摘要
针对滚动轴承的故障诊断问题,引入互近似熵的方法对轴承振动信号进行分析。通过研究嵌入维数和延迟时间对信号互近似熵的影响,提出多维度互近似熵的特征提取方法。利用多维度互近似熵方法所提取的特征,建立了基于支持向量机的轴承故障诊断模型。对轴承不同类型、不同程度的故障数据进行分析,证明了多维度互近似熵方法可以有效提取轴承不同状态的特征信息,与支持向量机结合可以精确地诊断轴承不同类型、不同程度故障,具有一定的优势。
Aiming at the fault diagnosis problem of rolling bearing,the cross approximate entropy (CAE)was used to analyze bearing vibration signal.Through researching the impact of embedding dimension and delaying time on signal CAE,a feature extraction method based on multi-dimension CAE was proposed.The diagnosis model was established to diagnosis bearing faults according to the support vector machine (SVM)and the feature calculated by the proposed method.The fault data with different types and varying degrees of bearings were analyzed and the results shown that multi-dimension CAE method for extracting the features is effective and the combination with SVM can diagnosis bearing different types and varying degrees faults accurately,and has a certain advantage.
作者
王宜静
谭海燕
WANG Yijing;TAN Haiyan(School of Mathematics and Physics Anyang Institute of Technology Anyang city He Nan province 455000,China;Chongqing Normal University,Chongqing 404000,China)
出处
《机械设计与研究》
CSCD
北大核心
2019年第1期110-112,124,共4页
Machine Design And Research
关键词
多维度
互近似熵
支持向量机
故障诊断
滚动轴承
multi-dimension
cross approximate entropy
support vector machine
fault diagnosis
rolling bearing
作者简介
王宜静(1978-),女,硕士,讲师;主要研究方向:应用数理统计,已发表论文12篇。
