远程故障诊断中融合推理及信息反馈的研究  

Research on remote fault diagnosis based on reasoning and feedback

作　　者：严刚[1] 张利[2] 程龙[2] 徐娟[3] 王跃飞[2] 

机构地区：[1]安徽江淮汽车股份有限公司,安徽合肥230601 [2]合肥工业大学机械与汽车工程学院,安徽合肥230009 [3]合肥工业大学计算机与信息学院,安徽合肥230009

出　　处：《合肥工业大学学报（自然科学版）》2011年第3期367-369,446,共4页Journal of Hefei University of Technology：Natural Science

基　　金：高等学校博士学科点专项科研基金资助项目(20070359028);合肥工业大学博士专项科研基金资助项目(GDBJ2010-008)

摘　　要：基于案例推理(CBR)与基于规则推理(RBR)的专家系统优势互补,并在机械故障诊断领域中有了一定的应用,但仍然受到知识库"瓶颈"的约束。文章提出了将CBR与RBR相结合的专家系统引入远程故障诊断中,使得系统的学习能力增强,知识库扩展速度提高;并引入信息反馈,提高了案例标本的准确性,更大程度地提高了故障诊断的效率及准确率。Case-based reasoning （CBR） and rule-based reasoning （RBR） expert systems complement each other and have been applied in mechanical fault diagnosis, but they are still subject to the ＂bottleneck＂ of knowledge base. In this paper, an expert system based on CBR and RBR is introduced to remote fault diagnosis which makes the system more capable of learning and faster in knowledge expansion. And the feedback is introduced to enhance the accuracy of case samples, which greatly improves the efficiency and accuracy of the fault diagnosis.

关 键 词：远程故障诊断 专家系统 基于案例推理 基于规则推理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]