计算机工程与应用 ›› 2006, Vol. 42 ›› Issue (19): 1-3.

• 博士论坛 •    下一篇

基于一类支持向量机的传感器故障诊断

钟清流,蔡自兴   

  1. 湖南大学计算机与通信学院
  • 收稿日期:2006-04-21 修回日期:1900-01-01 出版日期:2006-07-01 发布日期:2006-07-01
  • 通讯作者: 钟清流 zqlllj

Sensor Fault-Diagnoses Based-on One-Class SVM

,ZiXing Cai   

  1. 湖南大学计算机与通信学院
  • Received:2006-04-21 Revised:1900-01-01 Online:2006-07-01 Published:2006-07-01

摘要: 摘要: 提出一种基于一类支持向量机的传感器故障诊断方法,它利用相空间重构技术将传感器本身获取的相关时序数据转化成矢量,再用一类支持向量机来训练正常行为模型,进而通过发现数据异常来进行故障诊断.通过连续输入测量数据,它还可以实现在线诊断.仿真实验表明:该方法在诊断传感器故障方面有良好的性能.

关键词: 一类支持向量机, 传感器, 故障诊断

Abstract: Abstract: A method of fault-diagnoses for sensor based-on one-class SVM has been put forward, which transforms the time-series data from sensor into vector by means of the technology about reproduction in phase-space ,and trains normal-action model with one-class SVM and implements fault-diagnoses by finding abnormity data. The online-diagnoses can be implemented by continuously importing measuring data.The simulation-experiments have shown, it has nicer performance in sensor fault-diagnoses .

Key words: One-class SVM , sensor, fault-diagnoses