A Two-Phased PSO-SVM Predictive Quality Control Model for Multistage Production

DOI

10.2991/meic-14.2014.305How to use a DOI?

Keywords

quality predictive control; process parameters optimization; support vector machine (SVM); hierarchical model; particle swarm optimization (PSO)

Abstract

Steel production is regarded as a typical multi-stage system given its long process flow feature. In this paper, the quality predictive control features of steel production is studied; a two-phased PSO-SVM predictive control model for multi-stage production is established. In order to solve the model, a constrained PSO hyper kernel parameters optimization algorithm with a PCA data pre-processing method is proposed. The model is tested and proved to be effective by quality data of a steel production enterprise, in the case, the prediction of the multi-stage production is realized in phase one, and the global optimization of related process parameters is worked out in phase two.

Copyright

© 2014, 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  - Jingping Yang
AU  - Wanlei Wang
AU  - Yuegang Luo
AU  - Jing Kang
PY  - 2014/11
DA  - 2014/11
TI  - A Two-Phased PSO-SVM Predictive Quality Control Model for Multistage Production
BT  - Proceedings of the 2014 International Conference on Mechatronics, Electronic, Industrial and Control Engineering
PB  - Atlantis Press
SP  - 1353
EP  - 1356
SN  - 2352-5401
UR  - https://doi.org/10.2991/meic-14.2014.305
DO  - 10.2991/meic-14.2014.305
ID  - Yang2014/11
ER  -