论文部分内容阅读
为了区分航空发动机气路故障诊断过程中出现的相似故障,提高诊断准确率,提出了一种支持向量机(SVM)和协同神经网络(SNN)相结合的故障诊断方法.首先利用参数优化后的SVM对测量数据进行初步故障诊断分类,对诊断结果进行分析统计,得出难以区分的相似故障类型,并根据SNN对这些相似故障进一步地区分判断,最后根据实际数据对此故障模型进行仿真.结果显示:基于SVM的初步故障诊断准确率达到96%;而经过SNN进一步地相似故障区分后,诊断准确率提升到100%.
In order to distinguish the similar faults in aeroengine fault diagnosis and improve the diagnostic accuracy, a fault diagnosis method based on Support Vector Machine (SVM) and Cooperative Neural Network (SNN) is proposed.Firstly, SVM classifies the initial fault diagnosis data and analyzes the diagnostic results to find out the similar types of faults that are indistinguishable. According to the SNN, these similar faults are further distinguished, and finally the fault model is simulated based on the actual data. It shows that the accuracy of the initial fault diagnosis based on SVM reaches 96%, and after the similar SNN fault is further distinguished, the diagnostic accuracy rate increases to 100%.