Research on Big data Preprocessing Technology of Thermal System

DOI

10.2991/eesed-16.2017.41How to use a DOI?

Keywords

Big data of thermal system; Pretreatment; Pearson correlation coefficient; VIF; Condition number

Abstract

There is a big amount of overlap among the data of thermal system, which will seriously affect the accuracy and precision of the model. In order to improve the value density of big data of thermal system and improve the quality and efficiency of modeling, pretreatment and analysis have to be made. Aimed at the diagnosis and treatment of the multiple co-linearity among variables, three reduction models have been established, respectively by Pearson correlation coefficient diagnostic method, VIF auxiliary regression test and condition number diagnosis method. And the models have been validated by the data of a 600MW unit of a power plant. Through the analysis of the results, it is found that the condition number diagnosis method can effectively solve the problem of multiple co-linearity of big data of thermal system, realizing the pretreatment of big data of thermal system.

Copyright

© 2017, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Yi-Fan Zhao
AU  - Zhong-Guang Fu
AU  - Fei Chen
PY  - 2016/08
DA  - 2016/08
TI  - Research on Big data Preprocessing Technology of Thermal System
BT  - 2nd Annual International Conference on Energy, Environmental & Sustainable Ecosystem Development (EESED 2016)
PB  - Atlantis Press
SP  - 303
EP  - 311
SN  - 2352-5401
UR  - https://doi.org/10.2991/eesed-16.2017.41
DO  - 10.2991/eesed-16.2017.41
ID  - Zhao2016/08
ER  -