摘要
煤矿主通风机作为保障煤矿安全的重要部件,其中滚动轴承使用时间过长会容易出现故障,而滚动轴承的振动信号通常表现出非线性、非平稳特性,加大了故障诊断难度,为此提出基于EMD的煤矿主通风机滚动轴承故障诊断方法。利用EMD方法中的CEEMD算法对振动信号实施分解处理,提取信号IMF分量,并对信号不同阶IMF值实施样本熵计算,将非平稳信号分解为多个平稳的本征模态函数。针对IMF分量提取不同振动信号EMD空间状态特征谱以及IMF奇异值谱作为信号特征,联合PNN网络构建诊断网络模型,并在PNN的输入层引入自适应权重调整机制,根据特征的重要性和贡献度动态调整权重,通过优化后的模型实现滚动轴承故障诊断。实验结果表明,利用该方法开展轴承故障诊断时,诊断精度高、效果好。
As an important component to ensure the safety of coal mines,the rolling bearings are prone to failures due to extended periods of use,and the vibration signals of the rolling bearings usually show nonlinear and non-smooth characteristics,which increases the difficulty of fault diagnosis,so we propose the EMD-based fault diagnosis method for the rolling bearings of the coal mine main ventilator.The Complete Ensemble Empirical Mode Decomposition(CEEMD)algorithm within the Empirical Mode Decomposition(EMD)method is employed to decompose the vi-bration signal,thereby extracting the Intrinsic Mode Function(IMF)components of the signal.Subsequently,the sample entropy of the different order IMF values is calculated.In this manner,the non-smooth signal is decomposed into multiple smooth eigenmode functions.The EMD spatial state feature spectra of dfferent vibration signals and the IMF singular value spectra are extracted as the signal features for the IMF components,and the diagnostic network model is constructed jointly with the PNN network,and an adaptive weight adjustment mechanism is introduced into the input layer of the PNN,which dynamically adjusts the weights according to the importance and contribution of the features,so as to realize the fault diagnosis of the rolling bearings through the optimized model.The experimental results show that the diagnosis accuracy is high and the effect is good when bearing fault diagnosis is carried out by this method.
作者
李韬
杨文宇
李渊
王嘉宇
LI Tao;YANG Wen-yu;LI Yuan;WANG Jia-yu(Ccteg Information Technology Co.,Ltd,Xi'an Shaanxi 710000,China)
出处
《计算机仿真》
2025年第5期520-524,共5页
Computer Simulation
基金
中煤科工集团信息技术有限公司项目(2021021223)。
关键词
EMD算法
煤矿主通风机:滚动轴承
故障诊断模型
EMD algorithm
Coal mine main ventilation fan
Rolling bearing
Fault diagnosis model
