摘要
利用虚拟仪器技术实现基于模糊支持向量机的航空发动机润滑系统故障诊断。通过对润滑油油液中磨损元素进行光谱识别与分析,提取故障诊断所需的特征参数作为支持向量机的学习样本,使用ActiveX技术在LabVIEW中调用MATLAB.m文件,完成对润滑系统的故障诊断,并比较了基于BP神经网络的诊断方法与模糊SVM故障诊断方法的诊断结果。结果表明:模糊SVM方法在故障诊断速度和诊断准确性方面都具有明显优势,其平均故障识别率达到95%以上。
Based on virtual instrument and fuzzy SVM,a fault-diagnosis system was set up for aviation-engine lubrication system.According to spectrum analysis and recognition of wear elements in lubrication oil,the char-acteristic vectors were extracted as the input signal of fuzzy SVM.Using the MATLAB script in LabVIEW based on the technology of Active,the fault diagnosis of the aviation-engine lubrication system was realized.The result of fault diagnosis of BP neural-network was compared with that of fuzzy SVM.The results show that fuzzy SVM method has a transparent superior in fault diagnosis with high speed and accuracy,the average rate of fault recognition can reach 95%.
出处
《润滑与密封》
CAS
CSCD
北大核心
2010年第3期90-95,共6页
Lubrication Engineering
