结合统计的模型辨识在发动机故障诊断中应用  

Application of pattern recognition with statistics for engine fault diagnosis

作　　者：朱大明[1] 朱之丽[1] 

机构地区：[1]北京航空航天大学能源与动力工程学院,北京100191

出　　处：《航空动力学报》2009年第5期1061-1065,共5页Journal of Aerospace Power

摘　　要：以一个双轴分排涡扇发动机为例,研究了数理统计和模型辨识组合方法诊断发动机双故障的可行性和效果.模型辨识法基于发动机性能仿真模型,在辨识的过程中利用了发动机平衡技术,考虑了模型的非线性.运用数理统计方法对辨识法得到的结果进行再处理,弥补了单纯以拟合程度为标准进行故障隔离的不足,定义和选择合适的故障指标,可以在多重故障模型下得到良好的故障隔离效果.A combined method of pattern recognition and statistics was examined to diagnose the double faults of a double-shaft dividually-exhausting turbofan engine.The pattern recognition is based on the engine performance simulation model.Balance technique of engine was used during recognition process and the non-linear characteristic was considered.The result got by pattern recognition was treated statistically,compensating the deficiency in fault isolation decided purely by comparability.The right fault index is ...

关 键 词：发动机 故障诊断 模型辨识 统计 

分 类 号：V263.6[航空宇航科学与技术—航空宇航制造工程]