基于自编码器和门限循环单元神经网络的滚动轴承退化趋势预测

PDF(1276 KB)

振动与冲击 ›› 2020, Vol. 39 ›› Issue (17) : 106-111.

论文

王鹏，邓蕾，汤宝平，韩延

作者信息 +

Degradation trend prediction of rolling bearing based on auto-encoder and GRU neural network

WANG Peng， DENG Lei， TANG Baoping， HAN Yan

Author information +

文章历史 +

摘要

针对现有滚动轴承性能退化趋势预测方法存在退化指标选取困难、预测精度较低的问题，提出基于自编码器和门限循环单元神经网络的滚动轴承退化趋势预测方法。首先，构建轴承振动信号混合域高维特征集，采用指标综合评价值初步筛选敏感性高、趋势性好的性能退化指标。然后，利用自编码器融合高维特征集，消除混合域特征之间的冗余信息。在此基础上，将融合后的特征输入门限循环单元神经网络模型以完成滚动轴承退化趋势预测。实验结果表明，本文所提方法能获得更加准确的滚动轴承退化趋势预测结果。

Abstract

It is difficult for the existing rolling bearing performance degradation trend prediction method to select the degradation index and its prediction accuracy is low. To address the problem, a prediction method of rolling bearing degradation trend based on self-encoder and GRU neural network is proposed. Firstly, the high-dimensional feature set of the mixed vibration domain of the bearing vibration signal is constructed, and the performance degradation index with high sensitivity and good trend is initially selected by using the comprehensive evaluation value of the index. Then, the self-encoder is used to fuse the high-dimensional feature set to eliminate the redundant information between the mixed domain features. On this basis, input the fused features into the GRU neural network model to complete the rolling bearing degradation trend prediction. The experimental results show that the proposed method can obtain more accurate prediction results of rolling bearing degradation trend.

导出引用

王鹏，邓蕾，汤宝平，韩延. 基于自编码器和门限循环单元神经网络的滚动轴承退化趋势预测[J]. 振动与冲击, 2020, 39(17): 106-111

WANG Peng， DENG Lei， TANG Baoping， HAN Yan. Degradation trend prediction of rolling bearing based on auto-encoder and GRU neural network[J]. Journal of Vibration and Shock, 2020, 39(17): 106-111

参考文献

[ 1 ] Lei Y G, Lin J, He Z J, et al. A review on empirical mode decomposition in fault diagnosis of rotating machinery [J]. Mechanical Systems and Signal Processing, 2013, 35(1–2):108-126.
[ 2 ] 张焱, 汤宝平, 韩延,等. 融合失效样本与截尾样本的滚动轴承寿命预测[J]. 振动与冲击, 2017, 36(23):10-16.
Zhang Yan, Tang Bao-ping, Han Yan, et al. Life prediction for rolling bearings utilizing both failure and truncated samples [J]. Journal of Vibration and Shock, 2017, 36(23):10-16.
[ 3 ] Shao H, Jiang H, Li X, et al. Rolling bearing fault detection using continuous deep belief network with locally linear embedding[J]. Computers in Industry, 2018, 96:27-39.
[ 4 ] 肖婷, 汤宝平, 秦毅,等. 基于流形学习和最小二乘支持向量机的滚动轴承退化趋势预测[J]. 振动与冲击, 2015, 34(9):149-153.
XIAO Ting, TANG Bao-ping, QIN Yi, et al. Prediction of Rolling Bearing Degradation Trend Based on Manifold Learning and Least Squares Support Vector Machine[J]. Journal of Vibration and Shock, 2015, 34(9): 149-153.
[ 5 ] Du S , Lv J , Xi L . Degradation process prediction for rotational machinery based on hybrid intelligent model[J]. Robotics and Computer-Integrated Manufacturing, 2012, 28(2):190-207.
[ 6 ] Dong S , Luo T . Bearing degradation process prediction based on the PCA and optimized LS-SVM model[J]. Measurement, 2013, 46(9):3143-3152.
[ 7 ] 赵申坤, 姜潮, 龙湘云. 一种基于数据驱动和贝叶斯理论的机械系统剩余寿命预测方法[J]. 机械工程学报, 2018, 54(12):115-124.
ZHAO Shen-kun, JIANG Chao, LONG Xiang-yun. Remaining Useful Life Estimation of Mechanical Systems Based on the Data-driven Method and Bayesian Theory [J]. Journal of Mechanical Engineering, 2018, 54(12): 115-124.
[ 8 ] 欧龙辉, 彭晓燕, 杨宇,等.GS-ASTFA方法及其在滚动轴承寿命预测中的应用[J]. 振动与冲击, 2017,36(11):14-19.
OU Long-hui, PENG Xiao-yan, YANG Yu, et al. GS-ASTFA Method and Its Application in life prediction of rolling bearings[J]. Journal of Vibration and Shock, 2017, 36(11):14-19.
[ 9 ] Guo L , Li N , Jia F , et al. A recurrent neural network based health indicator for remaining useful life prediction of bearings[J]. Neurocomputing, 2017, 240:98-109.
[ 10 ] Zhang B, Zhang S H, Li W H. Bearing performance degradation assessment using long short-term memory recurrent network[J]. Computers in Industry, 2019, 106:14-29.
[ 11 ] 赵建鹏, 周俊. 基于长短时记忆网络的旋转机械状态预测研究[J]. 噪声与振动控制, 2017,37(4):155-159.
ZHAO Jian-peng, ZHOU Jun. State Prognosis of Rotary Machines Based on Long and Short Term Memory Network[J]. Noise and Vibration Control, 2017,37(4):155-159.
[ 12 ] Javed K , Gouriveau R , Zerhouni N , et al. Enabling Health Monitoring Approach Based on Vibration Data for Accurate Prognostics[J]. IEEE Transactions on Industrial Electronics, 2015, 62(1):647-656.
[ 13 ] Lei Y , Li N , Guo L , et al. Machinery health prognostics: A systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing, 2018, 104:799-834.
[ 14 ] 骆志高, 张保刚, 何鑫. 基于BP神经网络的金属拉深件裂纹在线监测[J]. 振动与冲击, 2012, 31(10):102-105.
LUO Zhi-gao, ZHANG Bao-gang, He Xin. On-line crack monitoring of metal deep drawing parts based on BP neural network [J].Journal of Vibration and Shock, 2012, 31(10): 102-105.
[ 15 ] Qiu H , Lee J , Lin J , et al. Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics[J].Journal of Sound and Vibration, 2006, 289(4):1066-1090.