煤矿大型机械设备滚动轴承故障诊断改进方法研究  

Improved methods for fault diagnosis of rolling bearings for large mechanical equipment in coal mines

作　　者：彭强 PENG Qiang(Yongcheng Coal Power Chengjiao Coal Mine of Henan Energy and Chemical Group,Yongcheng 476600,China)

机构地区：[1]河南能源集团有限公司永城煤电城郊煤矿,河南永城476600

出　　处：《煤炭工程》2023年第4期141-146,共6页Coal Engineering

摘　　要：针对传统的特征选择算法用于煤矿机械轴承故障诊断时将嵌入学习和特征排序分开,无法准确选择出能表征高维数据集的子集和故障诊断准确率不高的问题。文章提出了一种基于嵌入学习与稀疏回归的煤矿机械轴承故障诊断方法。该方法首先构造嵌入学习模型,学习高维数据的流形结构;其次,在回归模型中引入具有组稀疏性的l 2,1范数,有效剔除冗余特征;然后联合嵌入学习和稀疏回归构造特征选择框架,选择出能准确表征原始高维数据的本质特征;最后通过与K-最近邻算法相结合进行煤矿机械轴承的故障诊断。实验结果表明,提出的模型显著提高了煤矿机械轴承的故障诊断精度。In the traditional feature selection algorithm used for fault diagnosis of coal mine machinery bearing separates embedded learning and feature selection,it cannot accurately select subsets that can represent high-dimensional data sets and the accuracy of fault diagnosis is not high.A fault diagnosis method for coal mine machinery bearing based on joint embedded learning and sparse regression is proposed.The method first constructs an embedded learning model to learn the manifold structure of high-dimensional data.And then the l 2,1-norm with group sparsity is introduced into the regression model to eliminate the influence of redundant features;furthermore,a feature selection framework is constructed jointly with embedded learning and sparse regression,and the essential features that can accurately characterize the original high-dimensional data are selected;finally,the fault diagnosis of coal mine mechanical bearing is carried out by combining with K-nearest neighbor algorithm.The experimental results show that the fault diagnosis accuracy is significantly improved by the proposed model.

关 键 词：煤矿机械轴承 故障诊断 特征选择 嵌入学习 稀疏回归 K-最近邻 

分 类 号：TD608[矿业工程—矿山机电]