[1]王浏洋,徐彦伟,等.基于优化 CNN 与信息融合的地铁牵引电机轴承故障诊断[J].机械与电子,2023,41(08):39-44.
 WANG Liuyang,XU Yanwei,XIE Tancheng,et al.Fault Diagnosis of Metro Traction Motor Bearing Based on Optimized CNN and Information Fusion[J].Machinery & Electronics,2023,41(08):39-44.
点击复制

基于优化 CNN 与信息融合的地铁牵引电机轴承故障诊断()
分享到:

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
41
期数:
2023年08期
页码:
39-44
栏目:
智能工程
出版日期:
2023-08-25

文章信息/Info

Title:
Fault Diagnosis of Metro Traction Motor Bearing Based on Optimized CNN and Information Fusion
文章编号:
1001-2257 ( 2023 ) 08-0039-06
作者:
王浏洋1 徐彦伟 1 2 颉潭成 1 2 曹胜博 1
1. 河南科技大学机电工程学院,河南 洛阳 471003 ;
2. 智能数控装备河南省工程实验室,河南 洛阳 471003
Author(s):
WANG Liuyang1 XU Yanwei1 2 XIE Tancheng1 2 CAO Shengbo1
( 1.School of Mechatronics Engineering , Henan University of Science and Technology , Luoyang 471003 , China ;
2.Henan Engineering Laboratory of Intelligent Numerical Control Equipment , Luoyang 471003 , China )
关键词:
参数优化卷积神经网络信息融合地铁牵引电机轴承故障诊断
Keywords:
parameter optimization CNN information fusion metro traction motor bearing fault diagnosis
分类号:
TH133.33 ; U269.6
文献标志码:
A
摘要:
针对在单一传感器下轴承故障识别率低的问题,提出一种基于优化 CNN 与信息融合的地铁牵引电机轴承故障智能检测方法。首先,选取 NU216 轴承为研究对象,预制故障缺陷;然后,采用正交试验法设计试验方案,采集 NU216 轴承的振动信号和声发射信号;其次,将原始数据通过连续小波变换,分别提取轴承的振动和声发射信号的时频域特征,并将 2 类单通道数据进行融合,得到双通道融合数据集;最后,将得到的 3 类数据集分别划分为训练集和测试集,输入优化后的卷积神经网络模型进行训练、测试。试验结果表明,基于振动信号的故障诊断准确率为 95.76% ,基于声发射信号的故障诊断准确率为 92.33% ,基于融合信号的故障诊断准确率为 98.59% 。
Abstract:
Aiming at the low recognition rate of bearing fault under single sensor , an intelligent detection method for bearing fault of metro traction motor based on optimized CNN and information fusion is proposed.Firstly , NU216 bearing is selected as the research object to prefabricate fault defects ; Then , the orthogonal test method is used to design the test scheme , and the vibration signal and acoustic emission signal of NU216 bearing are collected ; Secondly , the time and frequency domain characteristics of bearing vibration and acoustic emission signals are extracted from the original data through continuous wavelet transform , and the two types of single channel data are fused to obtain dual channel fusion data sets ; Finally , the three kinds of data sets are divided into training set and test set , and the optimized convolutional neural network model is input for training and testing.The test results show that the accuracy of fault diagnosis based on vibration signal is 95.76% , the accuracy of fault diagnosis based on acoustic emission signal is 92.33% , and the accuracy of fault diagnosis based on fusion signal is 98.59%.

参考文献/References:

[ 1 ] 谢天雨,董绍江 . 基于改进 CNN 的噪声以及变负载条件下滚动轴承故障诊断方法[ J ] . 噪声与振动控制,2021 , 41 ( 2 ): 111-117.

[ 2 ] 米月花,霍国涛 . 多传感器信息融合的滚动轴承振动性能研究[ J ] . 机械科学与技术, 2021 , 40 ( 8 ): 1233-1239.
[ 3 ] SOOTHER D K , KALWAR I H , HUSSAIN T , et al. A novel method based on UNET for bearing fault diagnosis [ J ] .Computers , materials andcontinua , 2021 , 69( 1 ): 393-408.
[ 4 ] 张弘斌,袁奇,赵柄锡,等 . 采用多通道样本和深度卷积神经网络的轴承故障诊断方法[ J ] . 西安交通大学学报,2020 , 54 ( 8 ): 58-66.
[ 5 ] 张西宁,刘书语,余迪,等 . 改进深度卷积神经网络及其在变工况滚动轴承故障诊断中的应用[ J ] . 西安交通大学学报,2021 , 55 ( 6 ): 1-8.
[ 6 ] HABBOUCHE H , AMIRAT Y , BENKEDJOUH T , et al.Bearing fault event-triggered diagnosis using a variational mode decomposition-based machine learning approach [ J ] .IEEE Transactions on energy conversion ,2022 , 37 ( 1 ): 466-474.
[ 7 ] 张超,秦敏敏,张少飞 . 基于 1D CNN-XGBoost 的滚动轴承故障诊断 [ J ] . 机床与液压, 2022 , 50 ( 16 ):169-173.
[ 8 ] 王军敏,樊养余,李祖贺 . 基于深度卷积神经网络和迁移学习的纹理图像识别[ J ] . 计算机辅助设计与图形学学报,2022 , 34 ( 5 ): 701-710.
[ 9 ] OZCAN I H , DEVECIOGLU O C , INCE T , et al.Enhanced bearing fault detection using multichannel , multilevel 1D CNN classifier [ J ] .Electrical engineering ,2022 , 104 ( 2 ): 435-447.
[ 10 ] WANG J X , WANG D Z , WANG S H , et al.Fault diagnosis of bearings based on multi-sensor information fusion and 2D convolutional neural network [ J ] . IEEE Access , 2021 , 9 : 23717-23725.
[ 11 ] 郭双全 . 多卷积神经网络融合的滚动轴承故障识别方法[ J ] . 装备机械, 2021 ( 2 ): 79-84.
[ 12 ] 姚明镜,唐璇,吕昂 . 基于改进卷积神经网络的行星齿轮箱故障诊断研究[ J ] . 制造技术与机床,2021 ( 7 ):141-145.
[ 13 ] 蒙志强,董绍江,潘雪娇,等 . 基于改进卷积神经网络的滚动轴承故障诊断[ J ] . 组合机床与自动化加工技术,2020 ( 2 ): 79-83.
[ 14 ] ZHANG J Q , SUN Y , GUO L , et al.A new bearing fault diagnosis method based on modified convolutional neural networks [ J ] .Chinese journal of aeronautics , 2020 , 33 ( 2 ): 439-447.
[ 15 ] XU G W , LIU M , JIANG Z F , et al.Online fault diagnosis method based on transfer convolutional neural networks [ J ] .IEEE Transactions on instrumentation and measurement , 2020 , 69 ( 2 ): 509-520.
[ 16 ] 刘飞,陈仁文,邢凯玲,等 . 基于迁移学习与深度残差网络的滚动轴承快速故障诊断算法[ J ] . 振动与冲击, 2022 , 41 ( 3 ): 154-164.
[ 17 ] 郑海波,李志远,陈心昭 . 基于连续小波变换的齿轮故障诊断方法研究[ J ] . 机械工程学报, 2002 , 38 ( 3 ): 69-73.

相似文献/References:

[1]吕明珠1,2,苏晓明 1,等. 改进粒子群算法优化的支持向量机在滚动轴承故障诊断中的应用[J].机械与电子,2019,(01):42.
 ,,et al.Application of SVM Optimized by IPSO in Rolling Bearing Fault Diagnosis[J].Machinery & Electronics,2019,(08):42.
[2]章玮玮,张根烜,叶 锐,等.某光控相控阵雷达组件热设计与参数优化[J].机械与电子,2019,(06):22.
 ,,et al.Thermal Design and Parameter Optimization of Optical Controlled Phased Array Radar[J].Machinery & Electronics,2019,(08):22.
[3]王骁贤,张保华,陆思良.基于连续小波变换和卷积神经网络的无刷直流电机故障诊断[J].机械与电子,2018,(06):29.
 WANG Xiaoxian,ZHANG Baohua,LU Siliang.Fault Diagnosis of Brushless Direct Current Motor Based on Continuous Wavelet Transform and Convolutional Neural Network[J].Machinery & Electronics,2018,(08):29.
[4]刘志宇,黄亦翔.基于深度学习和迁移学习的液压泵健康评估方法[J].机械与电子,2018,(09):67.
 LIU Zhiyu,HUANG Yixiang.Health Assessment for Hydraulic Pump Based on Deep Learning and Transfer Learning[J].Machinery & Electronics,2018,(08):67.
[5]安莉,朱旭辉,罗建国.某机载电子机箱的动力学仿真及参数优化[J].机械与电子,2016,(02):3.
 AN Li,ZHU Xuhui,LUO Jianguo.Dynamic Analysis and Parameters Optimization of an Airborne Electronic Equipment Box[J].Machinery & Electronics,2016,(08):3.
[6]屈长龙,王喜顺.基于FLUENT的高压水射流除锈的流场仿真及射流参数优化[J].机械与电子,2016,(02):24.
 QU Changlong,WANG Xishun.Jet Flow Simulation and Parameters Optimization of High Pressure Water Jet for Derusting Based on FLUENT[J].Machinery & Electronics,2016,(08):24.
[7]曾雪琼,黎杰.基于卷积神经网络的时频图像识别研究[J].机械与电子,2016,(05):25.
 ZENG Xueqiong,LI Jie.Time-frequency Image Recognition Based on Convolutional Neural Network[J].Machinery & Electronics,2016,(08):25.
[8]严宏.基于拓扑优化的某机载显控台轻量化设计[J].机械与电子,2016,(11):22.
 YAN Hong.Design of a Lightweight Airborne Display Console Based on Topological Optimization[J].Machinery & Electronics,2016,(08):22.
[9]赵吉庆,黄晓华,张言中,等.基于Fluent的中间摆臂注射成型工艺参数优化[J].机械与电子,2020,(01):19.
 ,,et al.Optimization of Intermediate Swing Arm Injection Molding Parameters Based on Fluent[J].Machinery & Electronics,2020,(08):19.
[10]齐爱玲1,李 琳1,朱亦轩2,等.基于融合特征的双通道CNN滚动轴承故障识别[J].机械与电子,2021,(05):15.
 QI Ailing,LI Lin,ZHU Yixuan,et al.Dual Channel CNN Bearing Fault Identification Based on Fusion Feature[J].Machinery & Electronics,2021,(08):15.

备注/Memo

备注/Memo:
收稿日期: 2022-11-14
基金项目:国家自然科学基金资助项目( 51805151 );河南省高等学校重点科研项目( 21B460004 )
作者简介:王浏洋 ( 1997- ),男,河南新蔡人,硕士研究生,研究方向为故障诊断;徐彦伟 ( 1978- ),男,河南洛阳人,博士,副教授,研究方向为制造装备精度设计、故障诊断,通信作者。
更新日期/Last Update: 2023-09-08