国外文献 > 1.轴承 > 7. 智能方法与计算 > 神经网络
关键词搜索：
| 标 题： |
A comparative Study for Ball Bearing Fault Classification Using Kernel-SVM with Kullback Leibler Divergence Selected Features
基于Kullback-Leibler发散选择特征的核-支持向量机在滚动轴承故障分类中的比较研究 |
| 作 者： |
Zahra MEZNI
Claude DELPHA
Demba DIALLO
Ahmed BRAHAM |
| 关键词： |
Ball bearing faults classification [滚动轴承故障分类]
Support vector machine [ 支持向量机]
Wavelet SVM [ 小波SVM]
Statistical analysis [ 统计分析]
Empirical mode decomposition [ 经验模态分解]
Intrinsic mode function selection [ 内在模式功能选择]
Kullback leibler divergence [ 库尔巴克-莱布勒离散性]
Fault diagnosis [ 故障诊断] |
| 出版年： |
2019 |
| 会议名： |
45th Annual Conference of the IEEE Industrial Electronics Society (IECON 2019)
第45届IEEE工业电子学会年会（IECON 2019） |
| 届 次： |
45th |
| 摘 要： |
Bearing early fault detection and diagnosis (classification, estimation, ...) is a key issue in Condition Monitoring (CM) of rotating machinery. In this context, we propose in this paper a multi-fault classification comparison between traditional Support Vector Machine (SVM) solutions and wavelet SVM (WSVM). For this work several kernel and wavelet functions were considered in the Kullback Leibler Divergence (KLD) framework. First, Empirical Mode Decomposition (EMD) is employed to preprocess vibration signals acquired from the rolling bearings elements. Second, a specific statistical analysis study is performed to select the most salient components from the different obtained Intrinsic Mode Functions (IMFs). Then, the KLD of the retained IMFs is calculated to carry out the classification of three bearing ball fault severities for several operating conditions. Thanks to four criteria, namely the classification accuracy rate average (ARA), the support vector average (SVA), the training time (T_rt) and testing time (T_st), our results are derived to highlight the technique allowing to obtain the better results.
早期故障检测与诊断（分类、估计等）是旋转机械状态监测（CM）中的关键问题。本文提出了一种传统支持向量机（SVM）方法与小波SVM（WSVM）之间的多故障分类对比研究。在Kullback-Leibler发散（KLD）框架下，本文考虑了多种核函数和小波函数。首先，采用经验模分解（EMD）对滚动轴承元件采集的振动信号进行预处理； 其次，通过特定的统计分析方法，从不同得到的本征模函数（IMFs）中筛选出最具代表性的成分； 然后，计算保留IMFs的KLD值，以实现对三种轴承滚珠故障严重程度在多种运行工况下的分类。基于四个评价指标——分类准确率平均值（ARA）、支持向量平均值（SVA）、训练时间（T_rt）和测试时间（T_st），我们得出结论，表明该技术能够获得更优的分类效果。 |
| 中文内容为网络AI翻译，专业术语未必准确，仅供参考。 |
京公网安备 11010202009788