基于IPSO-Elman神经网络的航空发动机故障诊断  

Aero-engine fault diagnosis based on IPSO-Elman neural network

作　　者：皮骏[1] 黄江博 

机构地区：[1]中国民航大学中欧航空工程师学院,天津300300 [2]中国民航大学航空工程学院,天津300300

出　　处：《航空动力学报》2017年第12期3031-3038,共8页Journal of Aerospace Power

基　　金：中央高校基本科研业务费中国民航大学专项资金(3122013H001)

摘　　要：为提高航空发动机故障诊断的精度,提出改进粒子群优化的Elman神经网络对航空发动机故障诊断的方法。利用MIV(平均影响值)对神经网络的输入端自变量进行筛选,降低输入维度;采用改进粒子群优化算法对Elman神经网络的权值和阀值进行优化,并对优化的神经网络进行训练;用训练好的神经网络对航空发动机故障进行诊断并与常规的BP(back propagation)、Elman神经网络、GM(1,n)、SVM(support vector machines)进行对比。仿真结果表明:IPSO-Elman(improved particle swarm optimization Elman neural network)神经网络的诊断误差在不同数量训练样本时都小于其他方法,并且在参选故障诊断的性能参数不同时,其诊断误差相近,展现出较强的适应能力。An Elman neural network optimized by improved particle swarm optimization algorithm was proposed to improve the accuracy of aero-engine fault diagnosis.The input variables of the neural network were selected by MIV（mean impact value）to reduce the dimension.The improved particle swarm optimization algorithm was used to optimize the weights and thresholds of the Elman neural network,and the optimized neural network was trained.The trained neural network was used to diagnose the aero-engine fault and compared with the conventional BP（back propagation）,Elman neural networks,GM（1,n）,SVM（support vector machines）.The simulation results show that the diagnostic error of IPSOElman（improved particle swarm optimization Elman neural network）is smaller than other methods,and it has a good diagnosis ability and strong adaptability when the selection fault diagnosis performance parameters have changed.

关 键 词：航空发动机 ELMAN神经网络 平均影响值 改进粒子群优化算法 故障诊断 

分 类 号：V231[航空宇航科学与技术—航空宇航推进理论与工程]