The Application of Data-driven Modelling and State Monitoring in Steam Pipe Networks in Iron& Steel Enterprises

DOI

10.2991/icmse-18.2018.24How to use a DOI?

Keywords

Data Driven Modelling, Monitoring, PCA, Steam Pipe Networks.

Abstract

The steam pipe network is a complex object to be modelled and monitored with traditional mathematical model. In this paper, the mathematical model of single steam pipe is analyzed and an innovated data-drive modelling method with piecewise performed principal analysis (PCA) is proposed. In this method, the variable space is separated into smaller sections and perform PCA respectively to generate the corresponding approximate linear PCA model. By monitoring the statistical variables T2and SPE, the abnormality and fault data can be easily discovered. The simulation result shows the effectiveness of the proposed method.

Copyright

© 2018, 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  - Xianxi Luo
AU  - Wei Wang
AU  - Hongwei Deng
AU  - Zehao Wu
PY  - 2018/05
DA  - 2018/05
TI  - The Application of Data-driven Modelling and State Monitoring in Steam Pipe Networks in Iron& Steel Enterprises
BT  - Proceedings of the 2018 8th International Conference on Manufacturing Science and Engineering (ICMSE 2018)
PB  - Atlantis Press
SP  - 116
EP  - 122
SN  - 2352-5401
UR  - https://doi.org/10.2991/icmse-18.2018.24
DO  - 10.2991/icmse-18.2018.24
ID  - Luo2018/05
ER  -