论文部分内容阅读
二、磨粒的分类及识别特征 铁谱分析技术将油液中的固体颗粒分为正常磨损、疲劳磨损、球状、层状、严重滑动、切削、腐蚀磨损、红色氧化物、暗金属氧化物、有色金属、非金属和晶体、污染物等12类。 领域专家根据磨粒的形态（总体形状、边缘细节和表面纹理）、颜色、粒度和厚度信息来识别铁谱磨粒,它们大都是模糊信息,一般用语义形式描述,因此需要采用模糊神经网络识别,识别结果为磨粒类型,系非模糊集合。磨粒特征见表1。
Second, classification and identification of abrasive particles Ferrography analysis technology will be divided into solid particles in the oil into normal wear, fatigue wear, spherical, layered, severe sliding, cutting, corrosion wear, red oxide, dark metal oxide, Non-ferrous metals, non-metals and crystals, pollutants and other 12 categories. Domain experts identify ferrous abrasive particles based on the morphology of the abrasive particles (overall shape, edge detail and surface texture), color, grain size, and thickness information, mostly fuzzy information, generally described in semantic format, and therefore require fuzzy neural network identification , Identification results for abrasive type, Department of non-fuzzy collection. Wear particles in Table 1.