[1]吴 锐,马 洁,丁恺林.航空涡扇引擎剩余使用寿命预测算法研究[J].南京理工大学学报(自然科学版),2019,43(06):708-714.[doi:10.14177/j.cnki.32-1397n.2019.43.06.006]
 Wu Rui,Ma Jie,Ding Kailin.Remaining useful life prediction algorithm for aviationturbofan engine[J].Journal of Nanjing University of Science and Technology,2019,43(06):708-714.[doi:10.14177/j.cnki.32-1397n.2019.43.06.006]
点击复制

航空涡扇引擎剩余使用寿命预测算法研究()
分享到:

《南京理工大学学报》(自然科学版)[ISSN:1005-9830/CN:32-1397/N]

卷:
43卷
期数:
2019年06期
页码:
708-714
栏目:
出版日期:
2019-12-31

文章信息/Info

Title:
Remaining useful life prediction algorithm for aviationturbofan engine
文章编号:
1005-9830(2019)06-0708-07
作者:
吴 锐马 洁丁恺林
北京信息科技大学 自动化学院,北京 100192
Author(s):
Wu RuiMa JieDing Kailin
School of Automation,Beijing Information Science and Technology University,Beijing 100192,China
关键词:
航空 涡扇引擎 剩余使用寿命 预测 全特征输入 长短时记忆单元
Keywords:
aviation turbofan engine remaining useful life prediction full features input long-short term memory
分类号:
TP273
DOI:
10.14177/j.cnki.32-1397n.2019.43.06.006
摘要:
为改进故障预测技术,提出了全特征输入长短时记忆单元(AF-LSTM)算法。根据底层原始传感器数据自动学习更高级的抽象表示,并利用这些表示导出传感器数据,估计剩余使用寿命(RUL)。该文方法不依赖任何退化趋势假设,对噪声健壮,并能处理缺失值。在公开航空涡扇汽轮机引擎仿真数据集上的实验结果表明:该文方法的均方误差(MSE)指标明显优于多层感知器(MLP)模型,其时间分数(Score)指标优于带指数假设的线性回归(LR-EXP)模型。
Abstract:
To improve failure prediction technology,a all features input long-short term memory(AF-LSTM)algorithm is proposed. This algorithm learns higher-level abstract representations from the underlying raw sensor data automatically,and uses these representations to derive sensor data and evaluate remaining useful life(RUL). This algorithm is independent of degradation trend assumptions and robust to noise,and can handle missing values. The experimental results of the open aviation turbofan engine simulation data set show that the mean square error(MSE)index of AF-LSTM is better than that of the multi-layer perception(MLP),and the score index of AF-LSTM is better than that of the linear regression-exponential(LR-EXP).

参考文献/References:

[1] 郑建飞,胡昌华,司小胜,等. 考虑不确定测量和个体差异的非线性随机退化系统剩余寿命估计[J]. 自动化学报,2017,43(2):259-270.
Zheng Jianfei,Hu Changhua,Si Xiaosheng,et al. Remaining useful life estimation of nonlinear stochastic degradation systems considering uncertain measure-ments and individual differences[J]. Acta Automatica Sinica,2017,43(2):259-270.
[2]司小胜,胡昌华,周东华. 带测量误差的非线性退化过程建模与剩余寿命估计[J]. 自动化学报,2013,39(5):530-541.
Si Xiaosheng,Hu Changhua,Zhou Donghua. Nonlinear degradation process modeling with measurement error and remaining useful life estimation[J]. Acta Automatica Sinica,2013,39(5):530-541;
[3]喻勇,司小胜,胡昌华,等. 数据驱动的可靠性评估与寿命预测研究进展:基于协变量的方法[J]. 自动化学报,2018,44(2):216-227.
Yu Yong,Si Xiaosheng,Hu Changhua,et al. Data driven reliability assessment and life-time prognostics:A review on covariate models[J]. Acta Automatica Sinica,2018,44(2):216-227.
[4]Saxena A,Celaya J,Balaban E,et al. Metrics for evaluating performance of prognostic techniques[C]//International Conference on Prognostics and Health Management(PHM08). Denver,Colo,USA:IEEE,2008:1-17.
[5]周东华,史建涛,何潇. 动态系统间歇故障诊断技术综述[J]. 自动化学报,2014,40(2):161-171.
Zhou Donghua,Shi Jiantao,He Xiao. Review of intermittent fault diagnosis techniques for dynamic systems[J]. Acta Automatica Sinica,2014,40(2):161-171.
[6]Mosallam A,Medjaher K,Zerhouni N. Component based data-driven prognostics for complex systems:Methodology and applications[C]//PHM 2015 Conference. Beijing,China:IEEE,2015:1-7.
[7]Fatih C,Omer F,Saim B,et al. Comparison of sensors and methodologies for effective prognostics on railway turnout systems[J]. Proceedings of the Institution of Mechanical Engineers,Part F:Journal of Rail and Rapid Transit,2016,230(1):24-42.
[8]Cho K,Van Merrienboer B,Gulcehre C,et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[EB/OL]. https://arxiv. org/pdf/1406. 1078v3. pdf,2019-10-28.
[9]Malhotra P,Ramakrishnan A,Anand G,et al. LSTM-based encoder-decoder for multi-sensor anomaly detection[EB/OL]. https://www. researchgate. net/publication/304758073_LSTM-based_Encoder-Decoder_for_Multi-sensor_Anomaly_Detection,2019-10-28.
[10]Lam J,Sankararaman S,Stewart B. Enhanced trajectory based similarity prediction with uncertainty quantifica-tion[EB/OL]. http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.658.313&rep=rep1&type=pdf,2019-11-17.
[11]陈保家,汪新波,赵春华,等. 基于自适应局部迭代滤波和能量算子解调的滚动轴承故障特征提取[J]. 南京理工大学学报,2018,42(4):445-452.
Chen Baojia,Wang Xinbo,Zhao Chunhua,et al. Fault feature extraction of rolling bearing based on adaptive local iterative filtering and energy operator demodulation[J]. Journal of Nanjing University of Science and Technology,2018,42(4):445-452.
[12]Wang P,Hu C. A generic probabilistic framework for structural health prognostics and uncertainty management[J]. Mechanical Systems and Signal Processing,2012,28(1):622-637.
[13]冯永辉,马洁. 基于聚类分析的涡扇发动机的潜在故障检测[J]. 北京信息科技大学学报(自然科学版),2016,31(2):88-91.
Feng Yonghui,Ma Jie. Potential fault detection of turbofan engine based on cluster analysis[J]. Journal of Beijing Information Science and Technology University(Natural Science Edition),2016,31(2):88-91.
[14]杨青,孙佰聪,朱美臣,等. 基于小波包熵和聚类分析的滚动轴承故障诊断方法[J]. 南京理工大学学报,2013,37(4):517-523.
Yang Qing,Sun Baicong,Zhu Meichen,et al. Rolling bearing fault diagnosis method based on wavelet packet entropy and clustering analysis[J]. Journal of Nanjing University of Science and Technology,2013,37(4):517-523.

备注/Memo

备注/Memo:
收稿日期:2018-03-29 修回日期:2019-10-25
基金项目:国家自然科学基金(61973041)
作者简介:吴锐(1994-),男,硕士,主要研究方向:故障预测与健康管理、智能算法,E-mail:ivory2020@163.com。
引文格式:吴锐,马洁,丁恺林. 航空涡扇引擎剩余使用寿命预测算法研究[J]. 南京理工大学学报,2019,43(6):708-714.
投稿网址:http://zrxuebao.njust.edu.cn
更新日期/Last Update: 2019-12-31