1.中国计量大学 计量测试与仪器学院,杭州 310018
2.安徽第二医学院 口腔医学院,合肥 230601
3.东莞理工学院 机械工程学院,东莞 523429
潘作舟,男,1994年生,安徽巢湖人,博士研究生,副教授,硕士研究生导师;主要研究方向为旋转机械关键部件智能诊断与预测;E-mail:panzz@cjlu.edu.cn。
收稿:2025-06-18,
修回:2025-08-01,
纸质出版:2026-05-15
移动端阅览
潘作舟,吴一丁,胡宜成,等. 基于累积变换和EResNet-KSLSTM网络的滚动轴承剩余使用寿命预测方法[J]. 机械强度,2026,48(5):9-21.
PAN Zuozhou,WU Yiding,HU Yicheng,et al. Remaining useful life prediction of rolling-element bearings based on cumulative transformation and EResNet-KSLSTM network[J]. Journal of Mechanical Strength,2026,48(5):9-21.
潘作舟,吴一丁,胡宜成,等. 基于累积变换和EResNet-KSLSTM网络的滚动轴承剩余使用寿命预测方法[J]. 机械强度,2026,48(5):9-21. DOI: 10.16579/j.issn.1001.9669.2026.05.002.
PAN Zuozhou,WU Yiding,HU Yicheng,et al. Remaining useful life prediction of rolling-element bearings based on cumulative transformation and EResNet-KSLSTM network[J]. Journal of Mechanical Strength,2026,48(5):9-21. DOI: 10.16579/j.issn.1001.9669.2026.05.002.
目的
2
针对滚动轴承工作环境恶劣、早期退化趋势微弱,导致预测过程的故障特征提取难度大、预测精度不高等问题,提出一种基于累积变换的强化诊断模型,对滚动轴承开展剩余使用寿命预测任务。
方法
2
首先,提出了基于累积变换的特征强化方法,将提取所得特征量转换为对应的累积变换形式,增强原始特征量的敏感度;其次,构建基于累积特征的新型健康指标,利用连续触发机制算法对健康指标进行状态划分,获得初始故障发生点;最后,强化ResNet的跳连接模块、增加额外的校准通道,提高网络模型对关键退化特征的聚焦能力,并通过带Kolmogorov-Arnold Network (KAN)模块的堆叠长短期记忆(Stacked Long Short-Term Memory with KAN Module
KSLSTM)网络,获取全时空特征,进行轴承剩余使用寿命的精准预测。
结果
2
结果表明,通过构建累积变换特征和优化网络结构来提高小样本训练环境下的轴承剩余使用寿命预测精度,仿真和试验证明了该方法的有效性。
Objective
2
Aiming at the problems of harsh working environment and weak early degradation trend of rolling bearings
which lead to great difficulty in fault feature extraction and low prediction accuracy
a reinforced diagnosis model based on cumulative transformation was proposed for the remaining useful life (RUL) prediction of rolling bearings.
Methods
2
Firstly
a feature enhancement method based on cumulative transformation was proposed
where the extracted features were converted into the corresponding cumulative transformation form to improve the sensitivity of the original features. Secondly
a new health index based on cumulative features was constructed
and the continuous trigger mechanism algorithm was used to divide the states of the health index to determine the initial fault occurrence point. Finally
the skip connection module of the ResNet was enhanced and additional calibration channels were added to improve the network’s ability to focus on key degradation features
and then the stacked long short-term memory with Kolmogorov-Arnold network module (KSLSTM) network was used to obtain full spatiotemporal features for the accurate prediction of bearing RUL.
Results
2
The results show that the prediction accuracy of bearing RUL in the small-sample training environment is significantly improved by constructing cumulative transformation features and optimizing the network structure
and the effectiveness of the method is verified by simulations and tests.
KIM S , SEO Y H , PARK J . Transformer-based novel framework for remaining useful life prediction of lubricant in operational rolling bearings [J]. Reliability Engineering & System Safety , 2024 , 251 : 110377 .
YANG Y , HU N Q , LI Y H , et al . Dynamic modeling and analysis of planetary gear system for tooth fault diagnosis [J]. Mechanical Systems and Signal Processing , 2024 , 207 : 110946 .
REN X Y , WANG S X , ZHAO W L , et al . Universal federated domain adaptation for gearbox fault diagnosis:a robust framework for credible pseudo-label generation [J]. Advanced Engineering Informatics , 2025 , 65 : 103233 .
XIAO Y C , LIU D D , CUI L L , et al . Heterogeneous graph representation-driven multiplex aggregation graph neural network for remaining useful life prediction of bearings [J]. Mechanical Systems and Signal Processing , 2024 , 220 : 111679 .
SONG Q Y , JIANG X X , DU G F , et al . Smart multichannel mode extraction for enhanced bearing fault diagnosis [J]. Mechanical Systems and Signal Processing , 2023 , 189 : 110107 .
KHAKIPOUR M H , SAFAVI A A , SETOODEH P . Bearing fault diagnosis with morphological gradient wavelet [J]. Journal of the Franklin Institute , 2017 , 354 ( 6 ): 2465 - 2476 .
HUANG N E , SHEN Z , LONG S R , et al . The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis [J]. Proceedings:Mathematical,Physical and Engineering Sciences , 1998 , 454 ( 1971 ): 903 - 995 .
WANG S Q , FENG Z G . Multi-sensor fusion rolling bearing intelligent fault diagnosis based on VMD and ultra-lightweight GoogLeNet in industrial environments [J] . Digital Signal Processing , 2024 , 145 : 104306 .
HUANG X K , WU X F , TIAN Z Z , et al . Fault diagnosis study of mine drainage pump based on MED-WPD and RBFNN [J]. Journal of the Brazilian Society of Mechanical Sciences and Engineering , 2023 , 45 ( 7 ): 347 .
WANG Z J , ZHAO W Y , LI Y F , et al . Adaptive staged RUL prediction of rolling bearing [J]. Measurement , 2023 , 222 : 113478 .
JIANG F , KUANG Y C , LI T , et al . Towards Enhanced Interpretability:a Mechanism-Driven domain adaptation model for bearing fault diagnosis across operating conditions [J]. Mechanical Systems and Signal Processing , 2025 , 225 : 112244 .
WANG S Y , HU J H , DU Y W , et al . WCFormer:an interpretable deep learning framework for heart sound signal analysis and automated diagnosis of cardiovascular diseases [J]. Expert Systems with Applications , 2025 , 276 : 127238 .
YANG S L , TANG B P , WANG W Y , et al . Physics-informed multi-state temporal frequency network for RUL prediction of rolling bearings [J]. Reliability Engineering & System Safety , 2024 , 242 : 109716 .
WANG Z J , ZHAO W Y , LI Y F , et al . Adaptive staged RUL prediction of rolling bearing [J]. Measurement , 2023 , 222 : 113478 .
LIU Y , ZHOU G D , ZHAO S J , et al . A novel two-stage method via adversarial strategy for remaining useful life prediction of bearings under variable conditions [J]. Reliability Engineering & System Safety , 2025 , 254 : 110602 .
HUANG C G , HUANG H Z , LI Y F , et al . A novel deep convolutional neural network-bootstrap integrated method for RUL prediction of rolling bearing [J]. Journal of Manufacturing Systems , 2021 , 61 : 757 - 772 .
钟建华 , 黄聪 , 钟舜聪 , 等 . 基于 t -SNE降维方法的滚动轴承剩余寿命预测 [J]. 机械强度 , 2024 , 46 ( 4 ): 969 - 976 .
ZHONG Jianhua , HUANG Cong , ZHONG Shuncong , et al . Remaining useful life of rolling bearing based on t -SNE [J]. Journal of Mechanical Strength , 2024 , 46 ( 4 ): 969 - 976 . (In Chinese)
YANG T G , WU D L , QIU S R , et al . The STAP-Net:a new health perception and prediction framework for bearing-rotor systems under special working conditions [J]. Reliability Engineering & System Safety , 2025 , 254 : 110633 .
WANG J , SHAO H D , YAN S , et al . C-ECAFormer:a new lightweight fault diagnosis framework towards heavy noise and small samples [J]. Engineering Applications of Artificial Intelligence , 2023 , 126 : 107031 .
LI X L , ZHANG W , DING Y , et al . Rolling bearing degradation stage division and RUL prediction based on recursive exponential slow feature analysis and Bi-LSTM model [J]. Reliability Engineering & System Safety , 2025 , 259 : 110923 .
PEI X W , LI X Y , GAO L . A novel machinery RUL prediction method based on exponential model and cross-domain health indicator considering first-to-end prediction time [J]. Mechanical Systems and Signal Processing , 2024 , 209 : 111122 .
汪应 , 宋宇博 , 朱大鹏 . ALIF-NLM轴承微弱故障特征提取方法 [J]. 机械强度 , 2024 , 46 ( 5 ): 1026 - 1035 .
WANG Ying , SONG Yubo , ZHU Dapeng . Rolling bearing weak fault feature extraction method with ALIF-NLM [J]. Journal of Mechanical Strength , 2024 , 46 ( 5 ): 1026 - 1035 . (In Chinese)
杨森 , 王恒迪 , 崔永存 , 等 . 基于改进SSA的参数优化VMD和ELM的轴承故障诊断 [J]. 机械传动 , 2023 , 47 ( 10 ): 162 - 168 .
YANG Sen , WANG Hengdi , CUI Yongcun , et al . Bearing fault diagnosis based on parameter optimized VMD and ELM with improved SSA [J]. Journal of Mechanical Transmission , 2023 , 47 ( 10 ): 162 - 168 . (In Chinese)
PAN Z Z , MENG Z , CHEN Z J , et al . A two-stage method based on extreme learning machine for predicting the remaining useful life of rolling-element bearings [J]. Mechanical Systems and Signal Processing , 2020 , 144 : 106899 .
PENG S , HUANG H B , CHEN W J , et al . More trainable inception-ResNet for face recognition [J]. Neurocomputing , 2020 , 411 : 9 - 19 .
GINART A , BARLAS I , GOLDIN J , et al . Automated feature selection for embeddable prognostic and health monitoring (PHM)architectures [C]// 2006 IEEE Autotestcon . IEEE , 2006 : 195 - 201 .
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 Transactions on Industrial Electronics , 2015 , 62 ( 12 ): 7762 - 7773 .
AHMAD W , KHAN S A , MANJURUL ISLAM M M , et al . A reliable technique for remaining useful life estimation of rolling element bearings using dynamic regression models [J]. Reliability Engineering & System Safety , 2019 , 184 : 67 - 76 .
WANG G , XIANG J W . Remain useful life prediction of rolling bearings based on exponential model optimized by gradient method [J]. Measurement , 2021 , 176 : 109161 .
SAXENA A , CELAYA J , BALABAN E , et al . Metrics for evaluating performance of prognostic techniques [C]// 2008 International Conference on Prognostics and Health Management . IEEE , 2008 : 1 - 17 .
QIN Y , XIANG S , CHAI Y , et al . Macroscopic-microscopic attention in LSTM networks based on fusion features for gear remaining life prediction [J]. IEEE Transactions on Industrial Electronics , 2020 , 67 ( 12 ): 10865 - 10875 .
ZHANG T S , YE M , LI X F , et al . Fractional derivative kernel recursive generalized maximum correntropy for RUL prediction of rolling bearings [J]. Mechanical Systems and Signal Processing , 2024 , 217 : 111527 .
0
浏览量
23
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