摘要
引入了一套磨粒形态学描述体系,用来提取磨损颗粒的显微形态特征,然后以此为输入参数,提出了一套BP神经网络,对磨损颗粒进行自动识别分类。以很少的磨粒特征量,可以正确识别磨损类别,提高了磨损识别的效率。
A set of morphology descriptors of debris is presented to describe the micro-feature of wear particles, and the program to auto-identify wear particles by means of artificial neural network （ANN） technique is compiled. With less micro-features ,the wear particles can be identified accurately ,the proficiency is highly improved.
出处
《机械工程与自动化》
2005年第3期56-57,62,共3页
Mechanical Engineering & Automation
关键词
BP神经网络
磨粒识别
分类器
back-propagation neural network wear particle recognition classing apparatus
