基于信息融合的舵回路故障诊断  

Fault Diagnosis of Actuator Loop Based on Information Fusion

作　　者：王兴伟[1] 杨拥民[1] 胡政[1] 葛哲学[1] 

机构地区：[1]国防科学技术大学,湖南长沙410073

出　　处：《计算机仿真》2006年第6期73-76,共4页Computer Simulation

基　　金：留学启动基金项目

摘　　要：对直升机舵回路常见的几种故障诊断时,传统的单信息诊断方法已经不能满足快速诊断需求。该文基于D-S证据理论,提出了利用测试信息、模型信息和历史信息等异类信息进行不解体融合诊断的方法,并分别采用灰关联分析法和重要度分析法为诊断信息构造基本可信度。根据舵回路的工作原理,建立实物系统进行故障模拟和诊断。实验结果表明,经过异类信息融合诊断后,显著地降低了故障诊断的不确定性,提高了故障模式的识别率,充分显示了利用信息融合进行诊断的有效性。When diagnosing some vulgar faults of the actuator loop of the helicopter, the conventional approach already can＇t meet the need of the fast diagnosis. An approach using the heterogeneous information fusion based on D - S evidential theory is put forward, and the heterogeneous informations are the testing information, the model informations and the historical information. The grey incidence analysis and importance analysis are utilized to obtain the basic belief. Based on the principle of the actuator loop, a system is established to simulate and diagnose the fault. The experiment results show that the uncertainty of the diagnostic result decreases markedly, and the identifiability of the fauh is improved evidently. So the provided method is proved to be highly effective.

关 键 词：证据理论 故障诊断 异类信息 灰关联分析法 重要度分析 

分 类 号：TP271[自动化与计算机技术—检测技术与自动化装置]