基于SVM的卷接机组刀盘半轴机构轴承故障识别方法

SVM-based fault diagnosis of countershaft bearing of cutoff blade carrier in cigarette maker

为解决卷接机组无法对刀盘半轴机构轴承进行在线监测和故障诊断等问题,通过研究时域和频域统计指标对SVM(Support Vector Machine)分类结果的影响,建立了基于频域特征的SVM卷接机组轴承故障智能识别方法.以预制故障的FAG 2206-2RS-TVH型轴承为对象进行试验,将在不同故障类型和故障程度轴承上采集到的振动数据进行预处理、特征提取和SVM智能训练,并进行故障诊断测试,结果表明:①在不同转速和故障程度下,基于频域统计指标的SVM分类准确率均超过92%,能够在特定转速范围和不同故障程度下实现轴承状态分类.②基于时域统计指标的准确率为77.6%,基于频域统计指标的准确率为95.6%,表明频域统计指标的SVM分类结果显著优于时域指标.该方法可为实现卷接机组轴承故障智能识别提供支持.

In order to conduct the online monitoring and fault diagnosis of the countershaft bearing of cutoff blade carrier in cigarette maker,an intelligent fault diagnosis method was established with SVM on the basis of frequency domain indexes after analyzing the influences of statistical indexes in time domain and frequency domain on SVM classification results.Testing was conducted on the FAG 2206-2RS-TVH bearings with prefabricated faults,the vibration data collected from the bearings with faults of different types and degrees were subjected to preprocessing,characteristic extraction,SVM intelligent training and fault diagnosis testing.The results showed that:1)At different rotational speeds and fault degrees,the SVM classification based on frequency domain statistic indexes presented higher accuracies of 92%and over,it was able to classify the status of bearings within a specified rotational speed range at different fault degrees.2)The accuracy based on time domain statistic indexes was 77.6%compared to that based on frequency domain statistic indexes of 95.6%,which suggested that the later was more accurate.This method provides a support for the intelligent fault diagnosis of bearing in cigarette maker.