基于全卷积层神经网络的轴承剩余寿命预测

摘要/Abstract

摘要： 传统的数据驱动的轴承剩余寿命预测方法需要基于知识和经验，通过人工建立性能退化指标，费时费力，为此，采用卷积神经网络对输入信号进行特征自学习和剩余寿命预测。将传统卷积神经网络中的全连接层全部更换为卷积层与池化层，以减少神经网络需训练的参数；采用加权平均方法对预测结果进行降噪处理。轴承加速寿命实验数据集验证了所提方法的有效性。

关键词: 全卷积层, 神经网络, 轴承, 剩余寿命预测

Abstract: Traditional method of data-driven bearing remaining life prediction was based on knowledge and experience, and the degradation index was established manually which was time-consuming and labor-intensive. Therefore, the convolutional neural network (CNN) was used to perform feature self-learning and remaining life prediction. All connected layers in the traditional CNN were replaced with convolutional layers and pooling layers to reduce the training parameters of the neural network. Weighted average method was used to denoise the prediction results. Dataset of the accelerated life test of the bearings shows the effectiveness of the proposed method.

Key words: full convolutional layer, neural network, bearing, remaining life prediction

中图分类号:

TH133

张继冬;邹益胜;邓佳林;张笑璐. 基于全卷积层神经网络的轴承剩余寿命预测[J]. 中国机械工程.

ZHANG Jidong;ZOU Yisheng;DENG Jialin;ZHANG Xiaolu. Bearing Remaining Life Prediction Based on Full Convolutional Layer Neural Networks[J]. China Mechanical Engineering.

参考文献

[1]LI N P, LEI Y G, LIN J, et al. An Improved Exponential Model for Predicting Remaining Useful Life of Rolling Element Bearings[J]. IEEE Trans. Industr. Electron., 2015, 62：7762-7773.
[2]王冰, 李洪儒, 许葆华. 基于多尺度形态分解谱熵的电机轴承预测特征提取及退化状态评估[J]. 振动与冲击, 2013, 32(22):124-128.
WANG Bing, LI Hongru, XU Baohua. Motor Bearing Forecast Feature Extracting and Degradation Status Identification Based on Multi-scale Morphological Decomposition Spectral Entropy[J]. Journal of Vibration and Shock, 2013, 32(22):124-128.
[3]李洪儒,于贺,田再克,等. 基于二元多尺度熵的滚动轴承退化趋势预测[J]. 中国机械工程, 2017, 28(20)：2420-2425.
LI Hongru, YU He, TIAN Zaike, et al. Degradation Trend Prediction of Rolling Bearing Based on Two-element Multiscale Entropy[J]. China Mechanical Engineering, 2017, 28(20):2420-2425.
[4]WANG F, SUN J, YAN D, et al. A Feature Extraction Method for Fault Classification of Rolling Bearing Based on PCA[J]. Journal of Physics：Conference Series, 2015, 628：012079.
[5]王建利. 滚动轴承性能退化评价与趋势预测研究[D]. 大连：大连理工大学, 2013.
WANG Jianli, Research on Performance Degradation Assessment and Trend Prediction of Rolling Bearing[D]. Dalian：Dalian University of Technology, 2013.
[6]高斯博. 基于退化数据的寿命预测中估计问题研究[D]. 大连：大连理工大学, 2016.
GAO Sibo. Estimation Research in Remaining Useful Life Prediction Driven by Statistical Data[D]. Dalian：Dalian University of Technology, 2016.
[7]LIU Z, LI Q, MU C. A Hybrid LSSVR-HMM Based Prognostics Approach[J]. Sensors, 2013, 13(5):5542-5560.
[8]申中杰，陈雪峰，何正嘉. 基于相对特征和多变量支持向量机的滚动轴承剩余寿命预测[J]. 机械工程学报, 2013, 49 (2):183-189.
SHEN Zhongjie, CHEN Xuefeng, HE Zhengjia. Remaining Life Predictions of Rolling Bearing Based on Relative Features and Multivariable Support Vector Machine[J]. Journal of Mechanical Engineering, 2013, 49 (2):183-189.
[9]陈法法, 杨勇, 陈保家,等. 基于模糊信息粒化与小波支持向量机的滚动轴承性能退化趋势预测[J]. 中国机械工程, 2016, 27(12):1655-1661.
CHEN Fafa, YANG Yong, CHEN Baojia, et al. Degradation Trend Prediction of Rolling Bearing Based on Fuzzy Information Granulation and Wavelet Support Vector Machine[J]. China Mechanical Engineering, 2016, 27(12):1655-1661.
[10]LECUN Y, BENGIO Y, HINTON G. Deep Learning[J]. Nature, 2015, 521(7553):436-444.
[11]NECTOUX P, GOURIVEAU R, MEDJAHER K, et al. PRONOSTIA：An Experimental Platform for Bearings Accelerated Degradation Tests[C]∥IEEE International Conference on Prognostics and Health Management. Denver, 2012:1-8.
[12]雷亚国. 旋转机械智能故障诊断与剩余寿命预测[M]. 西安：西安交通大学出版社, 2017：294-299.
LEI Yaguo. Intelligent Fault Diagnosis and Remaining Useful Life Prediction of Rotating Machinery[M]. Xi'an：Xi'an Jiaotong University Press, 2017：294-299.
[13]GUO L, LEI Y G, LI N P, et al. Deep Convolution Feature Learning for Health Indicator Construction of Bearings[C]∥Prognostics and System Health Management Conference. Harbin, 2017:1-6.

[1]	李小力, 陈威, 闫蓉. 基于BP神经网络的空间轮廓误差自适应补偿 [J]. J4, 201016, 21(16): 1902-1906.
[2]	胡超, 刘佐民. 基于材料匹配性的球轴承Heathcote黏-滑模型研究 [J]. J4, 201016, 21(16): 1969-1973.
[3]	赵伟, 王志远, 周志立. 载重汽车连续下坡弯道路段制动稳定性仿真研究 [J]. J4, 201016, 21(16): 2010-2015.
[4]	李胜远, 郑龙席. 磁轴承激励下转子系统动力学特性[J]. 中国机械工程, 2021, 32(08): 901-907.
[5]	郑近德, 王兴龙, 潘海洋, 童靳于, 刘庆运. 基于自适应自相关谱峭度图的滚动轴承故障诊断方法[J]. 中国机械工程, 2021, 32(07): 778-785，792.
[6]	陈换过, 刘培君, 俞杭, 肖雪. 基于改进PCA-SOM的电静压伺服作动器油滤堵塞故障诊断[J]. 中国机械工程, 2021, 32(07): 799-805.
[7]	王玉龙, 裴锋, 刘文如, 闫春香, 周卫林, 李智. 基于开关式深度神经网络的拟人化自动驾驶决策算法[J]. 中国机械工程, 2021, 32(06): 689-696.
[8]	李冰1;张永德1;袁立鹏2;朱光强3;代雪松1;苏文海3. 液压四足机器人足端的力预测控制与运动平稳性[J]. 中国机械工程, 2021, 32(05): 523-532.
[9]	王瑞1；贾谦1,2；袁小阳1. 石墨水润滑动压推力轴承的起飞转速及磨损的量化研究[J]. 中国机械工程, 2021, 32(03): 269-274.
[10]	郭保苏；庄集超；章钦；吴凤和. 基于多分量卷积神经网络的多晶硅晶片颜色差异检测[J]. 中国机械工程, 2021, 32(03): 297-304.
[11]	钟百鸿；王琳；钟诗胜. 基于综合灰关联序模型的残差门控循环神经网络位标器零部件选配[J]. 中国机械工程, 2021, 32(03): 314-320,356.
[12]	丁嘉鑫;王振亚;姚立纲;蔡永武. 广义复合多尺度加权排列熵与参数优化支持向量机的滚动轴承故障诊断[J]. 中国机械工程, 2021, 32(02): 147-155.
[13]	闫岗1;袁小阳1;陈润霖2;贾谦1;金英泽1. 超导磁液推力轴承的结构设计及性能分析[J]. 中国机械工程, 2021, 32(01): 32-39.
[14]	杨路航1;李宝庆1;王平2,3;王健2,3;杨宇1. 基于概率输出弹性凸包的滚动轴承故障诊断方法[J]. 中国机械工程, 2021, 32(01): 40-46.
[15]	万书亭;彭勃;王晓龙. 基于双时域变换和稀疏编码收缩的滚动轴承早期故障诊断方法[J]. 中国机械工程, 2020, 31(23): 2829-2836.