[1]陈万胜,谭 震,高永军,等.矿用切带机主轴轴承故障诊断方法研究[J].机械与电子,2026,44(04):53-61.
　CHEN Wansheng,TAN Zhen,GAO Yongjun,et al.Research on Fault Diagnosis Method for Main Shaft Bearings of Mining Band Cutting Machines[J].Machinery & Electronics,2026,44(04):53-61.
点击复制

矿用切带机主轴轴承故障诊断方法研究()
分享到：

《机械与电子》[ISSN:1001-2257/CN:52-1052/TH]

卷:
44
期数:
2026年04期
页码:
53-61
栏目:
智能检测
出版日期:
2026-04-27

文章信息/Info

Title:
Research on Fault Diagnosis Method for Main Shaft Bearings of Mining Band Cutting Machines
文章编号:
1001-2257(2026)04-0053-09
作者:
陈万胜1; 2; 谭 震1; 高永军1; 朱信龙1; 刘 杰1
陈万胜1,2,谭 震1,高永军1,朱信龙1,刘 杰1
Author(s):
CHEN Wansheng1; 2; TAN Zhen1; GAO Yongjun1; ZHU Xinlong1; LIU Jie1
(1.Shenmu Ningtiaota Mining Co.,Ltd.,Shaanxi Coal Group,Yulin 719300,China;
2.Liaoning Technical University,Fuxin 123000,China)
关键词:
切带机; 轴承; 故障诊断; 复合滤波经验模态分解; 最优熵权混合校正
Keywords:
belt cutting machine; bearing; fault diagnosis; composite filtering empirical mode decomposition(CFEMD); optimal entropy weight mixed correction (OEWMC)
分类号:
TH133.3;TP391
文献标志码:
A
摘要:
针对钢丝绳输送带切带机主轴轴承在低转速和高扭矩工况下故障振动信号微弱、噪声干扰强,
导致故障诊断困难的问题,提出一种基于复合滤波经验模态分解(CFEMD)与最优熵权混合校正
(OEWMC)并结合一维卷积神经网络(1D CNN)的智能诊断方法。首先,采用窗函数与低通滤波器构成的
复合滤波器对振动信号进行降噪处理。其次,通过经验模态分解(EMD)将信号分解为多个本征模态函数
(IMF)分量,依据其与原始信号的相关系数确定有效阶数,并构建全局特征矩阵与局部特征矩阵。然后,分
别计算2类矩阵的最优熵权及其表征向量,通过混合校正模型修正后,与分量权重融合形成综合表征值。最
后,将表征值序列输入1D CNN,利用卷积层自适应提取深层故障特征,经池化层压缩和全连接层分类,实
现高精度故障识别。实验结果表明,该方法对于钢丝绳输送带切带机主轴轴承在低速、高冲击、强噪声条件
下仍具有较高的诊断精度,准确度达到100%,且计算效率高、稳定性强与通用性好。
Abstract:
Aiming at the problems of weak fault vibration signals,strong noise interference,and difficulty
in fault diagnosis for the main shaft bearing of the wire rope conveyor belt cutting machine under low speed
and high torque operating conditions,an intelligent diagnosis method based on composite filtering empirical
mode decomposition (CFEMD) and optimal entropy weight hybrid correction (OEWMC) combined
with one dimensional convolutional neural network (1D CNN) is proposed.Firstly,a composite filter,
consisting of a window function and a low pass filter,is adopted to reduce the noise of the vibration signal.
Secondly,the signal is then decomposed into multiple eigenmode function (IMF) components through
empirical mode decomposition (EMD).The effective order is determined based on the correlation coefficients
with the original signal,and both the global and local feature matrices are constructed.Subsequently,
the optimal entropy weights and their representation vectors of the two matrix types are calculated separately.
After correction through a hybrid model,these are fused with the component weights to form a
comprehensive representation value.Finally,the sequence of characterization values is input into the 1D
CNN network.The deep fault features are adaptively extracted by using the convolutional layer,compressed
by the pooling layer and classified by the fully connected layer to achieve high precision fault i-
dentification.The experimental results show that this method maintains high diagnostic accuracy for the
main shaft bearing of the wire rope conveyor belt cutting machine under conditions of low speed,high impact
and strong noise,achieving an accuracy of 100%.The method also exhibits the advantages including
high computational efficiency,strong stability and good universality.

参考文献/References:

[1] 陈鑫,张飞祥,郭瑜,等.面向低转速及变转速复合工况下滚动轴承故障诊断研究[J].振动工程学报,2026,39
(2):584 594.
[2] LI X,MA Z G,KANG D,et al.Fault diagnosis for rolling bearing based on VMD FRFT[J].Measurement,
2020,155:107554.
[3] 刘泽,鲁杰,张松.基于时频分析与卷积神经网络的滚动轴承故障诊断[J].机械管理开发,2025,40(10):82 85.
[4] YU Q,LI J,LI Z,et al.A clustering K SVD based sparse representation method for rolling bearing fault
diagnosis[J].Insight non destructive testing and condition monitoring,2021,63(3):160 167.
[5] ZHENG K,LI T,SU Z,et al.Faults diagnosis of rolling bearings based on shift invariant K singular value
decomposition with sensitive atom nonlocal means enhancement[J].Measurement,2019,135:836 851.
[6] LIANG K X,ZHAO M,LIN J,et al.An information based K singular value decomposition method for
rolling element bearing diagnosis[J].ISA Transactions,2020,96:444 456.
[7] YU Y,LI C M,WANG T Y,et al.Fault diagnosis and classification for bearing based on EMD ICA[C]∥
Proceedings of 2011 International Conference on Electronic and Mechanical Engineering and Information
Technology.New York:IEEE,2011:2715 2718.
[8] WANG J,DU G,ZHU Z,et al.Fault diagnosis of rotating machines based on the EMD manifold[J].Mechanical
systems and signal processing,2020,135:106443.
[9] 李兴城,方智超,王飞.MS FMD与SCA 在滚动轴承故障诊断中的应用[J].实验室研究与探索,2025,44
(12):98 104.
[10] 胡少轩,郭雨竹,苏妮娜.基于熵权法的煤气共采一体化开发策略研究[J].能源与节能,2025(11):17 20.
[11] 朱莎,李绪阳,秦翔宇.基于CNN 识别振动图谱的双馈风电机组故障诊断[J/OL].发电设备,2025:1 12
[2026 01 05].https:∥link.cnki.net/urlid/31.1391.TN.20251225.1430.004.
[12] 杨旭,吴程飞,黄健,等.基于树形决策卷积神经网络的滚动轴承故障分层诊断[J].北京工业大学学报,
2026,52(1):64 74.
[13] 赵前程,王俊翔,解志杰,等.包络灰度图与CNN在滚动轴承故障诊断中的应用[J/OL].机械设计与制造,
2025:1 9 [2026 02 27].https:∥doi.org/10.19356/j.cnki.1001 3997.20251223.007.
[14] 孔令成.煤矿刮板输送机智能化故障诊断系统设计研究[J].煤矿机械,2026,47(1):188 192.
[15] 毋韶杰.煤矿带式输送机运行故障诊断技术研究[J].西部探矿工程,2025,37(12):83 85.

相似文献/References:

[1]韩海燕,李娜娜,尚雪梅.颗粒间距及相对运动对轴承油膜压力的影响[J].机械与电子,2019,(03):27.
　HAN Haiyan,LI Nana,SHANG Xuemei.Effects of Particles Distance and Relative Motion on Oil Film Pressure of Bearing[J].Machinery & Electronics,2019,(04):27.
[2]吉 莉,卯 杰.电机转子轴承拆卸工装的研制与应用[J].机械与电子,2019,(05):46.
　.Development and Application of Disassembly Tooling for Electronic Rotationg Shaft Bearing[J].Machinery & Electronics,2019,(04):46.
[3]孟庆宇.基于 ＥＥＭＤ- ＳＶＭ 的自动扶梯主驱动轴轴承故障诊断方法研究[J].机械与电子,2020,(05):51.
　Research on Fault Diagnosis Method for Main Drive Shaft Bearing of Escalator Based on EEMD-SVM [J].Machinery & Electronics,2020,(04):51.
[4]魏常庆,张 皓.铁路货车轮毂对轴承压装力-位移曲线的影响研究[J].机械与电子,2024,42(05):76.
　WEI Changqing,ZHANG Hao.Research on the Influence of Railway Freight Car Hub on the Force Displacement Curve of Bearing Press Mounting[J].Machinery & Electronics,2024,42(04):76.
[5]骆东松,马立东.基于深度学习的风电机组轴承诊断系统[J].机械与电子,2024,42(07):69.
　LUO Dongsong,MA Lidong.Deep Learning based Bearing Diagnosis System for Wind Turbines[J].Machinery & Electronics,2024,42(04):69.
[6]武 逵,王城宇,万书亭.基于 IGWO-MCKD-ROMP 的齿轮箱轴承故障特征提取方法[J].机械与电子,2025,(01):3.
　WU Kui,WANG Chengyu,WAN Shuting.Fault Feature Extraction Method of Gearbox Bearings Based on IGWO-MCKD-ROMP[J].Machinery & Electronics,2025,(04):3.

备注/Memo

备注/Memo:
收稿日期:2026-01-14
基金项目:辽宁省教育厅基础项目(JYTJT20220293)
作者简介:陈万胜 (1983-),男,陕西彬县人,博士研究生,高级工程师,研究方向为工矿装备自动化与智能化。
更新日期/Last Update: 2026-05-11