| 小波包和GA-SVM在轴承故障诊断中的应用 |
| |
| 引用本文： | 蒋恩超,傅攀,张思聪.小波包和GA-SVM在轴承故障诊断中的应用[J].应用声学,2017,25(10):7-10. |
| |
| 作者姓名： | 蒋恩超 傅攀 张思聪 |
| |
| 作者单位： | 西南交通大学 机械工程院,成都 610031,西南交通大学 机械工程院,成都 610031,西南交通大学 机械工程院,成都 610031 |
| |
| 基金项目： | 中央高校基本科研业务费专项资金资助(2682016CX033) |
| |
| 摘 要： | 为了解决傅里叶变换难以兼顾信号在时域和频域中的全貌和局部化特征以及支持向量机惩罚参数 和核函数参数 选取的问题，提出了基于小波包和GA-SVM的轴承故障诊断方法。首先通过实验采集多种工况下故障轴承和正常轴承的振动信号，从振动信号中提取能够表征轴承运行状态的时频域特征以及基于小波包分析的特征向量来作为GA-SVM的输入，然后在SVM的基础上，针对SVM的惩罚参数和核函数参数在不同应用场景下的取值难以确定的特性，采用了遗传算法对支持向量机进行参数优化的GA-SVM算法进行模式识别。实验结果显示，基于小波包和GA-SVM的轴承故障诊断方法比SVM和BP都具有更高的识别精度。
|
| 关 键 词： | 滚动轴承 模式识别 GA-SVM 小样本 |
| 收稿时间： | 2017/3/3 0:00:00 |
| 修稿时间： | 2017/4/24 0:00:00 |
Application of Wavelet Packet and GA-SVM in Bearing Fault Diagnosis |
| |
| Jiang Enchao,Fu Pan and Zhang Sicong.Application of Wavelet Packet and GA-SVM in Bearing Fault Diagnosis[J].Applied Acoustics,2017,25(10):7-10. |
| |
| Authors: | Jiang Enchao Fu Pan and Zhang Sicong |
| |
| Institution: | School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China,School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China and School of Mechanical Engineering,Southwest Jiaotong University,Chengdu 610031,China |
| |
| Abstract: | In order to improve the accuracy of bearing fault diagnosis in small sample situation. In this paper, we used the method of GA-SVM which uses genetic algorithm to optimize the SVM as the penalty parameter and kernel function parameters of SVM are difficult to determine. And then We Collected various vibration signals of fault bearing and normal, extract the characteristics in time ,frequency domain and characteristics of wavelet feature vector. And we use GA-SVM in the end . the result shows that The accuracy of the fault diagnosis of bearings is up to 100% in case of both multiple samples and small samples, compared with GA-SVM is more advanced. |
| |
| Keywords: | Bearing pattern recognition GA-SVM Limited-sample |
|
| 点击此处可从《应用声学》浏览原始摘要信息 |
| 点击此处可从《应用声学》下载免费的PDF全文 |
|
