基于D-S证据理论的磨粒识别

Wear Particles Identification Based on Dempster-Shafer Evidential Reasoning

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。

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.