基于振动信号的热辊运行监测方法
2022-11-22 14:53:21   来源：   评论：0 点击：

关键词：振动信号；热辊；随机子空间；振动加速度幅值；旋转机械
中图分类号：TS152.7          文献标志码：B          文章编号：1001-9634(2022)05-0056-05

收稿日期：2021-12-13
作者简介：刘冠华（1995—），男，济南人，助理工程师,主要从事机械振动、轴承润滑与冷却方面的工作。
 
   
Abstract:In order to reduce the failure of chemical fiber equipment caused by the damage of the heat roller bearing，a monitoring method of heat roller operation based on vibration signal is proposed to monitor the service life and damage status of the heat roller bearing.The vibration signal of the heat roller is collected regularly by the vibration sensor，the random subspace method is used to calculate the vibration signal，and the corresponding vibration frequency and vibration acceleration amplitude parameters in the calculation result are extracted to judge the running state of the heat roller.It is pointed out that the random subspace method can accurately calculate the frequency of each vibration component in the overall vibration of the heat roller，but the calculation accuracy decreases when there are many vibration components.By comparing the multiple order calculation results，the non-stable frequency can be removed，and the calculation accuracy of frequency and acceleration amplitude can be improved.When the two order vibration frequencies are close to each other，there is a large error between the calculated vibration acceleration amplitude and the spectral amplitude after Fourier transform.Taking 130% of the vibration acceleration amplitude calculated by the random subspace method to make up for the error of the calculation result，the judgment results show that the vibration of some test samples is too large，but it is consistent with the situation that the test samples are not balanced for the whole machine，which indicates that the vibration monitoring method is effective.
Key Words:vibration signal；heat roller；random subspace；vibration acceleration amplitude；rotating machinery
 
参考文献:
[1] 裴桂鑫.热辊电机油雾润滑系统的电气升级[J].纺织机械，2014(5):90-92.
[2] 孙群丽，刘长良，甄成刚.隐马尔科夫模型在滚动轴承故障诊断中的应用[J].热能动力工程，2018， 33（10）:95-100.
[3] 郝俊虎，胡毅.基于XGBoost和自回归模型的轴承故障诊断和预警方法研究[J].组合机床与自动化加工技术，2020(2):140-142.
[4]  Muhammad Amar，Iqbal Gondal，Campbell Wilson.Vibration Spectrum Imaging:A Novel Bearing Fault Classification Approach[J].IEEE Transactions on Industrial Electronics，2015，62(1):494-502.
[5] Rui Zhao，Ruqiang Yan，Jinjiang Wang，et al.Learning to Monitor Machine Health with Convolutional Bi-Directional LSTM Networks[J].Sensors，2017，17(2):273.
[6] 刘焕云，王军宁，何迪，等.仿生模式识别目标自适应跟踪算法[J].西安电子科技大学学报，2013， 40(4):142-148.
[7] Randall Robert Bond.Vibration-Based Condition Monitoring:Industrial，Aerospace and Automotive Applications[M].John Wiley & Sons，2010.
[8] Aurelien Prudhom，Jose Antonino-Daviu，Hubert Razik.et al.Time-Frequency Vibration Analysis for the Detection of Motor Damages Caused by Bearing Currents[J].Mechanical Systems & Signal Processing，2017(84):747-762.
[9] 陈东超，徐婧，洪瑞新，等.基于广义回归神经网络的旋转机械振动特征预测[J].汽轮机技术，2015， 57(5):360-362.
[10] 郭玉.基于仿生模式识别的机械故障诊断方法研究[D].西安：西安工业大学，2016.