1.沈阳理工大学 汽车与交通学院,沈阳 110159
2.西南交通大学 轨道交通运载系统全国重点实验室,成都 610031
韩允童,男,1998年生,山东菏泽人,硕士研究生;主要研究方向为车辆系统动力学与控制;E-mail:980087657@qq.com。
收稿:2024-03-12,
修回:2024-04-16,
纸质出版:2026-02-15
移动端阅览
韩允童,王靖岳,侯兴达,等. 基于改进CNN-LSTM模型的在役轴承寿命预测方法[J]. 机械强度,2026,48(2):40-46.
HAN Yuntong,WANG Jingyue,HOU Xingda,et al. Service life prediction method for in-service bearings based on the improved CNN-LSTM model[J]. Journal of Mechanical Strength,2026,48(2):40-46.
韩允童,王靖岳,侯兴达,等. 基于改进CNN-LSTM模型的在役轴承寿命预测方法[J]. 机械强度,2026,48(2):40-46. DOI: 10.16579/j.issn.1001.9669.2026.02.005.
HAN Yuntong,WANG Jingyue,HOU Xingda,et al. Service life prediction method for in-service bearings based on the improved CNN-LSTM model[J]. Journal of Mechanical Strength,2026,48(2):40-46. DOI: 10.16579/j.issn.1001.9669.2026.02.005.
目的
2
针对传统卷积神经网络(Convolutional Neural Network
CNN)-长短期记忆(Long Short-Term Memory
LSTM)网络模型参数调整复杂、预测精度受限的问题,提出一种改进的剩余寿命预测方法,旨在提升在役滚动轴承寿命预测的准确性与稳定性。
方法
2
首先,融合黄金正弦策略来改进麻雀搜索算法(Golden Sparrow Search Algorithm
GSSA),以增强其全局与局部搜索能力,实现对CNN-LSTM关键参数的自适应优化;其次,构建基于相关性、单调性和鲁棒性的特征筛选体系,筛选出高敏感性退化特征;最后,利用PHM2012轴承数据集,建立GSSA-CNN-LSTM预测模型,通过对比反向传播(Back Propagation
BP)神经网络与CNN-LSTM模型验证其有效性。
结果
2
结果表明,所提GSSA-CNN-LSTM模型在均方根误差、平均绝对误差与均方误差上,较BP神经网络与CNN-LSTM模型分别降低了67.61%、83.71%、80.89%与61.18%、78.78%、51.02%,确定系数更接近1,显著提升了预测精度与鲁棒性。
Objective
2
Aiming at the problems of complex parameter adjustment and limited prediction accuracy in traditional convolutional neural network-long short-term memory (CNN-LSTM) models
an improved remaining useful life prediction method was proposed to enhance the accuracy and stability of life prediction for in-service rolling bearings.
Methods
2
Firstly
the golden sine strategy was integrated into the golden sparrow search algorithm (GSSA) to improve its global and local search capabilities
enabling adaptive optimization of key parameters in the CNN-LSTM model. Secondly
a feature screening system based on correlation
monotonicity
and robustness was constructed to select highly sensitive degradation features. Finally
using the PHM2012 bearing dataset
a GSSA-CNN-LSTM prediction model was established
and its effectiveness was validated through comparisons with back propagation (BP) neural network and CNN-LSTM model.
Results
2
The results showed that the proposed GSSA-CNN-LSTM model reduced the root mean square error
mean absolute error
and mean square error by 67.61%
83.71%
80.89% and 61.18%
78.78%
51.02%
respectively
compared with the BP neural network and CNN-LSTM models
while the determination coefficient was closer to 1
demonstrating significant improvements in prediction accuracy and robustness.
PAN H Y , YIN X L , CHENG J , et al . Periodic component pursuit-based kurtosis deconvolution and its application in roller bearing compound fault diagnosis [J]. Mechanism and Machine Theory , 2023 , 185 : 105337 .
FENG Z J , WANG Z H , LIU X Q , et al . Rolling bearing performance degradation assessment with adaptive sensitive feature selection and multi-strategy optimized SVDD [J]. Sensors , 2023 , 23 ( 3 ): 1110 .
CHEN P , KOIDE Y , LI K , et al . Life prediction of rolling bearing using genetic algorithm [J]. Applied Mechanics and Materials , 2011 ,58/ 59 / 60 : 2423 - 2427 .
WANG Y P , YANG C N , XU D , et al . Evaluation and prediction method of rolling bearing performance degradation based on attention-LSTM [J]. Shock and Vibration , 2021 , 2021 : 6615920 .
陈东楠 , 胡昌华 , 郑建飞 , 等 . 状态划分下基于Bi-LSTM-Att的轴承剩余寿命预测 [J]. 空间控制技术与应用 , 2023 , 49 ( 4 ): 29 - 39 .
CHEN Dongnan , HU Changhua , ZHENG Jianfei , et al . Prediction of bearing residual life based on Bi-LSTM-Att under state partition [J]. Aerospace Control and Application , 2023 , 49 ( 4 ): 29 - 39 . (In Chinese)
刘文广 , 司永战 . 基于ResNet-ABiLSTM的滚动轴承剩余寿命预测 [J]. 机电工程 , 2023 , 40 ( 6 ): 903 - 909 .
LIU Wenguang , SI Yongzhan . Residual life prediction of rolling bearing based on ResNet-ABiLSTM [J]. Journal of Mechanical & Electrical Engineering , 2023 , 40 ( 6 ): 903 - 909 . (In Chinese)
刘宇航 , 石宇强 , 王俊佳 . 基于FCM-LSTM的滚动轴承多阶段寿命预测 [J]. 机械设计 , 2023 , 40 ( 5 ): 43 - 50 .
LIU Yuhang , SHI Yuqiang , WANG Junjia . Multi-stage life prediction of rolling bearings based on FCM-LSTM [J]. Journal of Machine Design , 2023 , 40 ( 5 ): 43 - 50 . (In Chinese)
修嘉芸 , 谷玉海 , 任斌 , 等 . 基于LSTM与迁移学习的滚动轴承故障诊断 [J]. 重庆理工大学学报(自然科学) , 2021 , 35 ( 1 ): 83 - 88 .
XIU Jiayun , GU Yuhai , REN Bin , et al . Fault diagnosis for rolling bearing based on LSTM and transfer learning [J]. Journal of Chongqing University of Technology (Natural Science) , 2021 , 35 ( 1 ): 83 - 88 . (In Chinese)
徐海铭 , 夏乔阳 , 李勇 , 等 . 基于深度可分离卷积神经网络轴承剩余寿命预测 [J]. 机械强度 , 2022 , 44 ( 4 ): 763 - 771 .
XU Haiming , XIA Qiaoyang , LI Yong , et al . Bearing remaining life prediction based on deep separable convolutional neural network [J]. Journal of Mechanical Strength , 2022 , 44 ( 4 ): 763 - 771 . (In Chinese)
熊隽 , 陈林 , 王上庆 . 基于多分辨奇异值分解和ECNN-LSTM的滚动轴承寿命预测 [J]. 机械强度 , 2021 , 43 ( 3 ): 523 - 530 .
XIONG Juan , CHEN Lin , WANG Shangqing . Life prediction of rolling bearing based on multi-resolution singular value decomposition and ECNN-LSTM [J]. Journal of Mechanical Strength , 2021 , 43 ( 3 ): 523 - 530 . (In Chinese)
HUBEL D H , WIESEL T N . Receptive fields,binocular interaction and functional architecture in the cat’s visual cortex [J]. The Journal of Physiology , 1962 , 160 ( 1 ): 106 - 154 .
张振宇 , 王娆芬 , 朱安康 . 基于GCNN的滚动轴承故障诊断 [J]. 噪声与振动控制 , 2021 , 41 ( 4 ): 60 - 65 .
ZHANG Zhenyu , WANG Raofen , ZHU Ankang . Fault diagnosis of rolling bearings based on GCNN [J]. Noise and Vibration Control , 2021 , 41 ( 4 ): 60 - 65 . (In Chinese)
LI X H , GUO M M , ZHANG R R , et al . A data-driven prediction model for maximum pitting corrosion depth of subsea oil pipelines using SSA-LSTM approach [J]. Ocean Engineering , 2022 , 261 : 112062 .
薛建凯 . 一种新型的群智能优化技术的研究与应用:麻雀搜索算法 [D]. 上海 : 东华大学 , 2020 : 15 - 20 .
XUE Jiankai . Research and application of a novel swarm intelligence optimization technique:sparrow search algorithm [D]. Shanghai : Donghua University , 2020 : 15 - 20 . (In Chinese)
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 . New York : IEEE , 2012 : 1 - 8 .
ZHANG B , ZHANG L J , XU J W . Degradation feature selection for remaining useful life prediction of rolling element bearings [J]. Quality and Reliability Engineering International , 2016 , 32 ( 2 ): 547 - 554 .
0
浏览量
0
下载量
0
CSCD
关联资源
相关文章
相关作者
相关机构
京公网安备11010802024621