北京航空航天大学学报

• •    

变工况条件下基于相似性的剩余寿命预测方法

李琪1,高占宝1,李善营1,李宝安2   

  1. 1. 北京航空航天大学 自动化科学与电气工程学院
    2. 北京航空航天大学无人驾驶飞行器设计研究所
  • 收稿日期:2015-06-17 修回日期:2015-09-18 发布日期:2015-10-14
  • 通讯作者: 高占宝
  • 基金资助:
    中央高校基本科研业务费专项资金资助项目

Similarity–Based Remaining Useful Life Estimation Method under Varying Operational Conditions

  • Received:2015-06-17 Revised:2015-09-18 Published:2015-10-14

摘要: 剩余寿命预测是预测与健康管理中的核心环节。本文提出一种变工况条件下基于相似性的剩余寿命预测方法。结合相似性预测方法无需进行复杂的退化过程建模而能提供合理预测的优势,引入工况即设备工作时所处的环境或操作载荷等因素的影响来提升设备剩余寿命预测准确性。对参考样本建立多工况的设备退化模型提升模型精度,在服役样本相似性度量预测中进行工况的匹配以实现在变工况下的剩余寿命预测。方法能够更准确地描述实际工程中设备的退化过程和个体差异。依据相同准确度标准完成多组基本相似性方法和本文方法的对比实验结果表明,本文方法能够有效提高预测准确度。

关键词: 剩余使用寿命, 预测, 工况, 相似性, 健康指标

Abstract: The paper presents a similarity-based remaining useful life (RUL) estimation method under varying operational conditions. Similarity-based remaining useful life prediction method doesn’t need to build a model for entire complex system but can provide reasonable results, which is promising in engineering practice. However, the operational conditions such as different working loads and environmental conditions are not considered for degradation modeling. Therefore, this method combines basic similarity-based method and the effect from operational conditions to achieve better prediction accuracy. Degradation models with different operational conditions are built by training units, and the RUL estimation is achieved by matching corresponding model using the real-time operational conditions of the running unit. The proposed degradation models describe the degradation process more precisely by taking the differences of operational conditions into account. According to the same accuracy standard, multi-groups numerical experiments are finished by basic similarity-based method and the proposed method. The result shows the proposed method has a higher accuracy in remaining useful life prediction.

Key words: Remaining useful life, Prognostics, Operational condition, Similarity, Health Indicator


版权所有 © 《北京航空航天大学学报》编辑部
通讯地址:北京市海淀区学院路37号 北京航空航天大学学报编辑部 邮编:100191 E-mail:jbuaa@buaa.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发