

浏览全部资源
扫码关注微信
上海理工大学 机械工程学院,上海 200093
CHI Yulun, E-mail: chiyulun@163.com
Received:29 August 2024,
Revised:2024-11-01,
Published:15 June 2026
移动端阅览
迟玉伦, 黄浩伦. 基于CEEMDAN-LSTM-MHSA的磨削砂轮剩余使用寿命预测方法研究[J]. 机械强度,2026,48(6):29-44.
CHI Yulun,HUANG Haolun. Study on remaining useful life prediction method of grinding wheel based on CEEMDAN-LSTM-MHSA[J]. Journal of Mechanical Strength,2026,48(6):29-44.
迟玉伦, 黄浩伦. 基于CEEMDAN-LSTM-MHSA的磨削砂轮剩余使用寿命预测方法研究[J]. 机械强度,2026,48(6):29-44. DOI: 10.16579/j.issn.1001.9669.2026.06.004.
CHI Yulun,HUANG Haolun. Study on remaining useful life prediction method of grinding wheel based on CEEMDAN-LSTM-MHSA[J]. Journal of Mechanical Strength,2026,48(6):29-44. DOI: 10.16579/j.issn.1001.9669.2026.06.004.
目的
2
针对传统信号重构依赖先验知识和人为经验导致模型通用性下降,无法兼顾砂轮修整寿命和更换寿命预测的问题,用完全自适应的噪声互补集成经验模态分解(Complementary Ensemble Empirical Mode Decomposition with Adaptive Noise
CEEMDAN)、多头自注意力(Multi-Head Self-Attention
MHSA)机制和长-短时记忆(Long-Short Term Memory
LSTM)网络替换人工信号重构流程,提出一种基于CEEMDAN-LSTM-MHSA的通用砂轮寿命预测方法。
方法
2
首先,根据频率特征,利用CEEMDAN将磨削声发射和振动信号分离固有模态函数(Intrinsic Mode Function
IMF);其次,使用多个LSTM网络提取各IMF中的时域特征,通过MHSA建立影响因素特征与砂轮表面和直径变化之间的依赖关系,并构建砂轮修整和更换健康指标(Health Index
HI)曲线;然后,通过孤立森林异常检测算法和指数加权移动平均(Exponential Weighted Moving Average
EWMA)改善HI曲线的单调性和平滑度,并利用支持向量回归(Support Vector Regression
SVR)拟合HI曲线,结合HI曲线的阈值,实现对砂轮剩余使用寿命(Remaining Useful Life
RUL)的预测;最后,进行连续磨削和砂轮修整试验验证。
结果
2
结果表明,所提模型可对砂轮修整寿命和砂轮更换寿命进行准确预测,有效增强了砂轮RUL预测中的通用性。
Objective
2
Aiming at the problem that traditional signal reconstruction relies heavily on prior knowledge and manual experience
which reduces model generality and fails to simultaneously realize the prediction of grinding wheel dressing life and replacement life
the complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN)
multi-head self-attention (MHSA) mechanism and long-short term memory (LSTM) network were adopted to replace the manual signal reconstruction process. A general grinding wheel life prediction method based on CEEMDAN-LSTM-MHSA was proposed.
Methods
2
Firstly
according to frequency characteristics
CEEMDAN was used to decompose grinding acoustic emission and vibration signals into intrinsic mode function (IMF). Secondly
multiple LSTM networks were applied to extract time-domain features from each IMF. The MHSA mechanism was employed to establish the dependency between influencing factor features and the changes in grinding wheel surface morphology and diameter
and construct health index (HI) curves for grinding wheel dressing and replacement. Then
the isolation forest anomaly detection algorithm and exponential weighted moving average (EWMA) were utilized to improve the monotonicity and smoothness of HI curves. Support vector regression (SVR) was adopted to fit the HI curves
and the remaining useful life (RUL) prediction of the grinding wheel was realized combined with the threshold of HI curves. Finally
continuous grinding and grinding wheel dressing tests were carried out for verification.
Results
2
The results show that the proposed model can accurately predict the dressing life and replacement life of grinding wheels
and effectively improve the generality of grinding wheel RUL prediction.
杨磊 , 李郝林 , 迟玉伦 . 基于自适应模糊神经网络的砂轮磨损评估 [J]. 轻工机械 , 2020 , 38 ( 6 ): 72 - 76 .
YANG Lei , LI Haolin , CHI Yulun . Wear evaluation of grinding wheel based on adaptive fuzzy neural network [J]. Light Industry Machinery , 2020 , 38 ( 6 ): 72 - 76 . (In Chinese)
卢守相 , 郭塞 , 张建秋 , 等 . 高性能难加工材料可磨削性研究进展 [J]. 表面技术 , 2022 , 51 ( 3 ): 12 - 42 .
LU Shouxiang , GUO Sai , ZHANG Jianqiu , et al . Grindability of high performance difficult-to-machine materials [J]. Surface Technology , 2022 , 51 ( 3 ): 12 - 42 . (In Chinese)
焦锋 , 李成龙 , 牛赢 , 等 . 砂轮修整技术研究现状与展望 [J]. 中国机械工程 , 2021 , 32 ( 20 ): 2435 - 2448 .
JIAO Feng , LI Chenglong , NIU Ying , et al . Review and prospect of grinding wheel dressing technique [J]. China Mechanical Engineering , 2021 , 32 ( 20 ): 2435 - 2448 . (In Chinese)
谭永敏 , 施展 , 迟玉伦 , 等 . 基于Shannon熵与声发射信号的CBN砂轮性能监测方法研究 [J]. 机械强度 , 2023 , 45 ( 2 ): 321 - 330 .
TAN Yongmin , SHI Zhan , CHI Yulun , et al . Research on CBN grinding wheel performance monitoring method based on Shannon entropy and acoustic emission signal [J]. Journal of Mechanical Strength , 2023 , 45 ( 2 ): 321 - 330 . (In Chinese)
尹国强 , 王东 , 关云匀 , 等 . 基于声发射监测的砂轮磨损实验 [J]. 东北大学学报(自然科学版) , 2022 , 43 ( 8 ): 1127 - 1133 .
YIN Guoqiang , WANG Dong , GUAN Yunyun , et al . Grinding wheel wear experiment based on acoustic emission monitoring [J]. Journal of Northeastern University (Natural Science) , 2022 , 43 ( 8 ): 1127 - 1133 . (In Chinese)
ZHANG Q L , ZHAO Q L , TO S , et al . Diamond wheel wear mechanism and its impact on the surface generation in parallel diamond grinding of RB-SiC/Si [J]. Diamond and Related Materials , 2017 , 74 : 16 - 23 .
FAN K C , LEE M Z , MOU J I . On-line non-contact system for grinding wheel wear measurement [J]. The International Journal of Advanced Manufacturing Technology , 2002 , 19 ( 1 ): 14 - 22 .
YOU F Y , ZHOU W , WANG X , et al . Systematic monitoring and evaluating the wear of alumina wheel when grinding the workpiece of Cr 12 [J]. Complexity , 2021 , 2021 : 6665043 .
HUNDT W , LEUENBERGER D , REHSTEINER F , et al . An approach to monitoring of the grinding process using acoustic emission(AE) technique [J]. CIRP Annals , 1994 , 43 ( 1 ): 295 - 298 .
李厦 , 李郝林 . 切入磨削与纵向磨削的磨削力分析与比较 [J]. 中国机械工程 , 2012 , 23 ( 3 ): 269 - 273 .
LI Sha , LI Haolin . Analysis and comparison of grinding forces between plunge grinding and traverse grinding [J]. China Mechanical Engineering , 2012 , 23 ( 3 ): 269 - 273 . (In Chinese)
CHEN X , LIMCHIMCHOL T . Monitoring grinding wheel redress-life using support vector machines [J]. International Journal of Automation and Computing , 2006 , 3 ( 1 ): 56 - 62 .
郭维诚 , 李蓓智 , 杨建国 , 等 . 磨削过程信号监测与砂轮磨损预测模型构建 [J]. 上海交通大学学报 , 2019 , 53 ( 12 ): 1475 - 1481 .
GUO Weicheng , LI Beizhi , YANG Jianguo , et al . Monitoring of grinding signals and development of wheel wear prediction model [J]. Journal of Shanghai Jiao Tong University , 2019 , 53 ( 12 ): 1475 - 1481 . (In Chinese)
DEVENDIRAN S , MANIVANNAN K . Condition monitoring on grinding wheel wear using wavelet analysis and decision tree C4.5 algorithm [J]. International Journal of Engineering and Technology , 2013 , 5 ( 5 ): 4010 - 4024 .
YANG Z S , YU Z H . Grinding wheel wear monitoring based on wavelet analysis and support vector machine [J]. The International Journal of Advanced Manufacturing Technology , 2012 , 62 ( 1 ): 107 - 121 .
MAHATA S , SHAKYA P , BABU N R . A robust condition monitoring methodology for grinding wheel wear identification using Hilbert Huang transform [J]. Precision Engineering , 2021 , 70 : 77 - 91 .
YIN C , WANG Y L , LEE H P , et al . Robust wheel wear detection for solid carbide grinding under strong noise interference:a new approach based on improved ensemble noise-reconstructed empirical mode decomposition [J]. Wear , 2021 , 486 : 204112 .
陈晨 , 施展 , 迟玉伦 . AVMD-Kriging砂轮寿命周期磨削性能在线监测方法 [J]. 轻工机械 , 2023 , 41 ( 3 ): 88 - 99 .
CHEN Chen , SHI Zhan , CHI Yulun . Online monitoring method for grinding performance of grinding wheel life cycle based on AVMD-Kriging [J]. Light Industry Machinery , 2023 , 41 ( 3 ): 88 - 99 . (In Chinese)
杨斌 , 樊志刚 , 王建国 , 等 . 小波包和1D CNN结合的刀具磨损状态识别 [J]. 机械设计与制造 , 2024 ( 9 ): 228 - 232 .
YANG Bin , FAN Zhigang , WANG Jianguo , et al . Tool wear status recognition based on wavelet packet and 1D CNN [J]. Machinery Design & Manufacture , 2024 ( 9 ): 228 - 232 . (In Chinese)
苏史博 , 毕果 , 郑守红 , 等 . 基于LSTM和声发射的金刚石砂轮磨损状态识别 [J]. 组合机床与自动化加工技术 , 2021 ( 8 ): 169 - 172 .
SU Shibo , BI Guo , ZHENG Shouhong , et al . Identification of wear status of diamond grinding wheel based on LSTM and acoustic emission [J]. Modular Machine Tool & Automatic Manufacturing Technique , 2021 ( 8 ): 169 - 172 . (In Chinese)
史丽晨 , 史炜椿 , 王海涛 , 等 . 基于DRSN-BiLSTM模型的刀具磨损预测方法研究 [J]. 机械工程学报 , 2024 , 60 ( 24 ): 66 - 74 .
SHI Lichen , SHI Weichun , WANG Haitao , et al . Tool wear prediction based on DRSN-BiLSTM model [J]. Journal of Mechanical Engineering , 2024 , 60 ( 24 ): 66 - 74 . (In Chinese)
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)
张天缘 , 孙虎儿 , 朱继扬 , 等 . 基于SDP和改进SAM-MobileNetv2的滚动轴承故障诊断方法研究 [J]. 机械强度 , 2024 , 46 ( 4 ): 787 - 794 .
ZHANG Tianyuan , SUN Huer , ZHU Jiyang , et al . Fault diagnosis of rolling bearings based on SDP and improved SAM-MobileNetv2 [J]. Journal of Mechanical Strength , 2024 , 46 ( 4 ): 787 - 794 . (In Chinese)
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 .
曾浩 , 曹华军 , 董俭雄 . 基于ISABO-IBiLSTM模型的刀具磨损预测方法 [J]. 中国机械工程 , 2024 , 35 ( 11 ): 1995 - 2006 .
ZENG Hao , CAO Huajun , DONG Jianxiong . Tool wear prediction method based on ISABO-IBiLSTM model [J]. China Mechanical Engineering , 2024 , 35 ( 11 ): 1995 - 2006 . (In Chinese)
迟玉伦 , 李郝林 . 基于时间常数外圆切入磨削砂轮钝化的监测方法 [J]. 中国机械工程 , 2016 , 27 ( 2 ): 209 - 214 .
CHI Yulun , LI Haolin . Monitoring method of cylindrical plunge grinding wheel wear based on time constant [J]. China Mechanical Engineering , 2016 , 27 ( 2 ): 209 - 214 . (In Chinese)
周圣文 , 郭顺生 , 杜百岗 . 基于LSTM-ES-RVM的滚动轴承剩余寿命预测方法 [J]. 振动工程学报 , 2023 , 36 ( 6 ): 1723 - 1735 .
ZHOU Shengwen , GUO Shunsheng , DU Baigang . Remaining useful life prediction method of rolling bearing based on LSTM-ES-RVM networks [J]. Journal of Vibration Engineering , 2023 , 36 ( 6 ): 1723 - 1735 . (In Chinese)
周哲韬 , 刘路 , 宋晓 , 等 . 基于Transformer模型的滚动轴承剩余使用寿命预测方法 [J]. 北京航空航天大学学报 , 2023 , 49 ( 2 ): 430 - 443 .
ZHOU Zhetao , LIU Lu , SONG Xiao , et al . Remaining useful life prediction method of rolling bearing based on Transformer model [J]. Journal of Beijing University of Aeronautics and Astronautics , 2023 , 49 ( 2 ): 430 - 443 . (In Chinese)
0
Views
0
下载量
0
CSCD
Publicity Resources
Related Articles
Related Author
Related Institution
京公网安备11010802024621