改进降噪自编码的航空发动机气路故障诊断  

Gas Path Fault Diagnosis for Aero-engine Based on Improved Denoising Autoencoder

作　　者：洪骥宇 王华伟 车畅畅 倪晓梅 HONG Jiyu;WANG Huaxvei;CHE Changchang;NI Xiaomei(College of Civil Aviation, Nanjing University of Aeronautics and Astronautics Nanjing, 210016, China)

机构地区：[1]南京航空航天大学民航学院

出　　处：《振动．测试与诊断》2019年第3期603-610,675,共9页Journal of Vibration,Measurement & Diagnosis

基　　金：国家自然科学基金资助项目(71401073);国家自然科学基金与中国民航局联合资助项目(U1233115);江苏省研究生培养创新工程资助项目(SJZZ16_0060)

摘　　要：为提高故障诊断准确度,针对航空发动机气路故障中状态参数非线性强且易受噪声污染的问题,提出一种改进降噪自编码的航空发动机气路诊断方法。该方法在降噪自编码器(denoising autoencoder,简称DAE)基础上,采用改进萤火虫算法(firefly algorithm,简称FA)优化的径向基(radial basis function,简称RBF)神经网络,进行航空发动机故障诊断,DAE能够提取出更利于故障诊断的深层鲁棒特征。为了进一步提高算法的诊断准确度,引入惯性权重与自适应光强因子的改进FA来优化RBF网络从而得到萤火虫径向基(firefly radial basis function,简称FRBF)网络,再将DAE提取的特征导入其中进行故障诊断。通过实例,将提出方法与原始DAE、单独的FRBF、支持向量机(support vector machine,简称SVM)和RBF这4种算法进行对比,结果表明,所提出方法诊断精度最高,达到98.1%,且算法性能稳定,鲁棒性也优于其他几种方法。Considering the state parameters significant nonlinearity and the vulnerability to noise pollution in the aero-engine gas path faults,a method based on denoising autoencoder(DAE)and integrated with a neural networks of firefly algorithm(FA)and radial basis function(RBF)is proposed to diagnose the gas path faults and improve the diagnostic accuracy.The DAE is adopted through greedy algorithms to identify deeper robust features that helps diagnose the faults.To further improve the diagnostic accuracy of the algorithm,inertia weight and improved FA of self-adaptive light intensity factor are introduced to obtain the firefly radial basis function(FRBF)network after optimizing the RBF network.Then the robust features extracted from the DAE are imported into the FRBF for faults diagnosis.Based on practices,the extracting method is compared with the algorithms which are original DAE,independent FRBF,SVM and RBF.According to the results,the proposed method presents highest diagnostic accuracy of 98.1%,stable performance in the algorithms and more satisfying robustness.

关 键 词：航空发动机 故障诊断 降噪自编码 萤火虫算法 径向基网络 

分 类 号：TH17[机械工程—机械制造及自动化] TK14[动力工程及工程热物理—热能工程]