浏览全部资源
扫码关注微信
1.航天工程大学, 北京 101416
2.清华大学, 北京 100089
3.63931部队, 北京 100094
[ "叶瑞达(1995-),男,湖北孝感人,硕士研究生,2017年于湖北理工学院获得学士学位,主要从事机器故障检测、深度学习等方面的研究。E-mail:yerd0103@aliyun.com" ]
收稿日期:2020-12-28,
修回日期:2021-02-25,
纸质出版日期:2021-06-15
移动端阅览
叶瑞达,王卫杰,何亮等.基于残差自注意力机制的航空发动机RUL预测[J].光学精密工程,2021,29(06):1482-1490.
YE Rui-da,WANG Wei-jie,HE Liang,et al.RUL prediction of aero-engine based on residual self-attention mechanism[J].Optics and Precision Engineering,2021,29(06):1482-1490.
叶瑞达,王卫杰,何亮等.基于残差自注意力机制的航空发动机RUL预测[J].光学精密工程,2021,29(06):1482-1490. DOI: 10.37188/OPE.20212906.1482.
YE Rui-da,WANG Wei-jie,HE Liang,et al.RUL prediction of aero-engine based on residual self-attention mechanism[J].Optics and Precision Engineering,2021,29(06):1482-1490. DOI: 10.37188/OPE.20212906.1482.
针对传统神经网络在多维数据高分辨率特征识别和高精度信号提取方面的缺陷,开展基于残差自注意力机制的剩余使用寿命(RUL)预测算法研究。比较分析卷积神经网络(CNN)和长短期记忆神经网络(LSTM)的结构特性,揭示二者在长序列信息特征关联能力和局部特征提取能力上的局限性。研究自注意力机制,引入双层残差网络抑制误差函数反向传播中扩散性,进而构建了一种卷积记忆残差自注意力机制的深度学习方法。基于上述方法对典型航空涡扇发动机退化实验数据集进行仿真分析,结果表明:所述方法能够有效建立监测数据与发动机健康状态之间的关系,关键评价指标——剩余使用寿命预测的均方误差为225,相比传统自注意力机制均方误差降低了17.9%,验证了所述方法的可行性和有效性。
In this study, the remaining useful life (RUL) prediction algorithm based on the residual self-attention mechanism is employed to address the shortcomings of traditional neural networks in the context of multi-dimensional data high-resolution feature recognition and high-precision signal extraction. The structural characteristics of a convolutional neural network and long short-term memory (LSTM) neural network are compared and analyzed, whereby their limitations are revealed in terms of their long-sequence information feature correlation and local feature extraction abilities. Furthermore, as part of our research on the self-attention mechanism, we introduce a double-layer residual network to suppress the spread of the error function back propagation, following which we construct a deep learning method for the convolutional memory residual self-attention mechanism. Simulation analyses of the typical aviation aero-engine degradation experiment data set show that the proposed method can effectively establish the relationship between the monitoring data and engine health status. The obtained value of the key evaluation index, namely, the mean square error (MSE) of the RUL prediction, is 225. When compared with that of the traditional self-attention mechanism, the MSE in this case is reduced by 17.9%, which verifies the feasibility and effectiveness of the proposed method.
彭宇 , 刘大同 . 数据驱动故障预测和健康管理综述 [J]. 仪器仪表学报 , 2014 , 35 ( 3 ): 481 - 495 .
PENG Y , LIU D T . Data-driven prognostics and health management: A review of recent advances [J]. Chinese Journal of Scientific Instrument , 2014 , 35 ( 3 ): 481 - 495 . (in Chinese)
陈煜 . 基于非线性模型的涡喷发动机气路故障诊断研究 [D]. 南京 : 南京航空航天大学 , 2014 .
CHEN Y . Gas Path Fault Diagnosis for Turbojet Engine Based on Nonlinear Model [D]. Nanjing : Nanjing University of Astronautics , 2014 . (in Chinese)
葛怡 . 航空发动机几种典型故障建模仿真与预测 [D]. 西安 : 西安理工大学 , 2020 .
GE E . Modeling , Simulation and Prediction of Several Typical Faults of Aeroengine [D]. Xi'an : Xi'an University of Technology , 2020 . (in Chinese)
赵琳 , 王艺鹏 , 郝勇 . 在轨飞轮故障诊断混合框架设计 [J]. 光学 精密工程 , 2018 , 26 ( 7 ): 1728 - 1740 .
ZHAO L , WANG Y P , HAO Y . Hybrid frame design for on orbit flywheel fault diagnosis [J]. Opt. Precision Eng. , 2018 , 26 ( 7 ): 1728 - 1740 . (in Chinese)
徐彦伟 , 刘明明 , 刘洋 , 等 . 基于信息融合的机器人薄壁轴承故障智能诊断 [J]. 光学 精密工程 , 2019 , 27 ( 7 ): 1577 - 1592 .
XU Y W , LIU M M , LIU Y , et al . Intelligent fault diagnosis of robot thin wall bearing based on information fusion [J]. Opt. Precision Eng. , 2019 , 27 ( 7 ): 1577 - 1592 . (in Chinese)
吴海滨 , 陈寅生 , 张庭豪 , 等 . 改进多尺度幅值感知排列熵与随机森林结合的滚动轴承故障诊断 [J]. 光学 精密工程 , 2020 , 28 ( 3 ): 621 - 631 .
WU H B , CHEN Y S , ZHANG T H , et al . Rolling bearing fault diagnosis by improved multiscale amplitude-aware permutation entropy and random forest [J]. Opt. Precision Eng. , 2020 , 28 ( 3 ): 621 - 631 . (in Chinese)
马浩鹏 , 朱春媚 , 周文辉 , 等 . 基于深度学习的乳液泵缺陷检测算法 [J]. 液晶与显示 , 2019 , 34 ( 1 ): 81 - 89 .
MA H P , ZHU C M , ZHOU W H , et al . Defect detection algorithm of lotion pump based on deep learning [J]. Chinese Journal of Liquid Crystals and Displays , 2019 , 34 ( 1 ): 81 - 89 . (in Chinese)
LI X , DING Q , SUN J Q . Remaining useful life estimation in prognostics using deep convolution neural networks [J]. Reliability Engineering & System Safety , 2018 , 172(APR.): 1 - 11 .
SEN Z , YONG Z , SHANG W , et al . A recurrent neural network approach for remaining useful life prediction utilizing a novel trend features construction method [J]. Measurement , 2019 , 146 : 279 - 288 .
TAREk B , MOUSS H , KADRI O , et al . Aircraft engines remaining useful life prediction with an adaptive denoising online sequential extreme learning machine [J]. Engineering Applications of Artificial Intelligence , 2020 , 96 ( 103396 ): 1 - 10 .
彭开香 , 皮彦婷 , 焦瑞华 , 等 . 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 .
PENG K , PI Y , JIAO R , TANG P , et al . Health indicator construction and remaining useful life prediction for aircraft engine [J]. Control Theory and Applications , 2020 , 37 ( 4 ): 713 - 720 . (in Chinese)
VASWANI A , SHAZEER N , PARMAR N , et al . Attention is all you need [J]. arxiv , 2017 .
LIU S , YANG N , LI M , et al . A recursive recurrent neural network for statistical machine translation [C]. Meeting of the Association for Computational Linguistics , 2014 .
ATHIWARATKUN B , STOKES J W . Malware classification with LSTM and GRU language models and a character-level CNN [C]. ICMRSAsp IEEE International Conference on Acoustics . IEEE , 2017 .
HE K , ZHANG X , REN S , et al . Deep Residual Learning for Image Recognition [C]. 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE , 2016 .
SAXENA , ABHINAV , GOEBEL , et al . Damage propagation modeling for aircraft engine run-to-failure simulation [C]. Prognostics and Health Management , 2008 International Conference on; Denver , CO , USA . 2008 : 1 - 9 .
吴锐 , 马洁 , 丁恺林 . 航空涡扇引擎RUL预测算法研究 [J]. 南京理工大学学报(自然科学版) , 2019 , 43 ( 6 ): 708 - 714 .
WU R , MA J , DING K . Remaining useful life prediction algorithm for aviation turbofan engine [J]. Journal of Nanjing University of Science And Technology , 2019 , 43 ( 6 ): 708 - 714 . (in Chinese)
马忠 , 郭建胜 , 顾涛勇 , 等 . 基于改进卷积神经网络的航空发动机剩余寿命预测 [J]. 空军工程大学学报(自然科学版) , 2020 , 21 ( 6 ): 19 - 25 .
MA Z , GUO J S , GU T Y , et al . A Remaining useful life prediction for aero-engine based on improved convolution neural networks [J]. Journal of Air Force Engineering University (Natural Science Edition) , 2020 , 21 ( 6 ): 19 - 25 . (in Chinese)
0
浏览量
1512
下载量
1
CSCD
关联资源
相关文章
相关作者
相关机构