially suitable for transitional regions exhibiting dynamic information.
Accurate depiction of the process characteristics of dynamic multiphase flows using a data-driven model is a challenge in industrial practices. Collection of sufficient data is costly and cumbersome, and it is difficult to identify representative data efficiently. This article develops an active learning method to explore information from multiphase flow process data, thus facilitating smart process modeling and prediction. An index is proposed to describe the process dynamics and nonlinearity using a probabilistic model, facilitating determination of informative data. The subsequent absorption of these data into the training set enhances the model quality gradually. This is relevant especially for transitional regions exhibiting dynamic information. In addition, a simple and efficient criterion to judge the learning termination has been designed. Consequently, new representative data are explored and learned in a sequential manner. The experimental results of two industrial multiphase flows demonstrate the advantages of the proposed method.
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