摘要
为有效提高滚动轴承故障诊断准确率,提出了基于自适应噪声集合经验模态分解(CEEMDAN)气泡熵(BE)和支持向量机(SVM)相结合的轴承故障诊断方法。首先经CEEMDAN分解得到一系列本征模态函数(IMF)分量,然后筛选重要IMF分量计算其气泡熵值,构建故障特征向量并输入到经算术优化算法(AOA)优化的SVM模型中进行训练和轴承故障分类。结果表明该方法识别准确率高达99.2%,相比GA-SVM准确率提升了2.8%,也能成功识别出滚动轴承单一故障与复合故障,可以用于轴承故障分类。
In order to improve the accuracy of rolling bearing fault diagnosis effectively,a method of bearing fault diagnosis based on the combination of complete ensemble empirical model decomposition with adaptive noise,bubble entropy and support vector machine is proposed.Firstly,a series of intrinsic modal function components were obtained by CEEMDAN.Then,the important IMF components was chose through the chart and calculate it.Fault feature vectors were constructed and input into the SVM optimized by arithmetic optimization algorithm to train for bearing fault classification.The results show that the accuracy of this method is up to 99.2%which is 2.8%higher than that of GA-SVM.It can also successfully identify the single fault and compound fault of rolling bearing,so it can be used for bearing fault classification.
作者
陈剑
杨惠杰
季磊
徐庭亮
黄志
李雪原
Chen Jian;Yang Huijie;Ji Lei;Xu Tingliang;Huang Zhi;Li Xueyuan(Institute of Noise and Vibration,Hefei University of Technology,Hefei 230009,China;Anhui Automotive NVH Engineering and Technology Research Center,Hefei 230009,China)
出处
《电子测量技术》
北大核心
2023年第15期165-169,共5页
Electronic Measurement Technology
基金
安徽省科技重大专项(17030901049)资助
关键词
自适应经验模态分解
气泡熵
支持向量机
故障诊断
complete ensemble empirical model decomposition with adaptive noise
bubble entropy
support vector machine
fault diagnosis
