基于ALIF-PE-GOLSSVM的齿轮箱故障诊断  

Gearbox Fault Diagnosis Based on ALIF-PE-GOLSSVM

作　　者：黄英 李喜梅 叶仁虎 王睿 Huang Ying;Li Ximei;Ye Renhu;Wang Rui(School of Intelligent Manufacturing,Wuhan Huaxia Institute of Technology,Wuhan 430223,China)

机构地区：[1]武汉华夏理工学院智能制造学院,湖北武汉430223

出　　处：《机械传动》2022年第11期146-153,共8页Journal of Mechanical Transmission

基　　金：湖北省教育厅科学研究计划指导性项目(B2014277,B2016405)。

摘　　要：提出了基于基因优化最小二乘支持向量机(Gene optimized least squares support vector ma⁃chine,GOLSSVM)的自适应局部迭代滤波(Adaptive local iterative fittering,ALIF)和排列熵(Permuta⁃tion entropy,PE)的故障诊断方法,并将该方法应用于齿轮箱的诊断,成功实现了对齿轮箱4种故障种类的识别。针对排列熵无法直接识别齿轮箱不同故障类别的问题,利用ALIF方法相较于EMD方法在去除残余噪声及抑制模式混叠上的优势,使用ALIF方法对故障信号进行降噪,提取有效分量,再计算有分量的PE值(C-PE值),以获得振动信号的多尺度特性;然后,使用基因算法对最小二乘支持向量机(Least squares support vector machine,LSSVM)进行了优化;最后,将特征向量输入到GOLSSVM,对故障特征进行分类。结果表明,所提方法相比BP神经网络和SVM在故障识别精度上有优势。An adaptive local iterative filtering(ALIF)and permutation entropy(PE)fault diagnosis method based on gene optimized least squares support vector machine(GOLSSVM)is proposed.The method is applied to the diagnosis of gearboxes,and the identification of four fault types of gearboxes is successfully realized.Aim⁃ing at the problem that permutation entropy cannot directly identify different fault categories of gearboxes,the advantages of ALIF method in removing residual noise and suppressing mode aliasing compared with EMD meth⁃od are used,and the ALIF method is used to reduce noise and extract effective components.Then the PE value with component(C-PE value)is calculated to obtain the multi-scale characteristics of vibration signals.Then the genetic algorithm is used to optimize the least squares support vector machine(LSSVM).Finally,the feature vector is input into GOLSSVM to classify the fault features.The results show that the proposed method has ad⁃vantages in fault recognition accuracy compared with BP neural network and SVM.

关 键 词：基因优化 支持向量机 自适应局部迭代滤波 排列熵 

分 类 号：TH132.41[机械工程—机械制造及自动化]