基于监测实例的摩擦学系统状态辨识的知识获取  

Knowledge Acquisition of Tribological System Condition Identification Based on Monitoring Examples

作　　者：白秀琴[1,2] 袁成清[1,2] 王志芳[3] 

机构地区：[1]武汉理工大学能源与动力工程学院可靠性工程研究所,湖北武汉430063 [2]武汉理工大学船舶动力工程技术交通行业重点实验室,湖北武汉430063 [3]中国船级社武汉规范研究所,湖北武汉430022

出　　处：《润滑与密封》2010年第11期14-17,38,共5页Lubrication Engineering

基　　金：国家自然科学基金项目(50705070);教育部博士点新教师项目(20070497029)

摘　　要：对于摩擦学系统监测样本相对比较少或者投入运行时间不长的机器,研究如何实现其摩擦学系统的智能状态辨识具有重要意义。建立基于摩擦学状态监测实例和决策树的知识获取方法模型,并应用于船舶柴油机摩擦学状态辨识的知识获取,利用获得的知识对测试集进行状态识别,取得良好的摩擦学状态辨识结果,从而为从监测实例中挖掘摩擦学状态辨识知识提供方法与手段支持。Aimed at the machines which are not in operation for long time, the monitoring examples are relatively rare. How to realize the intelligent condition identification of trihology system is worth of studying. The knowledge acquisition model based on decision tree about tribology system monitoring examples was established, and was then used in the tribolo- gy system condition identification knowledge acquisition of diesel engine. Tile condition identification knowledge acquired with the model was used to the test examples. The results show that the knowledge acquisition model based on decision tree provides a new approach for the intelligent condition identification tribology system.

关 键 词：摩擦学 知识获取 状态 监测 决策树 

分 类 号：TH117.1[机械工程—机械设计及理论]