摘要
煤矿主副井提升机是煤矿生产中的关键设备,在井下煤炭提升以及设备和人员运送环节承担着重要作用,其工作状况的好坏,将直接影响矿井能否正常生产。本文以提升机主轴装置为研究对象,研究运用小波包能量法对监测的振动信号提取特征向量,基于概率神经网络建立故障诊断模型,在Matlab环境下进行仿真。结果表明,基于概率神经网络(PNN)建立的故障诊断模型收敛速度快,能够对提升机主轴装置的故障类型及故障位置进行很好地预测。
The main and auxiliary shafts hoist of mine bears the important task of lifting and transporting equipment which is the key equipment in coal production .What’s more ,the quality of their working conditions directly affects the production of the mine .In this paper ,the hoist spindle apparatus was used as the research object ,we tried to use wavelet packet energy method to extract the feature vectors from monitoring vibration signals and establish the fault diagnosis model based on probabilistic neural network（PNN） .The simulation results in MATLAB environment showed that the mine hoist fault diagnosis model based on PNN has fast convergence and can well predict the fault type and position .
出处
《电子测量技术》
2016年第11期187-189,194,共4页
Electronic Measurement Technology
关键词
矿井提升机
故障诊断
小波包分解
概率神经网络
mine hoist
fault diagnosis
wavelet packet decomposition
probabilistic neural network
