摘要
随着数控设备越来越复杂,对设备故障诊断与维修提出了更高的要求,采用专家系统的方式建立故障诊断系统以实现数控设备的快速诊断和维修.针对CBR(Case-Based Reasoning)系统自身的增量学习模式使系统的实例库逐渐增大,系统效能大大降低的缺点.根据数控系统结构的特点采用分层检索的方法,依据该检索方法采用框架型的知识表示方式,提高了大实例库的检索效率.将该方法应用于数控设备的故障诊断系统中,提高了故障诊断的诊断效率.
As the computer number control（CNC） become more and more complexity,there is a great demand for fault diagnosis and maintenance system to improve the efficiency of failure diagnostics and maintenance.The case-based reasoning（CBR） has been broadly applied in fault diagnosis.However the case base is increasingly large with the incremental learning which results in low solution retrieval efficiency and weak performance.To improve the accuracy of retrieval cases and reduce retrieval time,a method that searches the cases with stratified indexing and feature retrieval was presented in terms of the structure of CNC,and a frame of knowledge representation was detailed by this method.A prototype system was built with the search method and knowledge representation.The experimental results show that this method is effective.
出处
《北京航空航天大学学报》
EI
CAS
CSCD
北大核心
2011年第12期1557-1561,共5页
Journal of Beijing University of Aeronautics and Astronautics
基金
国家科技重大专项资助项目(2009ZX04009-014-02
2009ZX04013)
关键词
数控系统
故障诊断
实例推理
知识表示
computer number control
fault diagnosis
case-based reasoning
knowledge representation
