Recognition of Toxic Gases Emission in Power Plant Based on Artificial Neural Network

被引：2

作者：

Meng Xiaomin ^{[1
]}

机构：

[1] NE Dianli Univ, Inst Chem Engn, Jilin, Peoples R China

来源：

2012 INTERNATIONAL CONFERENCE ON FUTURE ELECTRICAL POWER AND ENERGY SYSTEM, PT B | 2012年 / 17卷

关键词：

toxic gas; recognition; back-propagation neural network (BP); self-organizing feature map (SOM);

D O I：

10.1016/j.egypro.2012.02.284

中图分类号：

TE [石油、天然气工业]; TK [能源与动力工程];

学科分类号：

0807 ; 0820 ;

摘要：

Two kinds of methods of artificial neural network, which are used to recognized toxic gas, are presented and the effects of recognition are also compared. Firstly, the composition and principle of sensor array sensitive to toxic gas are introduced. Two kinds of neural network models, Back-Propagation Neural Network (BP) and Self-Organizing Feature Map (SOM), for qualitative analysis and recognition to three kinds of gas (CO, SO2, NO2) in sensor array system are utilized. The results show that preciseness rate of the two recognitions reaches 100%, but the identify capacity of SOM, such as study time and training epochs, is better than BP in entirety. (C) 2012 Published by Elsevier Ltd. Selection and/or peer-review under responsibility of Hainan University.

引用

页码：1578 / 1584

页数：7