Remaining Useful Life Prediction of Flight Control System Based on Improved CNN-LSTM

doi:10.3778/j.issn.1002-8331.2111-0448

Abstract

Abstract: Recently, data-driven remaining useful life（RUL） prediction techniques play central role in health management of complex systems, while lacking of the dataset restricts the wide usability of the RUL across different systems. To remedy the addressed issue, this paper takes the flight control system as an example, and a simulation model and data hybrid-driven RUL prediction method is proposed. The simulation model can provide sufficient fault data, while the improved CNN-LSTM network enables the highly qualified fault information exploration. Initially, a system simulation model with its failure modes is established, and random failure time sequences generated by Monte Carlo method are supposed to be injected into the model iteratively. After the life labels of the sequences are distinguished according to the simulation response and the failure threshold, the failure dataset with multiple random failure sequences is well prepared. Then, this paper uses long short-term memory network（LSTM） to extract the fault information of the state sequence from time dimension, and combines 1-dimensional convolution neural network（1D-CNN） to get the correlation features among state parameters, thereby the temporal-spatial RUL prediction network is formulated subsequently. This paper proposes sufficient experimental results to demonstrate that the proposed method is helpful in achieving dynamic and accurate RUL prediction generally across different systems.

Key words: remaining useful life prediction, model simulation, long short-term memory network, 1-dimensional convolution neural network

摘要： 数据驱动的剩余寿命（remaining useful life，RUL）预测是复杂系统健康管理的重点研究内容，然而数据集的缺乏制约了不同系统上RUL预测的研究。针对这一问题，以飞控系统为例，提出一种仿真模型和数据混合驱动的RUL预测方法。该方法通过模型仿真提供充足的故障数据，并结合改进CNN-LSTM网络实现高质量的故障信息提取。首先对系统及其故障模式建立仿真模型，利用蒙特卡罗方法生成随机故障时间序列并依次注入故障，根据仿真响应和失效阈值确定序列的寿命标签，即可生成包含多组随机序列的系统失效数据集；其次利用长短时记忆网络（long short-term memory，LSTM）提取系统状态参数时间序列的故障信息，结合一维卷积神经网络（1D-CNN）提取不同状态参数之间的关联特征，从而形成时序-空间相结合的剩余寿命预测网络。充分的实验结果证明了所提方法对不同系统均能帮助达到动态和准确的剩余寿命预测。

关键词: 剩余寿命预测, 建模仿真, 长短时记忆网络, 一维卷积神经网络

LI Mengdie, ZHAO Guang, LUO Lingkun, HU Shiqiang. Remaining Useful Life Prediction of Flight Control System Based on Improved CNN-LSTM[J]. Computer Engineering and Applications, 2022, 58(16): 274-283.

李梦蝶, 赵光, 罗灵鲲, 胡士强. 基于改进CNN-LSTM的飞控系统剩余寿命预测[J]. 计算机工程与应用, 2022, 58(16): 274-283.

References

[1] 曾声奎，PECHT M G，吴际.故障预测与健康管理（PHM）技术的现状与发展[J].航空学报，2005，26（5）：626-632.
ZENG S K，PECHT M G，WU J.Status and development of failure prediction and health management（PHM） technology[J].Acta Aeronautica et Astronautica Sinica，2005，26（5）：626-632.
[2] 刘鹏鹏，左洪福，孙见忠.PHM体系中的航空器维修决策理论研究[J].航空制造技术，2012（20）：46-49.
LIU P P，ZUO H F，SUN J Z.Study on aircraft maintenance decision theory in PHM system[J].Aeronautical Manufacturing Technology，2012（20）：46-49.
[3] 王少萍.大型飞机机载系统预测与健康管理关键技术[J].航空学报，2014，35（6）：1459-1472.
WANG S P.Prognostics and health management key technology of aircraft airborne system[J].Acta Aeronautica et Astronautica Sinica，2014，35（6）：1459-1472.
[4] PECHT M G.Prognostics and health management of electronics[M].New York：John Wiley & Sons，2008：100-110.
[5] YU W K，HARRIS T A.A new stress-based fatigue life model for ball bearings[J].Tribology Transactions，2001，44（1）：11-18.
[6] 高云.仿真数据驱动的生成式对抗网络及机械传动系统故障诊断[D].温州：温州大学，2019.
GAO Y.Research on simulation-driven generative adversarial networks and mechanical transmission system fault diagnosis[D].Wenzhou：Wenzhou University，2019.
[7] 祝钧桃，姚光乐，张葛祥，等.深度神经网络的小样本学习综述[J].计算机工程与应用，2021，57（7）：22-33.
ZHU J T，YAO G L，ZHANG G X，et al.Survey of few shot learning of deep neural network[J].Computer Engineering and Applications，2021，57（7）：22-33.
[8] LIAO L，KOTTIG F.A hybrid framework combining data-driven and model-based methods for system remaining useful life prediction[J].Applied Soft Computing，2016，44：191-199.
[9] XIE Z，DU S，LV J，et al.A hybrid prognostics deep learning model for remaining useful life prediction[J].Electronics，2021，10（1）：39.
[10] LUO J，PATTIPATI K R，QIAO L，et al.Model-based prognostic techniques applied to a suspension system[J].IEEE Transactions on Systems，Man，and Cybernetics：Part A Systems and Humans，2008，38（5）：1156-1168.
[11] SAXENA A，GOEBEL K，SIMON D，et al.Damage propagation modeling for aircraft engine run-to-failure simulation[C]//2008 International Conference on Prognostics and Health Management，2008：1-9.
[12] 裴洪，胡昌华，司小胜，等.基于机器学习的设备剩余寿命预测方法综述[J].机械工程学报，2019，55（8）：1-13.
PEI H，HU C H，SI X S，et al.Review of machine learning based remaining useful life prediction methods for equipment[J].Journal of Mechanical Engineering，2019，55（8）：1-13.
[13] 赵申坤，姜潮，龙湘云.一种基于数据驱动和贝叶斯理论的机械系统剩余寿命预测方法[J].机械工程学报，2018，54（12）：115-124.
ZHAO S K，JIANG C，LONG X Y.Remaining useful life estimation of mechanical systems based on the data-driven method and Bayesian theory[J].Journal of Mechanical Engineering，2018，54（12）：115-124.
[14] 王玺，胡昌华，任子强，等.基于非线性Wiener过程的航空发动机性能衰减建模与剩余寿命预测[J].航空学报，2020，41（2）：195-205.
WANG X，HU C H，REN Z Q，et al.Performance degradation modeling and remaining useful life prediction for aero-engine based on nonlinear Wiener process[J].Acta Aeronautica et Astronautica Sinica，2020，41（2）：195-205.
[15] LIU Z，CHENG Y，WANG P，et al.A method for remaining useful life prediction of crystal oscillators using the Bayesian approach and extreme learning machine under uncertainty[J].Neurocomputing，2018，305：27-38.
[16] CHEN Z，LI Y，XIA T，et al.Hidden Markov model with auto-correlated observations for remaining useful life prediction and optimal maintenance policy[J].Reliability Engineering & System Safety，2019，184：123-136.
[17] 胡昌华，张浩，喻勇，等.基于深度学习的复杂退化系统剩余寿命预测研究现状与挑战[J].电光与控制，2021，28（2）：1-6.
HU C H，ZHANG H，YU Y，et al.Deep learning based RUL prediction of complex degradation systems：state of the art and challenges[J].Electronics Optics & Control，2021，28（2）：1-6.
[18] BABU G S，ZHAO P，LI X L.Deep convolutional neural network based regression approach for estimation of remaining useful life[C]//2016 International Conference on Database Systems for Advanced Applications.Cham：Springer，2016：214-228.
[19] HEIMES F O.Recurrent neural networks for remaining useful life estimation[C]//2008 International Conference on Prognostics and Health Management，2008：1-6.
[20] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[21] ZHENG S，RISTOVSKI K，FARAHAT A，et al.Long short-term memory network for remaining useful life estimation[C]//2017 IEEE International Conference on Prognostics and Health Management，2017：88-95.
[22] WU Y，YUAN M，DONG S，et al.Remaining useful life estimation of engineered systems using vanilla LSTM neural networks[J].Neurocomputing，2018，275：167-179.
[23] LU Z，ZHUANG L，DONG L，et al.Model-based safety analysis for the fly-by-wire system by using Monte Carlo simulation[J].Processes，2020，8（1）：90.
[24] DONG L，LU Z，LI M D，et al.Model-based system reliability analysis by using Monte Carlo methods[C]//2019 Prognostics and System Health Management Conference，Qingdao，2019：1-6.
[25] GU J，WANG Z，KUEN J，et al.Recent advances in convolutional neural networks[J].Pattern Recognition，2018，77（C）：354-377.
[26] LI J，LI X，HE D.A directed acyclic graph network combined with CNN and LSTM for remaining useful life prediction[J].IEEE Access，2019，7：75464-75475.
[27] MCRUER D T，MYERS T T，THOMPSON P M.Literal singular-value-based flight control system design techniques[J].Journal of Guidance，Control，and Dynamics，1989，12（6）：913-919.
[28] 田瑶瑶.基于机器学习的机电系统关键部件PHM技术研究[D].南京：南京航空航天大学，2018.
TIAN Y Y.Research on PHM technology of key components of electromechanical system based on machine learning[D].Nanjing：Nanjing University of Aeronautics and Astronautics，2018.
[29] DOM-GA A D，KASSA J G，SCHINDALL J E，et al.On the use of behavioral models for the integrated performance and reliability evaluation of fault-tolerant avionics systems[C]//2006 IEEE/AIAA 25th Digital Avionics Systems Conference，2006：1-14.
[30] WANG M，LI Y，ZHANG Y，et al.Spatio-temporal graph convolutional neural network for remaining useful life estimation of aircraft engines[J].Aerospace Systems，2021，4（1）：29-36.