首页|强噪声背景下地铁牵引电机轴承故障识别方法研究

强噪声背景下地铁牵引电机轴承故障识别方法研究

扫码查看
原文链接
  • 万方数据
  • 维普
为了实现地铁车辆牵引电机轴承故障识别，论文针对电机轴承故障冲击被强背景噪声淹没特征提取困难的问题，利用多点最优调整的最小熵解卷积增强故障冲击成分，采用粒子群优化算法自适应地确定滤波器阶数和故障周期，获取高信噪比的故障特征信号，最后对故障特征信号进行包络谱分析实现故障识别。现场采集数据验证了该方法的有效性。
Research on the Method of Recognition of Metro Traction Motor Bearing Fault Under the Background of Strong Noise
In order to realize the fault identification of the traction motor bearing of the subway vehicle,in order to solve the problem that the fault impact of the motor bearing is submerged by the multi-source noise and it is difficult to extract the feature,the filter order and fault period are determined adaptively,and the fault characteristic signal with high signal-to-noise ratio is ob-tained.Finally,the envelope spectrum analysis of the fault characteristic signal is carried out to realize the fault identification.The data collected in the field verified the effectiveness of the method.

railway vehiclerail vehiclesbearing fault diagnosisminimum entropy deconvolution with multi-point optimal adjustmentparticle swarm optimization

王锦畅、陈威、彭乐乐、郑树彬、钟倩文

展开 >

上海工程技术大学城市轨道交通学院 上海 201620

上海航天设备制造总厂有限公司 上海 200245

牵引电机 轴承故障诊断 多点最优调整的最小熵解卷积 粒子群优化

国家自然科学基金项目国家自然科学基金项目上海市科技计划项目上海申通地铁集团资助项目上海申通地铁集团资助项目

519071175197534722010501600JS-KY20R013-32021CL-KY20R013-3-JYF-050

2024

10.3969/j.issn.1672-9722.2024.07.056

计算机与数字工程
中国船舶重工集团公司第七0九研究所

计算机与数字工程

CSTPCD
影响因子：0.355
ISSN：1672-9722
年,卷(期)：2024.52(7)