基于图像分形计算的磨粒定量参数识别研究  

Quantitative Analysis and Recognition of Wear Particle Based on Fractal Description

作　　者：江良洲[1] 龙凤[1] 杨庆[1] 

机构地区：[1]第二炮兵工程学院装备管理工程系,陕西西安710025

出　　处：《计算机技术与发展》2010年第7期227-230,共4页Computer Technology and Development

基　　金：国家自然科学基金(60672108)

摘　　要：磨粒分形研究是磨粒分析技术中的热点。为了得到有效的磨粒分形定量特征,介绍了分形原理和磨粒的分形特性,在计算机和图像处理技术基础上,研究了磨粒分形参数提取。通过探寻磨粒边缘轮廓及纹理分形两种分形维数的计算方法,对大量典型磨粒分形维数进行了定量计算和统计分析,得出了相应的分布范围。给出了计算的一般方法和实例,提供磨粒分析的新的定量特征参数,是磨粒识别的一种有效途径,为最终解释磨损的机理提供了前提。Fractal dimensions are useful for wear particle recognition.In order to obtain quantitative features of wear particles,fractal characteristics of wear particle are expounded.Then,combining with image processing,this paper compares various methods to calculate profile and surface fractal dimension.Based on statistical analysis,fractal dimension distributing ranges of 6 kinds of typical wear particles are obtained through quantitative calculation.General methods and examples are presented,and the experimental results demonstrate that this method is practical for wear particle analysis.

关 键 词：铁谱分析 磨粒识别 分形维数 图像处理 

分 类 号：TH117[机械工程—机械设计及理论] TP391[自动化与计算机技术—计算机应用技术]