计算机科学 ›› 2022, Vol. 49 ›› Issue (11A): 211100122-7.doi: 10.11896/jsjkx.211100122
黄晓玲, 张德平
HUANG Xiao-ling, ZHANG De-ping
摘要： 基于深度学习的故障诊断方法在大数据发展的推动下逐渐成为近年来故障诊断领域的研究热点。但是在真实的工业领域,深度学习故障诊断仍存在两点局限性:1)早期故障特征微弱,故障信息提取不足;2)变工况下收集的故障数据分布不一致。这两点导致深度学习故障诊断存在故障识别率低、域适应性差的问题。为解决上述问题,提出了一种基于通道拆分CLAHE和自适应阈值残差网络的变工况故障诊断方法(FEResNet)。该方法从增强重要特征、删除冗余特征两个角度出发,首先对故障信号做Morlet小波变换,挖掘变工况下振动信号隐含的判别性时频信息;然后设计通道拆分的CLAHE方法,提高时频图的对比度和清晰度,增强故障特征;最后将特征增强后的时频图输入到设计的自适应阈值残差网络中进行训练,删除冗余特征。在CWRU数据集上的实验结果表明,该方法在同工况下的预测精度高达100%,在变工况下的平均预测精度高达99.03%,域适应性强。
中图分类号:
| [1]ZHAO W H,YAN W W.Research on data driven fault diagnosis[J].Microcomputer Information,2010,26(28):104-106. [2]ZHAO R,YAN R,CHEN Z,et al.Deeping Learning and Its Applications to Machine Health Monitoring:A Survey[J].arXiv:1612.07640,2016. [3]LI Y,KURFESS T R,LIANG S Y.Stochastic prognostics for rolling element bearings[J].Mechanical Systems and Signal Processing,2000,14(5):747-762. [4]OPPENHEIMER C H,LOPARO K A.Physically based diagnosis and prognosis of cracked rotor shafts[C]//Component and Systems Diagnostics,Prognostics,and Health Management II.International Society for Optics and Photonics,2002. [5]YU M,WANG D,LUO M.Model-Based Prognosis for Hybrid Systems With Mode-Dependent Degradation Behaviors[J].IEEE Transactions on Industrial Electronics,2013,61(1):546-554. [6]WIDODO A,YANG B S.Support vector machine in machine condition monitoring and fault diagnosis[J].Mechanical Systems & Signal Processing,2007,21(6):2560-2574. [7]MURALIDHARAN V,SUGUMARAN V.A comparative study of Nave Bayes classifier and Bayes net classifier for fault diagnosis of monoblock centrifugal pump using wavelet analysis[J].Applied Soft Computing,2012,12(8):2023-2029. [8]MALHI A,GAO R X.PCA-based feature selection scheme for machine defect classification[J].IEEE Transactions on Instrumentation and Measurement,2004,53(6):1517-1525. [9]LIU L,ZHU J C,HAN G J,et al.Bearing health monitoring and fault diagnosis based on 1D-CNN joint feature extraction[J].Journal Of Software,2021,32(8):2379-2390. [10]WEI Z,GAO L P,CHUANHAO L.Bearings Fault DiagnosisBased on Convolutional Neural Networks with 2-D Representation of Vibration Signals as Input[J].MATEC Web of Conferences,2017,95:13001. [11]HE K,ZHANG X,REN S,et al.Deep Residual Learning for Ima-ge Recognition[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition(CVPR).2016:770-778. [12]WEN L,LI X,GAO L.A transfer convolutional neural network for fault diagnosis based on ResNet-50[J].Neural Computing and Applications,2019,32(10):6111-6124. [13]ZHANG X H,GAO B P,WENG X L,et al.Application of Improved ResNet Network in the Diagnosis of Vibration Fault of Elevator Car[J].Modern Electronic Technology,2021,44(17):169-172. [14]ZHANG H,CISSE M,DAUPHIN Y N,et al.mixup:BeyondEmpirical Risk Minimization[J].arXiv:1710.09412,2017. [15]HOU Z L.Research Status and Development Prospects of Fault Diagnosis of Rotating Machinery [J].Mechanical Research and Application,2021,34(4):210-213. [16]GRINSTED A,MOORE J C,JEVREJEVA S.Application of thecross wavelet transform and wavelet coherence to geophysical time series[J].Nonlinear Processes in Geophysics,2004,11(5/6):561-566. [17]LIANG P F,DENG C ,WU J,et al.Intelligent fault diagnosis of rotating machinery via wavelet transform,generative adversarial nets and convolutional neural network[J].Measurement,2020,159:107768. [18]ZUIDERVELD K.Contrast Limited Adaptive Histogram Equali-zation[J].Graphics Gems,1994:474-485. [19]ZHANG P,WANG Y,WANG S S.Improved algorithm for low-contrast image enhancement based on CLAHE transform[J].Journal of Qingdao University(Engineering Technology Edition),2011,26(4):57-60. [20]SMITH W A,RANDALL R B.Rolling element bearing diagnostics using the Case Western Reserve University data:A benchmark study[J].Mechanical Systems and Signal Proces-sing,2015,64-65:100-131. [21]WEI Z,PENG G,LI C,et al.A New Deep Learning Model for Fault Diagnosis with Good Anti-Noise and Domain Adaptation Ability on Raw Vibration Signals[J].Sensors,2017,17(3):425. [22]WEI Z,LI C,PENG G,et al.A deep convolutional neural net-work with new training methods for bearing fault diagnosis under noisy environment and different working load[J].Mechanical Systems & Signal Processing,2017,100(FEB.1):439-453. [23]WAN L,CHEN Y,LI H,et al.Rolling-Element Bearing Fault Diagnosis Using Improved LeNet-5 Network[J].Sensors(Basel,Switzerland),2020,20(6):1693. |
|
||
首页