基于迁移学习的滚动轴承剩余使用寿命预测

姜苗; 向阳; 魏建红

doi:10.11990/jheu.202205075

Chinese

您当前的位置：

首页 >

文章列表页 >

基于迁移学习的滚动轴承剩余使用寿命预测

更新时间：2025-09-01

- 基于迁移学习的滚动轴承剩余使用寿命预测
- Prediction of the remaining service life of a rolling bearing based on transfer learning
- 哈尔滨工程大学学报 2024年45卷第4期页码：665-673
- 作者机构：
  
  1.武汉理工大学船海与能源动力工程学院, 湖北武汉 430000
  2.高性能船舶技术教育部重点实验室(武汉理工大学), 湖北武汉 430000
- 作者简介：
  
  [ "姜苗，男，博士研究生" ]
  [ "向阳，女，教授，博士生导师" ]
- 基金信息：
  
  国家工信部绿色智能内河船舶创新专项(20201g0079)
- DOI：10.11990/jheu.202205075
  中图分类号： TP319.56
- 收稿：2022-05-27，
  
  网络首发：2024-02-09，
  
  纸质出版：2024-04-05
- 稿件说明：
移动端阅览
姜苗, 向阳, 魏建红. 基于迁移学习的滚动轴承剩余使用寿命预测[J]. 哈尔滨工程大学学报, 2024,45(4):665-673.

Miao JIANG, Yang XIANG, Jianhong WEI. Prediction of the remaining service life of a rolling bearing based on transfer learning[J]. Journal of Harbin Engineering University, 2024, 45(4): 665-673.
姜苗, 向阳, 魏建红. 基于迁移学习的滚动轴承剩余使用寿命预测[J]. 哈尔滨工程大学学报, 2024,45(4):665-673. DOI： 10.11990/jheu.202205075.

Miao JIANG, Yang XIANG, Jianhong WEI. Prediction of the remaining service life of a rolling bearing based on transfer learning[J]. Journal of Harbin Engineering University, 2024, 45(4): 665-673. DOI： 10.11990/jheu.202205075.

摘要

为解决轴承剩余使用寿命预测模型预测泛化能力低

不能准确预测出未训练轴承剩余使用寿命的问题

本文提出了一种迁移轴承状态知识的剩余使用寿命的方法。利用计算时域、频域特征以及模糊熵作为预测特征

使用“3σ”准则将轴承全寿命过程划分为正常阶段、退化阶段

以实现对退化阶段轴承剩余使用寿命的预测。构建基于门控循环单元的轴承剩余使用寿命预测模型

并使用某一轴承的全寿命周期数据进行训练

使模型学习到新轴承的状态信息。研究表明: 相较于未使用迁移学习的方法

其预测所有轴承的轴承剩余使用寿命平均均方根误差减小了52.53 %

平均百分比误差减少了68.87 %。本文提出的方法可以有效、准确地预测出轴承的轴承剩余使用寿命。

Abstract

To address the issue of low generalization ability in predicting the remaining useful life (RUL) of bearings using the prediction model

and difficulties in accurately predicting the RUL of untrained bearings

this paper proposes a method to transfer knowledge of bearing conditions for RUL prediction. By utilizing computed time and frequency-domain features

and fuzzy entropy as predictive features

the bearing's entire life cycle is divided into normal and degraded stages employing the '3σ' criterion to achieve prediction of the RUL during the degradation stage. A bearing's RUL prediction model based on Gated Recurrent Units is constructed

trained on the full life cycle data of a particular bearing to enable the model to learn the state information of new bearings. Research indicates that

compared to methods not employing transfer learning

the root mean square error in predicting the RUL of all bearings decreased by 52.53 %

while the average percentage error reduced by 68.87 %. The proposed method effectively and accurately predicts the RUL of bearings.

关键词

Keywords

references

BAI Ruxue, XU Quansheng, MENG Zong, et al. Rolling bearing fault diagnosis based on multi-channel convolution neural network and multi-scale clipping fusion data augmentation[J]. Measurement, 2021, 184: 109885.

YANG Boyuan, LIU Ruonan, ZIO E. Remaining useful life prediction based on a double-convolutional neural network architecture[J]. IEEE transactions on industrial electronics, 2019, 66(12): 9521-9530.

LEE J, WU Fangji, ZHAO Wenyu, et al. Prognostics and health management design for rotary machinery systems—Reviews, methodology and applications[J]. Mechanical systems and signal processing, 2014, 42(1/2): 314-334.

LECUN Y, BENGIO Y, HINTON G. Deep learning[J]. Nature, 2015, 521: 436-444.

BABU G S, ZHAO Peilin, LI Xiaoli. Deep convolutional neural network based regression approach for estimation of remaining useful life[C]//International Conference on Database Systems for Advanced Applications. Cham: Springer, 2016, 9642: 214-228.

DING Hua, YANG Liangliang, CHENG Zeyin, et al. A remaining useful life prediction method for bearing based on deep neural networks[J]. Measurement, 2021, 172: 108878.

CHEN Zheng, ZHAO Hongqian, ZHANG Yuanjian, et al. State of health estimation for lithium-ion batteries based on temperature prediction and gated recurrent unit neural network[J]. Journal of power sources, 2022, 521: 230892.

ANSARI M S, BARTOŠ V, LEE B. GRU-based deep learning approach for network intrusion alert prediction[J]. Future generation computer systems, 2022, 128: 235-247.

TONG Sheng, YANG Jie, ZONG Haohua. A prediction model for complex equipment remaining useful life using gated recurrent unit complex networks[J]. Enterprise information systems, 2023, 17(5): 2008515.

杨泗智, 龚春林, 谷良贤. 一种基于磁传感器的高旋火箭弹滚转角测量方法[J]. 中国惯性技术学报, 2019, 27(4): 481-485.

YANG Sizhi, GONG Chunlin, GU Liangxian. Roll angle measurement method for high-rotation rocket based on magnetic sensor[J]. Journal of Chinese inertial technology, 2019, 27(4): 481-485.

赵柄锡, 冀大伟, 袁奇, 等. 采用时域与时频域联合特征空间的转子系统碰磨故障诊断[J]. 西安交通大学学报, 2020, 54(1): 75-84.

ZHAO Bingxi, JI Dawei, YUAN Qi, et al. Rubbing fault diagnosis of rotor system based on combined feature space in time and time-frequency domains[J]. Journal of Xi'an Jiaotong University, 2020, 54(1): 75-84.

何青, 褚东亮, 毛新华. 基于EEMD和MFFOA-SVM滚动轴承故障诊断[J]. 中国机械工程, 2016, 27(9): 1191-1197.

HE Qing, CHU Dongliang, MAO Xinhua. Study on rolling bearing fault diagnosis based on EEMD and mffoa-svm[J]. China mechanical engineering, 2016, 27(9): 1191-1197.

陈剑, 蔡坤奇, 陶善勇, 等. 基于ⅡTD模糊熵与随机森林的滚动轴承故障诊断方法[J]. 计量学报, 2021, 42(6): 774-779.

CHEN Jian, CAI Kunqi, TAO Shanyong, et al. Fault diagnosis method of rolling bearing based on ⅡTD fuzzy entropy and random forest[J]. Acta metrologica sinica, 2021, 42(6): 774-779.

刘守道. 大型车用柴油机智能故障诊断技术及寿命预测方法的研究[D]. 北京: 石油大学, 2001.

LIU Shoudao. intelligent faults diagnosis and life prediction research for large power vehicle diesel engine[D]. Beijing: China University of Petroleum, 2001.

ZHAO Yuyu, WANG Yuxiao. Remaining useful life prediction for multi-sensor systems using a novel end-to-end deep-learning method[J]. Measurement, 2021, 182: 109685.

BUSARI G A, LIM D H. Crude oil price prediction: a comparison between AdaBoost-LSTM and AdaBoost-GRU for improving forecasting performance[J]. Computers&chemical engineering, 2021, 155: 107513.

庄福振, 罗平, 何清, 等. 迁移学习研究进展[J]. 软件学报, 2015, 26(1): 26-39.

ZHUANG Fuzhen, LUO Ping, HE Qing, et al. Survey on transfer learning research[J]. Journal of software, 2015, 26(1): 26-39.

DING Ning, LI Hulin, YIN Zhongwei, et al. Journal bearing seizure degradation assessment and remaining useful life prediction based on long short-term memory neural network[J]. Measurement, 2020, 166: 108215.

ZENG Fuchuan, LI Yiming, JIANG Yuhang, et al. An online transfer learning-based remaining useful life prediction method of ball bearings[J]. Measurement, 2021, 176: 109201.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

基于迁移学习的遥感影像少样本目标检测模型

基于拉东投影与改进卷积神经网络的小样本水下目标声呐图像识别方法

基于轻量级神经网络的单幅图像去雨滴模型

基于递归图和卷积神经网络-门控循环单元的水轮机空化状态识别方法

基于多域泛化的信道鲁棒自动调制分类