• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>International Conference on Mechanical Engineering and Mechanics vol.2; 20051026-28; Nanjing(CN) >Fault Detecting Using Support Vector Data Description with Genetic Algorithm
【24h】

Fault Detecting Using Support Vector Data Description with Genetic Algorithm

机译：支持向量机数据描述与遗传算法相结合的故障检测

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

Through the online fault detecting, we usually get more healthy condition samples than fault ones. In order to solve the problem of insufficient fault samples in intelligent monitoring and diagnosis for machinery, one-class classification-Support vector data description (SVDD) is proposed. It is only trained by the healthy data, also known as target data and never sees the "unhealthy" and can distinguish normal and abnormal condition effectively. In this paper we describe the basic algorithm of SVDD and use the experimental vibration data of bearings as the input of SVDD classifier. In order to select the most efficient parameter for classification, genetic algorithm (GA) is used to optimize the available input parameters and the parameters of SVDD. Through this method, we got high classification to recognize the fault condition of bearings. Compared neural network (ANN) with SVDD, the experiment result represents that in the environment which lacks of enough fault samples, SVDD has better classification than ANN.
机译：通过在线故障检测，通常可以获得比故障样本更多的健康状况样本。为了解决机械智能监控诊断中故障样本不足的问题，提出了一种一类分类支持向量数据描述方法。它仅由健康数据（也称为目标数据）训练，从不看到“不健康”，并且可以有效地区分正常和异常情况。在本文中，我们描述了SVDD的基本算法，并使用轴承的实验振动数据作为SVDD分类器的输入。为了选择最有效的分类参数，遗传算法（GA）用于优化可用的输入参数和SVDD的参数。通过这种方法，我们对轴承的故障状况进行了较高的分类。将神经网络（ANN）与SVDD进行比较，实验结果表明，在缺乏足够的故障样本的环境中，SVDD的分类要优于ANN。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号