• CSCD核心库收录期刊
  • 中文核心期刊
  • 中国科技核心期刊

电力建设 ›› 2016, Vol. 37 ›› Issue (1): 92-96.doi: 10.3969/j.issn.1000-7229.2016.01.014

• 发电技术 • 上一篇    下一篇

基于EEMD排列组合熵的SVM转子振动故障诊断研究

韩中合,焦宏超,朱霄珣,王智   

  1. 华北电力大学能源动力与机械工程学院,河北省保定市 071003
  • 出版日期:2016-01-01
  • 作者简介:韩中合(1964),男,博士生导师,教授,主要研究方向为热力设备状态检测与故障诊断、两相流计算与测量 ; 焦宏超(1990),男,通信作者,硕士研究生,主要研究方向为热力设备状态检测与故障诊断 ; 朱霄珣(1985),男,博士,讲师,主要研究方向为热力设备状态检测与故障诊断; 王智(1978),男,博士,副教授,主要研究方向为湿蒸汽两相流计算。
  • 基金资助:

    国家自然科学基金项目(51306059)

SVM Rotor Vibration Fault Diagnosis Based on EEMD Permutation Entropy

HAN Zhonghe,JIAO Hongchao,ZHU Xiaoxun,WANG Zhi   

  1. School of Energy Power and Mechanical Engineering, North China Electric Power University, Baoding 071003, Hebei Province, China
  • Online:2016-01-01
  • Supported by:

    Project supported by National Natural Science Foundation of China (51306059)

摘要:

对汽轮机转子故障状态进行准确判别一直是工程领域研究的重点。在使用支持向量机作为模式识别方法进行故障诊断的过程中,提取能明显区别不同故障的信号特征参数,构建高质量的样本可以较大提高支持向量机(support vector machine,SVM)模型的分类正确率。针对此问题,提出一种总体平均经验模态分解(ensemble empirical mode decomposition,  EEMD)、排列组合熵和SVM相结合的汽轮机转子振动多故障诊断方法。方法首先引入有向无环图建立了多故障诊断模型,利用EEMD将振动信号分解成单一无混叠的内禀模态函数(intrinsic mode function,IMF)分量,然后计算对振动信号变化非常敏感的IMF排列组合熵作为特征向量,并应用到有向无环图SVM进行多故障状态识别。实验结果表明,该方法实现了汽轮机转子的振动多故障诊断,同时与基于EEMD能量法提取的特征向量进行对比,通过实验证明,该方法具有更加准确的识别率。

关键词: 总体平均经验模态分解(EEMD) , 排列组合熵, 支持向量机(SVM), 转子, 故障诊断

Abstract:

The accurate identification of the fault conditions of steam turbine rotor has been the research focus in the field of engineering. In the process of fault diagnosis by using support vector machine (SVM), extracting the signal characteristic parameters, which can clearly distinguish different fault signals to construct high-quality samples, plays a significant role in improving the classification accuracy of SVM model. To solve these problems, we propose a multiple fault diagnosis method for steam turbine rotor based on ensemble empirical mode decomposition (EEMD), permutation entropy and SVM. Firstly, this method applies directed acyclic graph to establish multiple faults diagnosis model, and uses EEMD to decompose the vibration signals into single and unmixed IMF components. Then, the permutation entropy of IMF component, which is very sensitive to the changes in vibration signal, is calculated as eigenvectors, and applied in directed acyclic graph SVM for multiple fault state recognition. The experimental results show that this method can realize the multiple faults diagnosis of turbine rotor vibration. Meanwhile, compared with the extracted eigenvectors based on EEMD energy method, the experiment proves that this method has more accurate recognition rate.

Key words: EEMD (ensemble empirical mode decomposition), permutation entropy, SVM (support vector machine), rotor, fault diagnosis

中图分类号: