基于BP神经网络的炉辊轴承故障诊断  

Fault Diagnosis of Furnace Roll Bearing Based on BP Neural Network

作　　者：王玉坤 牛锐祥 Wang Yukun;Niu Ruixiang(Shanxi Taigang Stainless Steel Co.,Ltd.,Taiyuan Shanxi 030002,China)

机构地区：[1]山西太钢不锈钢股份有限公司冷轧硅钢厂,山西太原030002

出　　处：《山西冶金》2023年第9期52-54,共3页Shanxi Metallurgy

摘　　要：为了提升连续退火炉炉辊轴承故障诊断的准确率,采用BP神经网络诊断炉辊轴承故障。通过多功能智慧移动终端测量炉辊轴承振动信号,提取一定时间间隔内振动数据的12个时域指标;制作数据集并划分训练集、验证集和测试集;基于BP神经网络构建炉辊轴承故障诊断模型,将数据集输入模型进行训练和验证。实验结果表明,基于BP神经网络的炉辊轴承故障诊断准确率达到了97.92%,有效提高了炉辊轴承的故障诊断准确率,为炉辊轴承的智能故障诊断提供了新思路。In order to improve the accuracy of furnace roll bearing fault diagnosis of continuous annealing furnace,BP neural network is used to diagnose the emulsion pump fault.Firstly,12 time-domain eigenvalues of vibration data within a certain time interval are extracted by measuring the vibration signal of furnace roll bearing through multi-functional intelligent mobile terminal.Then,make the data set and divide the training set,verification set and test set.Finally,the fault diagnosis model of furnace roll bearing is built based on BP neural network,and the data set is input into the model for training and verification.The experimental results show that the fault diagnosis and recognition rate of furnace roll bearing based on BP neural network reaches 97.92%,which effectively improves the fault diagnosis and recognition rate of furnace roll bearing,and provides a new idea for intelligent fault diagnosis of furnace roll bearing.

关 键 词：BP神经网络 炉辊轴承 故障诊断 

分 类 号：TF31[冶金工程—冶金机械及自动化]