摘要
为了提高旋转设备故障诊断正确率,将支持向量机SVM和基于案例推理CBR相融合,设计了旋转机械智能化故障诊断混合推理系统。根据两者各自的特点将它们最大限度地结合起来,同时每个推理单元又保持各自的独立性和完整性。讨论了进行SVM和CBR混合推理的关键过程和策略,并以矿井风机为例,建立了矿井风机案例库,对混合推理系统进行了验证。研究结果表明:混合推理系统不仅能提高故障诊断的正确率和系统运行的效率,而且还能增强系统对知识的提取能力。
In order to improve the accuracy of fault diagnosis of rotating machinery,a hybrid intelligent reasoning system of rotating machinery fault diagnosis has been developed by integrating the support vector machine（SVM） and the case-based reasoning（CBR）.Although they are highly integrated,the independence and integrity of each reasoning unit are maintained.This paper will discuss the key processes and hybrid reasoning strategy on SVM and CBR.A case study has been conducted using a mine ventilation fan.A database has been built and validated using the proposed hybrid reasoning system.The results show that the integrated reasoning mode can not only improve the efficiency and accuracy of the fault diagnosis system,but also enhance the ability of the knowledge extraction system.
出处
《辽宁工程技术大学学报（自然科学版）》
CAS
北大核心
2011年第4期580-583,共4页
Journal of Liaoning Technical University (Natural Science)
基金
国家自然科学基金资助项目(60970105)
国家安监总局安全生产科技发展计划资助项目(07-383)
关键词
支持向量机
基于案例推理
故障诊断
混合推理
案例索引
support vector machine
case-based reasoning
fault diagnosis
hybrid inference
case index
