A neural network based model for temperature prediction in high power microwave heating system

DOI

10.2991/eame-15.2015.206How to use a DOI?

Keywords

BP neural network; genetic algorithm; microwave heating; temperature prediction

Abstract

The applications of neutral network based temperature prediction for microwave heating system has been comprehensively investigated. Temperature prediction is essential due to the characteristics of high power microwave heating system, a.k.a. big inertia and pure time-delay. This work proposes a BP neutral network based model associated with a Genetic Algorithm (GA), which aims at improving the temperature prediction accuracy. Our numerical experiments show that the BP neutral network with tansig transfer function and trainlm training function is the most appropriate one in our case based on minimum measures of error. Experiments on the pure water and coal obtained in our simulated experimental facilities were used for training and testing the proposed optimal neutral network. Based on our experimental results, the GA based BP neural network model can significantly improve the prediction accuracy as well as the convergence speed. As a result, the proposed system is suitable for the real-world applications.

Copyright

© 2015, 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  - C. Chen
AU  - X.Z. Zhou
AU  - Z.Y. Tang,
AU  - Y.J. Lei
PY  - 2015/07
DA  - 2015/07
TI  - A neural network based model for temperature prediction in high power microwave heating system
BT  - Proceedings of the 2015 International Conference on Electrical, Automation and Mechanical Engineering
PB  - Atlantis Press
SP  - 761
EP  - 766
SN  - 2352-5401
UR  - https://doi.org/10.2991/eame-15.2015.206
DO  - 10.2991/eame-15.2015.206
ID  - Chen2015/07
ER  -