1.重庆交通大学 交通运输学院, 重庆 400074
2.重庆工商大学 管理科学与工程学院, 重庆 400067
黎政(1995— ),男,重庆人,硕士研究生;研究方向为智能算法及信号处理。
吴胜利(1983— ),男,河南南阳人,博士,副教授;研究方向为设备状态监测及信号处理。
扫 描 看 全 文
黎政,吴胜利,邢文婷等.基于MGAN和CNN的齿轮故障智能诊断方法[J].机械传动,2022,46(07):144-151.
Li Zheng,Wu Shengli,Xing Wenting,et al.Intelligent Diagnosis Method of Gear Faults based on MGAN and CNN[J].Journal of Mechanical Transmission,2022,46(07):144-151.
黎政,吴胜利,邢文婷等.基于MGAN和CNN的齿轮故障智能诊断方法[J].机械传动,2022,46(07):144-151. DOI: 10.16578/j.issn.1004.2539.2022.07.022.
Li Zheng,Wu Shengli,Xing Wenting,et al.Intelligent Diagnosis Method of Gear Faults based on MGAN and CNN[J].Journal of Mechanical Transmission,2022,46(07):144-151. DOI: 10.16578/j.issn.1004.2539.2022.07.022.
针对实际工程中采集的齿轮故障信号样本不足,以及在噪声干扰的情况下采用常见深度学习网络进行模式识别出现的训练不足、故障识别率低和生成对抗网络易发生模式坍塌等问题,提出了一种基于MGAN(Mixture generative adversarial nets)和CNN(Convolutional neural networks)的齿轮故障智能诊断方法。将真实齿轮信号经形态学滤波处理后通过时频变换技术转变为时频信号,利用MGAN网络合成新样本来获得一个平衡数据集,克服了样本不足的问题;同时,分析了MGAN网络主要参数对合成样本质量的影响规律;采用平衡数据集训练CNN进行故障诊断,有效提高了故障诊断率。通过对比试验和试验台试验,验证了该方法在样本不足条件下对故障进行准确识别以及克服神经网络模式坍塌方面的有效性及优势,为实现齿轮箱典型故障提取及智能识别提供了新的研究思路。
Aiming at the problems of insufficient samples of gear fault signals collected in practical engineering,insufficient training,low fault recognition rate and easy pattern collapse of generative adversarial networks when using common deep learning network for pattern recognition under noise interference. An intelligent diagnosis method of gear faults based on MGAN (Mixture Generative Adversarial Nets) and CNN (Convolutional Neural Networks) is proposed. The real gear signals are transformed into time-frequency signals by time-frequency transformation technology after morphological filtering,and new samples are synthesized by MGAN to obtain a balanced data set,which overcomes the problem of insufficient samples. At the same time,the influence law of main parameters of MGAN on the quality of synthesized samples is analyzed. The balanced data set is used to train CNN for fault diagnosis,which effectively improves the fault diagnosis rate. Through the comparative test and bench test,the effectiveness and advantages of this method in accurately identifying faults and overcoming the collapse of neural network mode under the condition of insufficient samples are verified,which provides a new research idea for typical fault extraction and intelligent identification of gearboxes.
生成对抗网络模式坍塌样本不足故障诊断
Generative adversarial networkModel collapseInsufficient samplesFault diagnosis
徐文博,任亚峰,韩冰.一种基于深度学习理论的齿轮系统故障诊断方法[J].机械传动,2020,44(8):78-83.
XU Wenbo,REN Yafeng,HAN Bing.A fault diagnosis approach of gear system based on deep learning theory[J].Journal of Mechanical Transmission, 2020,44(8):78-83.
何强,唐向红,李传江,等.负载不平衡下小样本数据的轴承故障诊断[J].中国机械工程,2021,32(10):1164-1171.
HE Qiang,TANG Xianghong,LI Chuanjiang,et al.Research on bearing fault diagnosis method based on small sample data under unbalanced load[J].China Mechanical Engineering,2021,32(10):1164-1171.
赵磊,郭瑜,伍星.基于包络加窗同步平均的行星齿轮箱特征提取[J].振动测试与诊断,2019,39(2):320-326.
ZHAO Lei,GUO Yu,WU Xing.Fault feature extraction of planetary gearboxes based on angle domain windowed synchronous average of the envelope signal[J].Journal of Vibration,Measurement & Diagnosis,2019,39(2):320-326.
CAO C J,WANG Z.Imcstacking:cost-sensitive stacking learning with feature inverse mapping for imbalanced problems[J].Knowledge-Based Systems,2018,150:27-37.
CORDON I,GARCIA S,FERNANDEZ A,et al.Imbalance:oversampling algorithms for imbalanced classification in R[J].Knowledge-Based Systems,2018,161:329-341.
GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al.Generative adversarial nets[C]//Neural Information Processing Systems.Cambridge:MIT Press,2014:2672-2680.
马波,蔡伟东,赵大力.基于GAN样本生成技术的智能诊断方法[J].振动与冲击,2020,39(18):153-160.
MA Bo,CAI Weidong,ZHAO Dali.Intelligent diagnosis method based on GAN sample generation technology[J].Journal of Vibration and Shock,2020,39(18):153-160.
WANG Z R,WANG J,WANG Y R.An intelligent diagnosis scheme based on generative adversarial learning deep neural networks and its application to planetary gearbox fault pattern recognition[J].Neurocomputing,2018,310(8):213-222.
HUSZAR F.How(not) to train your generative model:scheduled sampling,likelihood,adversary?[J].Computer Science,2015:1-9.
THEIS L,OORD A,BETHGE M.A note on the evaluation of generative models[J].Computer Ence,2016:1-10.
ARJOVSKY M,CHINTALA S,BOTTOU L.Wasserstein GAN[J].Machine Learning,2017:1-32.
ZHU J Y,PARK T,ISOLA P,et al.Unpaired image-to-image translation using cycle-consistent adversarial networks[C]//2017 IEEE International Conference on Computer Vision(ICCV),October 22-29,2017,Venice.New York:IEEE,2017:2223-2232.
GHOSH A,KULHARIA V,NAMBOODIRI V P,et al.Multi-agent diverse generative adversarial networks[C]//IEEE/CVF Conference on Conputer Vision and Pattern Recognition,June 18-23,2018,Salt Lake City.New York:IEEE,2018:8513-8521.
QUAN H,TU D N,LE T,et al.Mgan:Training generative adversarial nets with multiple generators[C]//ICLR 2018 Conferencr Acceptance Decision,2018:1-23.
RADFORD A,METZ L,CHINTALA S.Unsupervised representation learning with deep convolutional generative adversarial networks[J].Computer Ence,2015:1-16.
0
浏览量
3
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构