系统仿真学报 ›› 2021, Vol. 33 ›› Issue (11): 2561-2571.doi: 10.16182/j.issn1004731x.joss.21-FZ0703

• 仿真建模理论与方法 • 上一篇    下一篇

模糊信息粒化与改进RVM的滚动轴承寿命预测

胡小曼, 王艳*, 纪志成   

  1. 江南大学 物联网技术应用教育部工程研究中心,江苏 无锡 214122
  • 收稿日期:2021-04-17 修回日期:2021-07-17 出版日期:2021-11-18 发布日期:2021-11-17
  • 通讯作者: 王艳(1978-),女,博士,教授,研究方向为制造系统性能效优化。E-mail:wangyan@jiangnan.edu.cn
  • 作者简介:胡小曼(1997-),女,硕士生,研究方向为智能故障诊断与预测控制。E-mail:6191913002@stu.jiangnan.edu.cn
  • 基金资助:
    国家重点研发计划(2018YFB1701903); 国家自然科学基金(61973138)

Fuzzy Information Granulation and Improved RVM for Rolling Bearing Life Prediction

Hu Xiaoman, Wang Yan*, Ji Zhicheng   

  1. Engineering Research Center of Internet of Things Technology Applications Ministry of Education, Wuxi 214122, China
  • Received:2021-04-17 Revised:2021-07-17 Online:2021-11-18 Published:2021-11-17

摘要: 为解决轴承在寿命预测时精度不高且退化性能趋势及波动范围难以预测等问题,提出改进自适应完整集成经验模态分解去噪与模糊信息粒化改进相关向量机预测方法。针对轴承数据包含大量噪声问题,利用改进自适应完整集成经验模态分解结合小波包去噪,提取信号多种特征进行主成分分析,将其模糊信息粒化处理以提取有效信息,输入改进粒子群算法优化相关向量机模型对其退化指标波动范围以及剩余寿命进行预测。结果表明:该方法能够对其波动范围进行有效预测,且剩余寿命预测精度大幅提高。

关键词: 改进自适应完整集成经验模态分解, 轴承剩余寿命, 主成分分析, 模糊信息粒化, 粒子群算法, 相关向量机

Abstract: Aiming at the low accuracy in life prediction and unpredictable problems of degenerative performance trends and fluctuation ranges, etc. Of the bearing life prediction, an improved complete ensemble empirical mode decomposition with adaptive noise analysis and fuzzy information granulating method of improved relevance vector machine is proposed. Focusing on bearing data containing a lot of noise, through the improved complete ensemble empirical mode decomposition with adaptive noise analysis in combination with wavelet packet denoising, the principal component analysis is carride out by exitracing a variety of characeteristics of the signal, the effective information is extracted by granulating the fuzzy information, by entering the improved particle swarm algorithm to optimize the relevance vector machine model of the degradation index range and remaining life is predicted. The results show that the method can effectively predict the fluctuation range, and the residual life prediction accuracy is improved greatly.

Key words: improved complete ensemble empirical mode decomposition with adaptive noise, principal component analysis, bearing remaining life, fuzzy information granulation, particle swarm algorithm, relevance vector machine

中图分类号: