基于t⁃SNE降维方法的滚动轴承剩余寿命预测  

REMAINING USEFUL LIFE OF ROLLING BEARING BASED ON t⁃SNE

作　　者：钟建华 黄聪 钟舜聪[1,2] 肖顺根 ZHONG JianHua;HUANG Cong;ZHONG ShunCong;XIAO ShunGen(School of Mechanical Engineering and Automation,Fuzhou University,Fuzhou 350116,China;Fujian Provincial Key Laboratory of Terahertz Functional Devices and Intelligent Sensing,Fuzhou 350108,China;College of Information Engineering,Ningde Normal University,Ningde 352100,China)

机构地区：[1]福州大学机械工程及自动化学院,福州350116 [2]福建省太赫兹功能器件与智能传感重点实验室,福州350108 [3]宁德师范学院信息工程学院,宁德352100

出　　处：《机械强度》2024年第4期969-976,共8页Journal of Mechanical Strength

基　　金：国家自然科学基金项目(52275096);福建省技术创新重点攻关项目(2022G02030)资助。

摘　　要：由于实际工况下的轴承退化数据有限,无法获得足够的退化数据来训练神经网络,在深度学习网络中很难得到好的预测结果,所以提出一种新的结合机器学习和统计数据驱动的方法。首先对原始振动信号做特征提取,通过集合经验模态分解奇异值分解(Ensemble Empirical Mode Decompositiont Singular Value Decomposition,EEMD+SVD)得到数十维特征,加上剩余寿命预测常用的诸如峭度、均值等有效特征,利用决策树筛选出15维特征;将所筛选特征进行双指数拟合并通过t分布随机近邻嵌入(t⁃distributed Stochastic Neighbor Embedding,t⁃SNE)将退化信号降维成线性趋势。线性退化趋势在预测上相比于指数趋势有更好的泛化性,同时预测准确度相比于指数模型支持向量回归(Support Vector Regression,SVR)和深度信念网络(Deep Belief Network,DBN)都有较高的提升。Due to the limited bearing degradation data under actual working conditions,it is impossible to obtain enough degradation data to train the neural network,it is difficult to obtain good prediction results in the deep learning network,so a new fusion method was proposed.Firstly,the features of the original vibration signal was extracted,dozens of dimensional features were obtained through the ensemble empirical mode decomposition(EEMD)and the singular value decomposition(SVD),and the effective features such as kurtosis and mean value commonly used in remaining useful life prediction were added,then the decision tree to filter out 15⁃dimensional features was used the data was obtained by double exponential model fitting and the degraded signal was reduced to a linear trend through t⁃SNE.The linear degradation trend has better generalization in prediction than the exponential trend,and the prediction accuracy is superior to support veotor regression(SVR)and deep belief network(DBN)model.

关 键 词：特征提取 轴承 剩余寿命预测 双指数模型 t⁃SNE 

分 类 号：TH17[机械工程—机械制造及自动化]