利用DBO-VMD降噪的轴承剩余寿命预测Remaining Useful Life Prediction of Bearing Using DBO-VMD Noise Reduction
高淑芝,李泽琴,张义民
摘要(Abstract)：
针对目前轴承振动信号数据包含噪声的问题，提出了一种基于蜣螂算法优化变分模态分解（DBO-VMD）的降噪方法，并将其结合长短时记忆神经网络（LSTM）用于轴承剩余寿命预测。首先，提出一种基于蜣螂算法与去趋势互相关分析法（DCCA）的改进VMD降噪法，利用该方法对采集到的轴承振动信号进行分解重构，得到降噪后的轴承振动数据；然后，将得到的振动信号数据进行退化特征提取，再把得到的多维退化特征通过KPCA进行融合；最后，将得到的退化指标输入长短时记忆神经网络预测模型，输出预测结果。西安交通大学滚动轴承全寿命试验数据验证了所提方法的有效性。
关键词(KeyWords)： 机械轴承;剩余寿命预测;变分模态分解;蜣螂算法;长短时记忆神经网络
基金项目(Foundation): NSFC-国家自然科学基金（52275156）
作者(Author): 高淑芝,李泽琴,张义民
DOI: 10.19356/j.cnki.1001-3997.20260402.031
参考文献(References)：
- [1]Wang Youdao,Zhao Yifan.&Addepalli,Sir,et al.Remaining useful life prediction using deep learning approaches:a review[J].Procedia Manufacturing,2020(49):81-88.
- [2]胡启国，罗棚，等.基于VMD和ELM＿AdaBoost滚动轴承剩余寿命预测[J].机械设计与制造，2022,376(6):203-207.(Hu Qiguo,Luo Peng,et al.Prediction of remaining useful life of rolling bearings based on VMD and ELM＿AdaBoost[J]. Machinery Design&Manufacture,2022,376(6):203-207.)
- [3]杨铮鑫，王明罡，党鹏飞，等.基于VMD-HT的滚动轴承故障诊断[J].机械设计与制造，2023,385(3):15-18.(Yang Zhengxin,Wang Minggang,Dang Pengfei,et al.Fault diagnosis of rolling bearing based on feature extraction of VMD-HT[J].Machinery Design&Manufacture,2023,385(3):15-18.)
- [4]金志浩，穆鹏丞，张义民，等.一种改进的VMD及其在轴承故障诊断中的应用[J].机械设计与制造，2022,372(2):42-46.(Jin Zhihao,Mu Pengcheng,Zhang Yimin,et al.An lmproved VMD and its application in bearing fault diagnosis[J].Machinery Design&Manufacture,2022,372(2):42-46.)
- [5]郗涛，葛增元，王莉静，等.基于参数优化的VMD与DBN的滚动轴承故障诊断[J].组合机床与自动化加工技术，2022,586(12):57-61.(Xi Tao,Ge Zengyuan,Wang Lijing,et al. Parameter-optimized VMD with DBN for rolling bearing fault diagnosis[J].Modular Machine Tool&Automatic Manufacturing Technique,2022,586(12):57-61.)
- [6]李可，牛园园，宿磊，等.参数优化VMD的滚动轴承故障诊断方法[J].振动工程学报，2023,36(1):280-287.(Li Ke,Niu Yuanyuan,Su Lei,et al. Rolling bearing fault diagnosis method based on parameter optimized VMD[J].Journal of Vibration Engineering,2023,36(1):280-287.)
- [7]Xue Jiankai,Shen,Bo,et al.Dung beetle optimizer:a new meta-heuristic algorithm for global optimization[J]. The Journal of Supercomputing,2023(79):7305-7336.
- [8]Zebende G.F.DCCA cross-correlation coefficient:Quantifying level of cross-correlation[J].Physica A:Statistical Mechanics and its Applications,2011,390(4):614-618.
- [9]王奉涛，刘晓飞，邓刚，等.基于长短期记忆网络的滚动轴承寿命预测方法[J].振动.测试与诊断，2020,40(2):303-309+419.(Wang Fengtao,Liu Xufei,Deng Gang,et al.Remaining useful life prediction method for rolling bearing based on the long short-term memory network[J].Journal of Vibration,Measurement&Diagnosis,2020,40(2):303-309+419.)
- [10]Wang Biao,Lei Yaguo,Li Naipeng,et al.A hybrid prognostics approach for estimating remaining useful life of rolling element bearings[J].IEEE Transactions on Reliability,2020,69(1):401-412.
- [11]Soualhi A,Medjaher K,Zerhouni N,et al. Bearing health monitoring based on hilbert-huang transform,support vector machine and regression[J].IEEE Transactions on Instrumentation&Measurement,2014,64(1):52-62.