logo

SCIENCE CHINA Information Sciences, Volume 63 , Issue 4 : 149205(2020) https://doi.org/10.1007/s11432-018-9624-8

Multi-rate principal component regression model for soft sensor application in industrial processes

More info
  • ReceivedAug 12, 2018
  • AcceptedOct 15, 2018
  • PublishedSep 25, 2019

Abstract

There is no abstract available for this article.


Acknowledgment

This work was supported by National Natural Science Foundation of China (Grant Nos. 61603342), NSFC-Zhejiang Joint Fund for the Integration of Industrialization and Informatization (Grant No. U1609214), and China Postdoctoral Science Foundation (Grant No. 2018M630674)


References

[1] Ge Z, Song Z, Ding S X. Data Mining and Analytics in the Process Industry: The Role of Machine Learning. IEEE Access, 2017, 5: 20590-20616 CrossRef Google Scholar

[2] Zhou L, Zheng J, Ge Z. Multimode Process Monitoring Based on Switching Autoregressive Dynamic Latent Variable Model. IEEE Trans Ind Electron, 2018, 65: 8184-8194 CrossRef Google Scholar

[3] Yuan X, Wang Y, Yang C. Weighted Linear Dynamic System for Feature Representation and Soft Sensor Application in Nonlinear Dynamic Industrial Processes. IEEE Trans Ind Electron, 2018, 65: 1508-1517 CrossRef Google Scholar

[4] Ge Z. Process Data Analytics via Probabilistic Latent Variable Models: A Tutorial Review. Ind Eng Chem Res, 2018, 57: 12646-12661 CrossRef Google Scholar

[5] Zhou L, Chen J, Song Z. Semi-supervised PLVR models for process monitoring with unequal sample sizes of process variables and quality variables. J Process Control, 2015, 26: 1-16 CrossRef Google Scholar

[6] Yao L, Ge Z. Locally Weighted Prediction Methods for Latent Factor Analysis With Supervised and Semisupervised Process Data. IEEE Trans Automat Sci Eng, 2017, 14: 126-138 CrossRef Google Scholar

[7] Shao W, Tian X. Semi-supervised selective ensemble learning based on distance to model for nonlinear soft sensor development. Neurocomputing, 2017, 222: 91-104 CrossRef Google Scholar

[8] Chai T, Draxler R R. Root mean square error (RMSE) or mean absolute error (MAE)? - Arguments against avoiding RMSE in the literature. Geosci Model Dev, 2014, 7: 1247-1250 CrossRef ADS Google Scholar

  • Figure 1

    (Color online) (a) The flowchart of the papermaking wastewater treatment process; (b) the prediction results of the suspended solids (2${\rm{\#~}}$) in the anaerobic reactor outlet using (b.1) MRPCR, (b.2) PPCR, and (b.3) PLS; (c) the prediction results in anaerobic reactor outlet.

Copyright 2020  CHINA SCIENCE PUBLISHING & MEDIA LTD.  中国科技出版传媒股份有限公司  版权所有

京ICP备14028887号-23       京公网安备11010102003388号