摘要
该文将分形理论运用于火焰稳定性的研究,提出一种基于分形特征的图像分割方法,把火焰从背景中分离出来。此方法适应性比较好,并具有良好的抗噪性能。同时通过实验表明,除了传统常用的反映火焰燃烧状态的特征参量外,分形维数也可作为一个反映火焰稳定性的图像指标,运用到火焰稳定性诊断中去。
This paper introduces the fractal theory into the study of flame stability, and presents a new method of image segmentation based on fractal feature. Application of this methods successfully segment flame targets from the background, the he adaptability of this means is extensive and antinoise performance is strong. At the same time, some experiments show besides some conventional image characteristic parameters, fractal dimension is also one kind of image feature, which can reflect the combustion state, and be used to diagnose the flame stability.
出处
《中国电机工程学报》
EI
CSCD
北大核心
2004年第12期248-252,共5页
Proceedings of the CSEE
基金
国家自然科学基金项目(50106015)。
关键词
电站
锅炉
分形理论
火焰稳定性
诊断
图像分割
Thermal powe rengineering
Combustion diagnosis
Flame stability
Fractal dimension
Image segmentation
