湖南电力 ›› 2022, Vol. 42 ›› Issue (5): 114-118.doi: 10.3969/j.issn.1008-0198.2022.05.020

• 故障与分析 • 上一篇    下一篇

基于多重分形谱及支持向量机的水电机组轴系故障识别

孟繁聪1, 吉俊杰1, 薛小兵1, 姚航宇1, 胡飞2, 潘伟峰2, 白亮3   

  1. 1.华东宜兴抽水蓄能有限公司,江苏 宜兴 214205;
    2.南瑞集团有限公司(国网电力科学研究院有限公司),江苏 南京 211000;
    3.西安理工大学,陕西 西安 710048
  • 收稿日期:2022-08-05 出版日期:2022-10-25 发布日期:2022-11-16
  • 基金资助:
    国网新源控股有限公司科技项目(SGXYKY-2020-031)

Identification of Hydropower Unit Shafting Fault Based on Multifractal Spectrum and Support Vector Machine

MENG Fancong1 , JI Junjie1, XUE Xiaobing1, YAO Hangyu1, HU Fei2, PAN Weifeng2, BAI Liang3   

  1. 1. East China Yixing Pumped Storage Power Co. Ltd.,Yixing 214205,China;
    2. NARI Group Corporation(State Grid Electric Power Research Institute), Nanjing 211000, China;
    3. Xi′an University of Technology, Xi′an 710048,China
  • Received:2022-08-05 Online:2022-10-25 Published:2022-11-16

摘要: 针对水电机组轴系振动故障诊断,提出多重分形谱和支持向量机相结合的故障分类识别方法。该方法首先利用多重分形谱算法提取振动信号的特征数据,然后将该特征数据作为支持向量机的输入向量来实现故障的分类识别。实验数据表明,该方法能比较准确地识别轴系常见故障,为水电机组轴系故障智能识别提供了一种新的思路。

关键词: 水电机组, 多重分形, 支持向量机, 故障识别

Abstract: A method based on multifractal spectrum and support vector machine is proposed for fault identification of shafting system of hydropower units. Firstly, the multifractal spectrum algorithm is used to extract the feature data of vibration signals, and then the feature data is used as the input vector of support vector machine to realize the fault classification. The experimental data show that the method can accurately identify the common shafting faults, and provide a new method for the intelligent identification of shafting faults of hydropower units.

Key words: hydropower unit, multifractal, support vector machine, fault identification

中图分类号: