基于D-S证据理论的磨粒识别

基于D-S证据理论的信息融合方法应用于磨损颗粒的自动识别,编制了相应的计算机识别程序。在对磨粒图象的形态特征参数进行筛选和统计分析的基础上,确定了各参数的统计容许限和决策基元概率。通过对一组标准磨粒的模拟识别试验,显示该方法具有算法简单、运行可靠、识别正确率高以及识别速度快的优点。

Wear Particles Identification Based on Dempster-Shafer Evidential Reasoning

As an important method of information fusion technology, the theory of Dempster Shafer (D S) evidential reasoning has been applied to many areas such as automation,image analysis and object identification and so on.In this paper,the method of D S evidential reasoning is introduced into wear particles identification based on statistic selection and analysis of characteristic parameters of debris,and the statistic tolerance and decision making probability of image parameters of wear particles are also given based on identification test.The program of auto identification of wear particles has been made by means of Dempster Shafer evidential reasoning,and a classifying experiment of wear particles by this method has been done.It is shown in the experiment that the identification accuracy of debris by D S evidential reasoning is very good,and the speed of classification is very fast.