[1]方学宠,娄益凡,吴安定,等.基于 SVMD 与 SLLE 的机械设备齿轮箱故障诊断方法[J].机械与电子,2022,(01):36-41.
　FANG Xuechong,LOU Yifan,WU Anding,et al.Fault Diagnosis Method of Gearbox in Mechanical Equipment Based on SVMD and SLLE[J].Machinery & Electronics,2022,(01):36-41.
点击复制

基于 SVMD 与 SLLE 的机械设备齿轮箱故障诊断方法()
分享到：

机械与电子[ISSN:1001-2257/CN:52-1052/TH]

卷:
期数:
2022年01期
页码:
36-41
栏目:
机电一体化技术
出版日期:
2022-01-20

文章信息/Info

Title:
Fault Diagnosis Method of Gearbox in Mechanical Equipment Based on SVMD and SLLE
文章编号:
1001-2257 ( 2022 ) 01-0036-06
作者:
方学宠 1 ; 娄益凡 1 ; 吴安定 1 ; 覃嘉祺 2
1. 温州市特种设备检测院,浙江 温州 325000 ; 2. 武汉科技大学,湖北 武汉 430081
Author(s):
FANG Xuechong1 ;  LOU Yifan1 ;  WU Anding1 ;  QIN Jiaqi2
(1.Wenzhou Special Equipment Inspection Institute , Wenzhou 325000 , China ; 2.Wuhan University of Science and Technology , Wuhan 430081 , China )
关键词:
连续变分模式分解; 监督局部线性嵌入; 机械设备齿轮箱; 故障诊断
Keywords:
successive variational mode decomposition ;  supervised locally linear embedding ;  mechanical equipment gearbox ;  fault diagnosis
分类号:
TH13
文献标志码:
A
摘要:
针对机械设备齿轮箱故障识别难度较大,且采集的信号通常受到强背景噪声干扰等问题,提出一种将连续变分模式分解( SVMD )和监督局部线性嵌入( SLLE )相结合的算法,用于机械设备齿轮箱的故障诊断。首先通过 SVMD 对采集到的振动信号进行分解,得到特定的期望模式分量;然后再获取这些分量的类标签信息,并利用这些类标签信息来缩放不同类别分量间的欧几里德距离;最后通过 SLLE 对这些处理后的样本数据进行降维处理,从而准确识别机械设备齿轮箱的故障类型。通过对模拟仿真信号和从齿轮箱故障模拟实验平台采集到的振动信号进行分析,聚类识别的正确率可以达到 95.27% ,验证了所提出方法的可行性。
Abstract:
Aiming at the difficulty of identifying faults in gearbox of mechanical equipment and the the prolem that the collected signals are usually interfered by strong background noise , a method that combines Successive Variational Mode Decomposition ( SVMD ) and Supervised Locally Linear Embedding ( SLLE ) to achieve faults identification and diagnosis of gearbox in mechanical equipment is proposed.Firstly , the vibration signal collected by the gearbox is decomposed by SVMD to obtain the specific mode functions. Then it can get the class label information of these modes , and use these information to scale the Euclidean distance between different samples.Finally , SLLE is used to reduce the dimension of the processed sample data , so as to accurately identify the fault type of the mechanical equipment gearbox.In this paper , the numerical simulation signal and the data collected from the gearbox fault simulation experiment platform are analyzed , and the accuracy of cluster recognition can reach 95.27% , which verifies the feasibility of the proposed method.

参考文献/References:

[ 1 ] 李勇,钱尼君,陈星斌,等 . 基于 EEMD Treelet 和高斯过程的起重机齿轮故障诊断[ J ] . 计算机测量与控制,2021 , 29 ( 7 ): 36-40 , 51.

[ 2 ] 沈科宇 . 基于支持向量机的港口起重机减速箱故障诊断研究[ D ] . 南昌:华东交通大学,2020.
[ 3 ] HUANG S X , WANG X P , LI C F , et al.Data decomposition method combining permutation entropy and spectral substitution with ensemble empirical mode decomposition [ J ] .Measurement , 2019 , 139 : 438-453.
[ 4 ] 张安安,黄晋英,卫洁洁,等 . 基于 EMD SVD 与 PNN的行星齿轮箱故障诊断研究[ J ] . 机械传动,2018 , 42( 12 ): 160-165.
[ 5 ] SMITH S J.The local mean decomposition and its application to EEG perception data [ J ] .Journal of the royal society interface , 2005 , 2 ( 5 ): 443-454.
[ 6 ] JIA J D , REN G.An improved adaptive VMD method and its application in wear condition monitoring of main bearing [ J ] .Vibroengineering PROCEDIA , 2021 , 38 : 26-31.
[ 7 ] 王奉涛,柳晨曦,张涛,等 . 基于 k 值优化 VMD 的滚动轴承故障诊断方法 [ J ] . 振动、测试与诊断,2018 , 38( 3 ): 540-547.
[ 8 ] 刘建昌,权贺,于霞,等 . 基于参数优化 VMD 和样本熵的滚动轴承故障诊断[ J ] . 自动化学报, 2019 , 12 ( 12 ): 1-12.
[ 9 ] NAZARI M , SAKHAEI S M.Successive variational mode decomposition [ J ] .Signal processing , 2020 , 174 : 107610-1-107610-10.
[ 10 ] 谢小欣,胡建中,许飞云,等 . 一种基于多流形局部线性嵌入算法的故障诊断方法 [ J ] . 机械工程学报,2013 , 49 ( 11 ): 79-83.
[ 11 ] RIDDER D D , KOUROPTEVA O , OKUN O , et al. Supervised locally linear embedding [ C ]// Artificial Neural Networks and Neural Information Processing ICANN / ICONIP 2003 , 2003 : 333-341.

备注/Memo

备注/Memo:
收稿日期: 2021-09-15
基金项目:国家自然科学基金资助项目( 51805382 );浙江省市场监管系统科研计划项目( 20190332 )
作者简介:方学宠 ( 1981- ),男,浙江温州人,硕士,高级工程师,研究方向为机电特种设备。
更新日期/Last Update: 2022-02-28