摘要
由于风机的运行环境恶劣,当轴承发生故障时,其振动信号往往受到环境噪声的干扰,导致对于振动信号的故障信息提取困难。针对这一问题,本文提出了一种基于互补集合经验模态分解(CEEMD)和样本熵(SE)结合的特征提取方法,并将天鹰优化算法(AO)与支持向量机(SVM)结合进行故障分类,实现对风机轴承的故障诊断。本文采用凯斯西储大学轴承数据进行实验,并采用真实风机轴承数据进行进一步的验证。实验结果表明本文所提出方法具有很高的故障识别准确率。
Because of the bad operating environment of the fan,when the bearing is faulty,its vibration signal is often disturbed by environmental noise,which leads to the difficulty of fault information extraction for vibration signal.To solve this problem,this paper proposes a feature extraction method based on complementary ensemble empirical mode decomposition(CEEMD)and sample entropy(SE),which combines the Tianying optimization algorithm(AO)and support vector machine(SVM)for fault classification,and realizes the fault diagnosis of fan bearings.In this paper,the bearing data of Case Western Reserve University are used for the experiment,and the real fan bearing data are used for further verification.The experimental results show that the proposed method has high fault identification accuracy when fault vibration signal is disturbed by environmental noise.
作者
孙润发
汤占军
SUN Runfa;TANG Zhanjun(Faculty of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650504,China)
出处
《机械科学与技术》
CSCD
北大核心
2024年第6期962-966,共5页
Mechanical Science and Technology for Aerospace Engineering
基金
国家自然科学基金项目(61962031)。
关键词
特征提取
互补集合经验模态分解
样本熵
天鹰优化算法
支持向量机
feature extraction
complementary ensemble empirical mode decomposition
sample entropy
Tianying optimization algorithm
support vector machine
