中国机械工程 ›› 2026, Vol. 37 ›› Issue (1): 209-222.DOI: 10.3969/j.issn.1004-132X.2026.01.022

• 智能制造 • 上一篇    

高端旋转机械剩余使用寿命预测及其不确定性量化评估方法

崔硕1,2(), 刘秀丽1,2(), 李相杰3, 吴国新1,2   

  1. 1.北京信息科技大学现代测控技术教育部重点实验室, 北京, 100192
    2.北京信息科技大学 机电工程学院, 北京, 100192
    3.华锐风电科技(集团)股份有限公司安全生产部, 北京, 100000
  • 收稿日期:2024-10-22 出版日期:2026-01-25 发布日期:2026-02-05
  • 通讯作者: 刘秀丽
  • 作者简介:崔硕,男,1999年生,硕士研究生。研究方向为机电装备寿命预测与健康管理。发表论文2篇。E-mail:1317754704@qq.com
    刘秀丽*(通信作者),女,1986年生,博士、副研究员、硕士研究生导师。研究方向为可解释深度学习、装备故障诊断与寿命预测。发表论文30余篇。E-mail:liuxiulilw@163.com
  • 基金资助:
    国家自然科学基金(62303065);北京信息科技大学勤信人才项目(QXTCPC202120)

Prediction of RUL and Uncertainty Quantification Evaluation Methods for High-end Rotating Machinery

CUI Shuo1,2(), LIU Xiuli1,2(), LI Xiangjie3, WU Guoxin1,2   

  1. 1.Key Laboratory of Modern Measurement & Control Technology of Ministry of Education,Beijing Information Science and Technology University,Beijing,100192
    2.Mechanical Electrical Engineering School,Beijing Information Science and Technology University,Beijing,100192
    3.Safety Production Department,Sinovel Wind Group Co. ,Ltd. ,Beijing,100000
  • Received:2024-10-22 Online:2026-01-25 Published:2026-02-05
  • Contact: LIU Xiuli

摘要:

针对高端旋转机械剩余使用寿命预测中的准确性和不确定性量化问题,提出了基于变分深度高斯过程(VDGP)的预测方法。通过构建深度高斯过程更新模型实现不确定性的递推量化,并采用诱导点和变分推断提高大数据的处理能力。C-MAPSS和风机行星齿轮数据集的实验表明,VDGP比高斯过程方法具有更高的预测准确度和更窄的置信区间,在C-MAPSS的 FD002数据集上,均方根误差、评分函数分别比现有最佳的对比方法减小0.21%和45.3%。

关键词: 剩余使用寿命预测, 变分深度高斯过程, 不确定性量化, 旋转机械, 核函数

Abstract:

To address the challenges of accuracy and uncertainty quantification in RUL prediction of high-end rotating machinery, a prediction method was proposed based on VDGP. The method achieved recursive uncertainty quantification by constructing a deep Gaussian process update model, and enhanced large-scale data processing capability through the use of inducing points and variational inference. Experiments on the C-MAPSS and wind turbine planetary gearbox datasets demonstrate that VDGP achieves higher prediction accuracy and narrower confidence intervals compared to the standard Gaussian process methods. On the C-MAPSS FD002 dataset, the root mean square error and scoring function are reduced by 0.21% and 45.3% respectively, relative to the best baseline method.

Key words: remaining useful life(RUL) prediction, variational deep Gaussian process(VDGP), uncertainty quantification, rotating machinery, kernel function

中图分类号: