基于自适应VMD和DD-cCycleGAN的滚动轴承剩余寿命预测

PDF(2435 KB)

振动与冲击 ›› 2024, Vol. 43 ›› Issue (13) : 45-52.

论文

于军1,2，赵坤1，张帅3，邓四二4

作者信息 +

RUL prediction of rolling bearing based on adaptive VMD and DD-cCycleGAN

YU Jun1,2, ZHAO Kun1, ZHANG Shuai3, DENG Si’er4

Author information +

文章历史 +

摘要

为准确预测强噪声干扰小样本情况下的滚动轴承剩余寿命(remaining useful life, RUL)，提出一种基于自适应变分模态分解(Variational mode decomposition, VMD)和双判别器条件循环一致对抗网络(Double-discriminator conditional CycleGAN, DD-cCycleGAN)的滚动轴承RUL预测方法。将黑猩猩优化算法(Chimp optimization algorithm, ChOA)与VMD相结合，给出一种基于ChOA的自适应VMD算法，选取有效模态分量进行重构，降低强背景噪声的干扰；开发一种DD-cCycleGAN生成新样本，这些生成的新样本不但保留了源域的样本信息，还与目标域的样本相似；将训练样本的重构样本和生成的新样本作为输入，训练长短时记忆(Long short-term memory, LSTM)网络，用训练后的LSTM网络预测测试样本中滚动轴承的RUL。通过采用XJTU-SY滚动轴承加速寿命试验数据集验证该方法的有效性，试验结果表明该方法具有较强的抗噪能力和较高的轴承RUL预测精度。

Abstract

In order to accurately predict the remaining useful life (RUL) of rolling bearings under strong noise interference and small samples, a RUL prediction method of rolling bearings based on adaptive variational mode decomposition (VMD) and double-discriminator conditional CycleGAN (DD-cCycleGAN) is put forward. Combining chimp optimization algorithm (ChOA) with VMD, an adaptive VMD algorithm based on ChOA is presented, which selects effective mode components for reconstruction and reduces interference from strong background noise. A DD-cCycleGAN is developed to generate new samples which not only retain sample information from the source domain, but also resemble samples from the target domain. A long short-term memory (LSTM) network is trained by using the reconstructed samples of training samples and the generated new samples. The LSTM network after training is used to predict the RUL of rolling bearings in test samples. The effectiveness of this method was verified by using the XJTU-SY rolling bearing accelerated life test dataset. The experimental results show that this method possesses strong noise resistance and high accuracy in the bearing RUL prediction.

导出引用

于军1,2，赵坤1，张帅3，邓四二4. 基于自适应VMD和DD-cCycleGAN的滚动轴承剩余寿命预测[J]. 振动与冲击, 2024, 43(13): 45-52

YU Jun1,2, ZHAO Kun1, ZHANG Shuai3, DENG Si’er4. RUL prediction of rolling bearing based on adaptive VMD and DD-cCycleGAN[J]. Journal of Vibration and Shock, 2024, 43(13): 45-52

参考文献

[1] 王鹏程，邓艾东，凌峰, 等. 基于PSO-SEBD的风电机组滚动轴承故障诊断 [J]. 振动与冲击, 2023, 42(7): 281-288. WANG Pengcheng, DENG Aidong, LING Feng, et al. Fault diagnosis of rolling bearing of wind turbine generator based on PSO-SEBD [J]. Journal of Vibration and Shock, 2023, 42(7): 281-288. [2] 张伟涛，崔丹，刘璐, 等. 宽转速范围下的航发主轴轴承故障诊断方法 [J]. 振动与冲击, 2023, 42(5): 253-262. ZHANG Weitao, CUI Dan, LIU Lu, et al. Fault diagnosis method of aero engine main shaft rolling bearing in wide rotating speed range [J]. Journal of Vibration and Shock, 2023, 42(5): 253-262. [3] ZHAO W, ZHANG C, FAN B, et al. Research on rolling bearing virtual-real fusion life prediction with digital twin [J]. Mechanical Systems and Signal Processing, DOI: 10.1016/j.ymssp.2023.110434. [4] CHEN Y, HUANG R, CHEN Z, et al. Transfer learning algorithms for bearing remaining useful life prediction: A comprehensive review from an industrial application perspective [J]. Mechanical Systems and Signal Processing, 2023, 193: 110239. [5] 蒋全胜，许伟洋，朱俊俊, 等. 基于动态加权卷积长短时记忆网络的滚动轴承剩余寿命预测方法 [J]. 振动与冲击, 2022, 41(17): 282-291. JIANG Quansheng, XU Weiyang, ZHU Junjun, et al. Residual life prediction method of rolling bearing based on DW-CNN-LSTM networks [J]. Journal of Vibration and Shock, 2022, 41(17): 282-291. [6] DU X, JIA W, YU P, et al. A remaining useful life prediction method based on time-frequency images of the mechanical vibration signals [J]. Measurement, 2022, 202: 111782. [7] YAN T, WANG D, SUN S, et al. Novel sparse representation degradation modeling for locating informative frequency bands for machine performance degradation assessment [J]. Mechanical Systems and Signal Processing, 2022, 179: 109372. [8] ZHANG Y, SUN J, ZHANG J, et al. Health state assessment of bearing with feature enhancement and prediction error compensation strategy [J]. Mechanical Systems and Signal Processing, 2023, 182: 109573. [9] CHENG J, YANG Y, WANG P, et al. Bearing fault feature extraction method: improved weighted envelope spectrum [J]. Measurement Science and Technology, 2023, 34(9): 095118. [10] TANG J, ZHENG G, HE D, et al. Rolling bearing remaining useful life prediction via weight tracking relevance vector machine [J]. Measurement Science and Technology, 2021, 32(2): 024006. [11] CHE C, WANG H, NI X, et al. Multi-head self-attention bidirectional gated recurrent unit for end-to-end remaining useful life prediction of mechanical equipment [J]. Measurement Science and Technology, 2022, 33(11): 115115. [12] ZHAO H, ZHANG P, ZHANG R, et al. A novel performance trend prediction approach using ENBLS with GWO [J]. Measurement Science and Technology, 2023, 34(2): 025018. [13] LAN X, LI Y, SU Y, et al. Performance degradation prediction model of rolling bearing based on self-checking long short-term memory network [J]. Measurement Science and Technology, 2023, 34(1): 015016. [14] ZHAO W, ZHANG C, WANG J, et al. Research on main bearing life prediction of direct-drive wind turbine based on digital twin technology [J]. Measurement Science and Technology, 2023, 34(2): 025013. [15] SHI M, DING C, QUE H, et al. Multilayer-graph-embedded extreme learning machine for performance degradation prognosis of bearing [J]. Measurement, 2023, 207: 112299. [16] WU Y, ZHAO R, MA H, et al. Adversarial domain adaptation convolutional neural network for intelligent recognition of bearing faults [J]. Measurement, 2022, 195: 111150. [17] DRAGOMIRETSKIY K, ZOSSO D. Variational mode decomposition [J]. IEEE Transactions on Signal Processing, 2014, 62(3): 531-544. [18] 任良，甄龙信，赵云, 等. 基于SSA-VMD-MCKP的强背景噪声环境下滚动轴承故障诊断 [J]. 振动与冲击, 2023, 42(3): 217-226. REN Liang, ZHEN Longxin, ZHAO Yun, et al. Fault diagnosis of rolling bearing under strong background noise based on SSA-VMD-MCKD [J]. Journal of Vibration and Shock, 2023, 42(3): 217-226. [19] ZHU J, PARK T, ISOLA P, et al. Unpaired image-to-image translation using cycle-consistent adversarial networks [C] // Proceedings of IEEE International Conference on Computer Vision, Venice, Italy. 2017. [20] KHISHE M, MOSAVI M R. Chimp optimization algorithm [J]. Expert systems with applications, 2020, 149: 113338. [21] 张爽，王晓东，李祥, 等. 基于FVMD的滚动轴承故障特征提取方法 [J]. 振动与冲击, 2022, 41(6): 236-244. ZHANG Shuang, WANG Xiaodong, LI Xiang, et al. Extraction method of rolling bearing fault characteristics based on FVMD [J]. Journal of Vibration and Shock, 2022, 41(6): 236-244. [22] MIRZA M, OSINDERO S. Conditional generative adversarial nets[J]. Computer Science, 2014: 2672-2680. [23] 雷亚国，韩天宇，王彪, 等. XJTU-SY滚动轴承加速寿命试验数据集解读 [J]. 机械工程学报, 2019, 55(16): 1-6. LEI Yaguo, HAN Tianyu, WANG Biao, et al. XJTU-SY rolling element bearing accelerated life test datasets: a tutorial [J]. Journal of Mechanical Engineering, 2019, 55(16): 1-6.