基于模糊模式与火焰图像特征量的燃烧状态识别方法  

A METHOD FOR RECOGNIZING FLAME COMBUSTION STATUS BASED ON FUZZY MODE AND FLAME IMAGE EIGENVECTOR

作　　者：林彬[1] 马增益[1] 王飞[1] 严建华[1] 白卫东[1] 罗娅[1] 岑可法[1] 

机构地区：[1]浙江大学,浙江杭州310027

出　　处：《热力发电》2004年第10期19-21,共3页Thermal Power Generation

基　　金：国家自然科学基金资助项目 (N50 1 0 60 1 5)

摘　　要：通过对火焰图像进行分析 ,提取出火焰亮度、火焰面积、质心偏移距离和圆形度等 7个特征量 ,应用模糊模式建立识别模型 ,根据最大隶属度判别火焰的燃烧状态。模型识别结果表明 ,此方法识别准确率高 ,计算速度快 。Through analysis of flame image, seven eigenvectors, such as flame brightness, flame area, shifting distance of mass center and flame roundness etc. have been extracted, and a recognizing model being established by using the fuzzy mode to judge whether the combustion status of flame to be stable on the basis of max. subordinateness. Results of experiment show that the said method has very high recognition accuracy and rapid calculation speed, being suitable for practical application.

关 键 词：火焰图像 特征量 圆形 质心 模糊模式 计算速度 模型识别 识别方法 亮度 准确率 

分 类 号：TM572.2[电气工程—电器] TK311[动力工程及工程热物理—热能工程]