首页|Active training sample selection and updating strategy for near-infrared model with an industrial application

Active training sample selection and updating strategy for near-infrared model with an industrial application

扫码查看
原文链接
  • NETL
  • NSTL
  • 万方数据
  • 维普
Training sample selection is widely accepted as an important step in developing a near-infrared (NIR) spectro-scopic model. For industrial applications, the initial training dataset is usually selected empirically. This process is time-consuming, and updating the structure of the modeling dataset online is difficult. Considering the static structure of the modeling dataset, the performance of the established NIR model could be degraded in the online process. To cope with this issue, an active training sample selection and updating strategy is proposed in this work. The advantage of the proposed approach is that it can select suitable modeling samples automatically ac-cording to the process information. Moreover, it can adjust model coefficients in a timely manner and avoid ar-bitrary updating effectively. The effectiveness of the proposed method is validated by applying the method to an industrial gasoline blending process.

Near-infrared spectroscopyChemical processesProcess systemsSoft sensorGasoline blending

Kaixun He、Kai Wang、Yayun Yan

展开 >

College of Electrical Engineering and Automation, Shandong University of Science and Technology, Qingdao 266590, China

Key Laboratory of Advanced Control and Optimization for Chemical Processes, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China

Supported by the National Natural Science Foundation of ChinaSupported by the National Natural Science Foundation of ChinaNatural Science Foundation of Shandong Province, ChinaChina Postdoctoral Science FoundationResearch Fund for the Taishan Scholar Project of Shandong Province of China

6180323461751307ZR2017BF0262018M632691

2019

中国化学工程学报(英文版)
中国化工学会

中国化学工程学报(英文版)

CSTPCDCSCDSCIEI
影响因子：0.818
ISSN：1004-9541
年,卷(期)：2019.27(11)
  • 1
  • 3