南京师大学报（自然科学版）2012，Vol.35Issue(4)：140-144,5.
基于神经网络的火焰燃烧稳定性算法研究
Research on Flame Combustion Stability Based on Neural Network
摘要
Abstract
The paper aims at researching boiler flame stability problems and improving boiler combustion flame detection accuracy. For the use of boiler flame image analysis to detect the boiler flame combustion stability, when the combustion is affected,the flame appeared short pulsation. The traditional detection methods based on gray scale variance can not avoid the impact of flame pulsation on account of the inaccuracy of the boiler combustion stability detection. This paper presents a flame combustion instability detection method based on neural network and selects multiple features which are directly related to the flame stability as neural network input vector. Experiments show that this method can fight off the tiny ripple influence caused by the impurities combustion or peak and simultaneously, make accurate detection of the boiler combustion stability.关键词
锅炉/燃烧检测/燃烧稳定性/神经网络Key words
boiler,combustion detection,combustion stability,neural network分类
能源科技引用本文复制引用
陈书谦,柏桂枝..基于神经网络的火焰燃烧稳定性算法研究[J].南京师大学报（自然科学版）,2012,35(4):140-144,5.基金项目
江苏省高校科研成果产业化推进项目(JHB2012-61). （JHB2012-61）
