基于SVM和SNN的航空发动机气路故障诊断

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%.

Fault diagnosis of aero-engine gas path based on SVM and SNN

In order to distinguish similar faults of aero-engine gas path fault diagnosis and improve the diagnostic accuracy, a fault diagnosis method based on support vector machine(SVM) and synergetic neural network(SNN) was put forward. Firstly, the SVM after being optimized was used to diagnose and classify the faults preliminarily form measured data, and the diagnosis results were analyzed to obtain indistinguishable similar faults, then the SNN was introduced to distinguish similar faults and further determine corresponding fault model, finally this fault model was simulated based on actual data. The experimental results show that the preliminary fault diagnosis accuracy based on SVM is 96%, and after further distinguishing similar faults through SNN, the accuracy is increased to 100%.