Method for Mixed Gas Detecting in Coal Mine Based on Improved RBF Neural Network

DOI

10.2991/ism3e-15.2015.92How to use a DOI?

Abstract

Aiming at the problem of the coal mine rescue robot's perception of toxic and harmful gas in Coal Mine, The cross sensitivity of partial gas is reduced by using double gas sensor, and the influence of the variable factors such as temperature and humidity is considered, The improved RBF neural network based on genetic neural network algorithm and K clustering algorithm is proposed in combination with the practical application of coal rescue robot, A hybrid gas detection system based on RBF neural network is built. The experimental results show that: the improved RBF neural network algorithm is applied to the training of mixed gas quantitative recognition, The convergence speed is faster than the RBF neural network algorithm, and the learning accuracy is higher, Improve the performance of RBF and the detection accuracy of the mixed gas detection system, the system can take the quantitative detection of H2S, CO, CO2 and CH4 four kinds of gases and their mixed gas in the detection range.

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  - Ruiqing Mao
AU  - Xiliang Ma
AU  - Yong Wang
PY  - 2015/11
DA  - 2015/11
TI  - Method for Mixed Gas Detecting in Coal Mine Based on Improved RBF Neural Network
BT  - Proceedings of the 2015 International Symposium on Material, Energy and Environment Engineering
PB  - Atlantis Press
SP  - 382
EP  - 386
SN  - 2352-5401
UR  - https://doi.org/10.2991/ism3e-15.2015.92
DO  - 10.2991/ism3e-15.2015.92
ID  - Mao2015/11
ER  -