| 0 | 0 | 0 |
| Downloads | Citas | Reads |
针对滚动轴承不同损伤位置与程度的多状态识别困难问题，提出了一种基于EEMD包络谱和JS—SDAE的轴承故障诊断方法。首先，利用EEMD将轴承信号分解，保留与原信号高相关的本征模态函数；其次，用所选分量的包络谱构建高维特征作为网络的输入；最后，降维后输入经人工水母优化算法结构优化后的SDAE,完成轴承多类别故障识别。试验表明，将10类特征数据输入SDAE进行学习后，EEMD包络谱相比时域信号更能体现出故障特征，且JS-SDAE网络相比决策树、贝叶斯、网格搜索优化贝叶斯、SVM、贝叶斯优化SVM、KNN、贝叶斯优化KNN等算法具有更高的准确性。采用QPZZ-Ⅱ系统采集实验平台所采集的数据进行验证，结果表明模型测试集的准确率达到了96.7%。
Abstract：In order to solve the problem of difficulty in identifying multiple states of different damage positions and degrees of rolling bearings, a bearing fault diagnosis method based on Ensemble Empirical Mode Decomposition(EEMD) envelope spectrum and artificial Jellyfish Search(JS) optimizer-SDAE(Stacked Denoising Auto Encoder) was proposed. Firstly, EEMD was used to decompose the bearing signal to retain the intrinsic mode function(IMF) that correlates with the original signal height. Secondly, the envelope spectrum of the selected components is used to construct high-dimensional features as the input of the network. Finally, the dimensionality reduction was input into the SDAE optimized by the artificial jellyfish optimization algorithm to complete the multi-class fault identification of the bearing. Experiments show that after 10 types of feature data are input into SDAE for learning, the EEMD envelope spectrum can better reflect the fault characteristics than the time-domain signal. Moreover, the JS-SDAE network has higher accuracy than the decision tree, Bayesian, grid search optimized Bayesian, SVM, Bayesian optimized SVM, KNN, Bayesian optimized KNN and other algorithms. The data collected by the QPZZ-II system acquisition experiment platform were used for verification, and the results show that the model test set reaches an accuracy rate of 96.7%.
[1]王亚萍，李士松，葛江华，等.等距离映射和模糊C均值的滚动轴承故障识别[J].哈尔滨理工大学学报，2019,24(3):41-47.WANG Y P,LI S S,GE J H,et al.Rolling bearing with isometric feature mapping and fuzzy c-means fault identification method[J].Journal of Harbin University of Science and Technology,2019,24(3):41-47.
[2]柳秀，马善涛，谢怡宁，等.面向轴承故障诊断的深度学习方法[J].哈尔滨理工大学学报，2022,27(4):118-124.LIU X,MA S T,XIE Y N,et al.Deep learning method for bearing fault diagnosis [J].Journal of Harbin University of Science and Technology,2022,27(4):118-124.
[3]LEI Y G,LI N P,LIN J,et al.Fault diagnosis of rotating machinery based on an adaptive ensemble empirical mode decomposition [J].Sensors,2013,13(12):286-294.
[4]职保平，秦净净，杨春景，等.基于EEMD-SOBI的水电机组多源信息分离处理[J].振动与冲击，2023,42(4):229-235.ZHI B P,QIN J J,YANG C J,et al.Separation and processing of multi-source information of hydropower units based on EEMD-SOBI[J].Journal of Vibration and Shock,2023,42(4):229-235.
[5]李东炎，李常贤.基于动态PSO-MCKD-HHT的滚动轴承故障诊断方法研究与应用[J].电子测量技术，2021,44(21):12-18.LI D Y,LI C X.Research and application of fault diagnosis method for rolling bearings based on dynamic PSO-MCKD-HHT[J].Electronic Measurement Technology,2021,44(21):12-18.
[6]陈龙，张纯龙.基于EMD包络谱特征与PCA-PNN的滚动轴承故障诊断[J].煤矿机械，2022,43(10):173-176.CHEN L,ZHANG C L.Fault diagnosis of rolling bearings based on EMD envelope spectrum characteristics and PCA-PNN[J].Coal Mining Machinery,2022,43(10):173-176.
[7]HAN T,ZHANG LW,YIN Z J,et al.Rolling bearing fault diagnosis with combined convolutional neural networks and support vector machine[J].Measurement,2021,177:109022.
[8]QUAN Z Y ,ZHANG X L.Rolling bearing fault diagnosis based on CS-optimized multiscale dispersion entropy and ML-KNN[J].Journal of the Brazilian Society of Mechanical Sciences and Engineering,2022,44(9):430.
[9]HUANG X F,ZHOU F T,NIU W H,et al.Multi-stage affine motion estimation fast algorithm for versatile video coding using decision tree[J].Journal of Visual Communication and Image Representation,2023,96:103910.
[10]MA X R,LIN Y Z,NIE Z H,et al.Structural damage identification based on unsupervised feature-extraction via variational auto-encoder[J].Measurement,2020,160:107811.
[11]HE J,OUYANG M,YONG C,et al.A novel intelligent fault diagnosis method for rolling bearing based on integrated weight strategy features learning[J].Sensors,2020,20(6):1774.
[12]昌小昕.基于粒子群优化的深度自编码器在滚动轴承故障诊断中的应用[D].石家庄：石家庄铁道大学，2022.CHANG X X.Application of deep autoencoder based on particle swarm optimization in rolling bearing fault diagnosis[D].Shijiazhuang:Shijiazhuang Tiedao University,2022.
[13]涂福泉，陈超.基于特征增强与深度学习的轴承故障诊断[J] .矿山机械，2023,51(3):57-63.TU F Q,CHEN C.Bearing fault diagnosis based on feature enhancement and deep learning[J] .Mining Machinery,2023,51(3):57-63.
[14]VINCENT P,LAROCHELLE H,LAJOIE I,et al.Stacked denoising autoencoders:learning useful representations in a deep network with a local denoising criterion[J].Journal of Machine Learning Research,2010,11(12):3371-3408.
[15]万若青，张纯，江汇强，等.基于深度自编码器的振动信号盲去噪方法[J].振动与冲击，2023,42(12):118-125.WAN R Q,ZHANG C,JIANG H Q,et al.A blind denoising method of vibration signals based on a deep autoencoder[J].Vibration & Shock,2023,42(12):118-125.
[16]ARABLOUEI R,WERNER S,GANCAY K.Analysis of the gradient-descent total least-squares adaptive filtering algorithm[J].IEEE Transactions on Signal Processing,2014,62(5):1256-1264.
[17]陈尚年，李录平，张世海，等.基于EEMD-LSTM的汽轮机转子碰磨故障诊断模型及其工程应用[J].热能动力工程，2023,38(8):159-168.CHEN S N,LI L P,ZHANG S H,et al.Fault diagnosis model of steam turbine rotor grinding based on EEMD-LSTM and its engineering application[J].Thermal and Power Engineering,2023,38(8):159-168.
[18]CHOU J S,TRUONG D N.A novel metaheuristic optimizer inspired by behavior of jellyfish in ocean[J] .Applied Mathematics and Computation,2021,389:125535.
[19]杜先君，贾亮亮.基于优化堆叠降噪自编码器的滚动轴承故障诊断[J].吉林大学学报 (工学版) ,2022,52(12):2827-2838.DU X J,JIA L L.Fault diagnosis of rolling bearings based on optimized stacked noise reduction autoencoder[J].Journal of Jilin University(Engineering Science) ,2022,52(12):2827-2838.
Basic Information:
DOI：10.13291/j.cnki.djdxac.2025.04.005
China Classification Code:TH133.33;TP18
Citation Information:
[1]苑宇,郭琦.基于EEMD包络谱和JS-SDAE的轴承故障诊断[J].大连交通大学学报,2025,46(04):49-56+82.DOI:10.13291/j.cnki.djdxac.2025.04.005.
Fund Information:
国家自然科学基金项目(62001079); 辽宁省教育厅基金项目(JDL2020013)