航空发动机的健康指标构建与剩余寿命预测-Health indicator...

来自 : jcta.alljournals.ac.cn/cta_cn/ 发布时间：2021-03-25

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.
2019年1月16日摘要点击620全文点击340投稿时间:2019-01-16修订日期:2019-08-13 查看全文查看/发表评论下载PDF阅读器 DOI编号10.7641/CTA.2019.90039 ...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.;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.航空发动机的健康指标构建与剩余寿命预测