高彤,盛蔚,尹艳召,杜雪洁

• 1:北京航空航天大学仪器科学与光电工程学院
• 2:西安翔仪恒昌科技有限公司

摘要(Abstract)：

针对微机电系统(MEMS)惯性传感器温度诱导故障诊断任务，提出了一种基于最大平均差异(MMD)迁移学习的故障诊断方法，解决了离线样本充足而在线故障样本不足情况下的在线故障诊断问题。将MEMS惯性传感器在线故障诊断的问题转化为一个深度迁移学习问题，其中具有完整标签的离线样本作为迁移学习的源域，在线条件下的样本作为目标域；设计了基于多尺度卷积神经网络的故障模式识别方法；提出了一种基于MMD的迁移学习方法，将基于源域样本训练的模型迁移到目标域中，该方法采取了一种基于源域与目标域差异分析的半监督学习策略，使模型在目标域上获得满意的故障诊断性能。实验表明，提出的故障诊断方法较其他基于迁移学习的故障诊断方法在MEMS惯性传感器故障诊断任务中具有更好性能。

关键词(KeyWords)： 故障诊断;最大平均差异(MMD);迁移学习;卷积神经网络;MEMS惯性传感器

Abstract:

Keywords:

基金项目(Foundation): 国家自然科学基金(61274117)

作者(Author): 高彤,盛蔚,尹艳召,杜雪洁

参考文献(References)：

• [1] ROSSI M,BRUNELLI D.Autonomous Gas Detection and Mapping With Unmanned Aerial Vehicles[J].IEEE Transactions on Instrumentation & Measurement,2016,65(4):765-775.
• [2] BASKAYA E,BRONZ M,DELAHAYE D.Fault Detection & Diagnosis for Small UAVs via Machine Learning[C]// 2017 IEEE/AIAA 36th Digital Avionics Systems Conference (DASC),St.Petersburg,FL,USA.IEEE,2017.
• [3] ZHUT B,LU F.A Data-Driven Method of Engine Sensor on Line Fault Diagnosis and Recovery[J].Applied Mechanics and Materials,2014,490-491:1657-1660.
• [4] KORDESTANI M,SAMADI M F,SAIF M,et al.A New Fault Diagnosis of Multifunctional Spoiler System Using Integrated Artificial Neural Network and Discrete Wavelet Transform Methods[J].IEEE Sensors Journal,2018:1-1.
• [5] FRAVOLINI M L,NAPOLITANO M R,DEL CORE G,et al.Experimental interval models for the robust Fault Detection of Aircraft Air Data Sensors[J].Control Engineering Practice,2018,78:196-212.
• [6] XUYUN F U,CHEN H,ZHANG G,et al.A New Point Anomaly Detection Method About Aero Engine Based on Deep Learning[C]// 2018 International Conference on Sensing,Diagnostics,Prognostics,and Control (SDPC),Xi’an,China,2018.
• [7] GAO Z,MA C,SONG D,et al.Deep quantum inspired neural network with application to aircraft fuel system fault diagnosis[J].Neurocomputing,2017,238(MAY17):13-23.
• [8] HE Y,PENG Y,WANG S,et al.A Structured Sparse Subspace Learning Algorithm for Anomaly Detection in UAV Flight Data[J].IEEE Transactions on Instrumentation and Measurement,2017,67(1):90-100.
• [9] LECUN,Y.;BENGIO,Y.;HINTON,G.Deep learning[J].Nature,2015,521:436-444.
• [10] YAO Y,ZHANG S,YANG S,et al.Learning Attention Representation with a Multi-Scale CNN for Gear Fault Diagnosis under Different Working Conditions[J].Sensors (Basel,Switzerland),2020,20(4):1233-1253.
• [11] GUO D,ZHONG M,JI H,et al.A hybrid feature model and deep learning based fault diagnosis for unmanned aerial vehicle sensors[J].Neurocomputing,2018,319(30):155-163.
• [12] 代刚.MEMS-IMU误差分析补偿与实验研究[D].北京：清华大学，2011.
• [13] HAO R,YU H,PENG B,et al.Impacts of Residual Stress on Micro Vibratory Platform Used for Inertial Sensor Calibration[J].Sensors,2020,20(14):3959-3963.
• [14] DING X,HE Q.Energy-Fluctuated Multiscale Feature Learning With Deep ConvNet for Intelligent Spindle Bearing Fault Diagnosis[J].IEEE Transactions on Instrumentation and Measurement,2017,99:1-10.
• [15] WANG Z,DONG Y,LIU W,et al.A Novel Fault Diagnosis Approach for Chillers Based on 1-D Convolutional Neural Network and Gated Recurrent Unit[J].Sensors (Basel,Switzerland),2020,20(9):226-230.
• [16] CHEN S,GE H,LI J,et al.Correction to "Progressive Improved Convolutional Neural Network for Avionics Fault Diagnosis"[J].IEEE Access,2020,8:20012-20012.
• [17] GUO M F,YANG N C,CHEN W F.Deep-learning-based fault classification using Hilbert-Huang transform and convolutional neural network in power distribution systems[J].IEEE Sensors Journal,2019,19(16):6905-6913.
• [18] WEN L,LI X,GAO L,et al.A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method[J].IEEE Transactions on Industrial Electronics,2017,18(8):321-328.
• [19] LAN S,CHEN M J,CHEN D Y.A Novel HVDC Double-Terminal Non-Synchronous Fault Location Method Based on Convolutional Neural Network[J].IEEE Transactions on Power Delivery,2019,34(3):848-857.
• [20] RAMEZANI Z,POURDARVISH A.Transfer learning using Tsallis entropy:An application to Gravity Spy[J].Physica A:Statistical Mechanics and its Applications,2021,22(12):168-172.
• [21] TONG Z,LI W,ZHANG B,et al.Online Bearing Fault Diagnosis Based on a Novel Multiple Data Streams Transmission Scheme[J].IEEE Access,2019(99):1-9.
• [22] CHE C,WANG H,FU Q,et al.Deep transfer learning for rolling bearing fault diagnosis under variable operating conditions[J].Advances in Mechanical Engineering,2019,11(12):129-138.
• [23] TANG S,TANG H,CHEN M,et al.Transfer-learning based gas path analysis method for gas turbines[J].Applied Thermal Engineering,2019,34(12):1-13.
• [24] KLEIN V,MORELLI E A.Aircraft System Identification:Theory and Practice Volume 139 ||[J].2006,10.2514/4.861505.
• [25] GAO T,SHENG W,ZHOU M,et al.Method for Fault Diagnosis of Temperature-Related MEMS Inertial Sensors by Combining Hilbert-Huang Transform and Deep Learning[J].Sensors,2020,20(19):5633-5639.
• [26] XIAO D,HUANG Y,ZHAO L,et al.Domain Adaptive Motor Fault Diagnosis Using Deep Transfer Learning[J].IEEE Access,2019,31(7):80937-80949.
• [27] WU Z,JIANG H,ZHAO K,et al.An adaptive deep transfer learning method for bearing fault diagnosis[J].Measurement,2020,151(18):1-14.