首页 | 本学科首页   官方微博 | 高级检索  
     

航空发动机的健康指标构建与剩余寿命预测
引用本文:彭开香,皮彦婷,焦瑞华,唐鹏. 航空发动机的健康指标构建与剩余寿命预测[J]. 控制理论与应用, 2020, 37(4): 713-720
作者姓名:彭开香  皮彦婷  焦瑞华  唐鹏
作者单位:北京科技大学自动化学院工业过程知识自动化教育部重点实验室,北京100083;北京科技大学人工智能研究院,北京100083
摘    要:预测与健康管理技术能够有效的评估系统健康状态、预测系统剩余使用寿命,是提高复杂系统安全性、经济性的重要保障.为全面评估系统健康状态,本文提出了一种基于深度置信网络(DBN)的无监督健康指标构建方法,并结合隐马尔可夫模型(HMM)进行系统剩余寿命预测.首先,通过无监督训练深度置信网络实现历史数据的特征提取,进而构建健康指标;其次,利用健康指标集训练隐马尔可夫模型,实现设备健康状态的自动识别;最后,通过DBN-HMM混合模型来计算系统剩余寿命.采用商用模块化航空推进系统仿真软件(C-MAPSS)给出的航空发动机数据集,验证了上述方法的有效性.

关 键 词:深度置信网络  隐马尔可夫模型  健康指标  健康状态识别  剩余寿命预测
收稿时间:2019-01-16
修稿时间:2019-08-13

Health indicator construction and remaining useful life prediction for aircraft engine
PENG Kai-xiang,PI Yan-ting,JIAO Rui-hua and TANG Peng. Health indicator construction and remaining useful life prediction for aircraft engine[J]. Control Theory & Applications, 2020, 37(4): 713-720
Authors:PENG Kai-xiang  PI Yan-ting  JIAO Rui-hua  TANG Peng
Affiliation:University of Science and Technology Beijing,University of Science and Technology Beijing,University of Science and Technology Beijing,University of Science and Technology Beijing
Abstract:Prognostics and health management can effectively evaluate the health status and predict the remaining useful life of the system. It is an important guarantee to improve the safety and economy of complex systems. In order to fully assess the health status of the system, an unsupervised health indicator construction method based on the Deep Belief Network(DBN) is proposed in this paper, and remaining useful life of the system is predicted with the Hidden Markov Model(HMM). Firstly, the feature extraction of historical data is realized by unsupervised training Deep Belief Network, and then the health indicator is constructed. Secondly, the health indicator set is used to train the Hidden Markov Model, then the automatic recognition of equipment health state can be realized. Finally, the remaining useful life of the system is calculated by the DBN-HMM hybrid model. To validate the effectiveness of the proposed approach, a case study is performed on the commercial modular aero-propulsion system simulation(C-MAPSS) aircraft engine datasets.
Keywords:deep belief network   hidden Markov model   health indicator   health status recognition   remaining useful life prediction
本文献已被 CNKI 维普 万方数据 等数据库收录!
点击此处可从《控制理论与应用》浏览原始摘要信息
点击此处可从《控制理论与应用》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号