基于深度卷积生成对抗网络的缺失数据生成方法及其在剩余寿命预测中的应用

张晟斐; 李天梅; 胡昌华; 杜党波; 司小胜

doi:10.7527/S1000-6893.2021.25708

航空学报 >

2022 , Vol. 43 >Issue 8: 225708 - 225708

DOI: https://doi.org/10.7527/S1000-6893.2021.25708

固体力学与飞行器总体设计

基于深度卷积生成对抗网络的缺失数据生成方法及其在剩余寿命预测中的应用

张晟斐 ,
李天梅 ,
胡昌华 ,
杜党波 ,
司小胜

展开

火箭军工程大学导弹工程学院, 西安 710025

收稿日期: 2021-04-23

修回日期: 2021-06-29

网络出版日期: 2021-06-29

基金资助

国家自然科学基金(61833016,62073336,61922089)

收起

Missing data generation method and its application in remaining useful life prediction based on deep convolutional generative adversarial network

ZHANG Shengfei ,
LI Tianmei ,
HU Changhua ,
DU Dangbo ,
SI Xiaosheng

Expand

College of Missile Engineering, Rocket Force University of Engineering, Xi'an 710025, China

Received date: 2021-04-23

Revised date: 2021-06-29

Online published: 2021-06-29

Supported by

National Natural Science Foundation of China (61833016,62073336,61922089)

Fold

摘要

数据驱动的设备剩余寿命(RUL)预测方法旨在通过建模分析设备运行监测数据,以确定设备剩余可用时间,因此数据的质量直接关系到预测结果的精度。随着传感器技术的发展与物联网的普及,数据规模呈井喷式增长,但海量数据往往存在数据缺失问题,这类问题将会对建模的准确性与决策的可靠性产生关键性影响。针对数据缺失下的剩余寿命预测问题,论文提出了一种基于深度卷积生成对抗网络(DCGAN)的缺失数据生成方法。该方法利用生成对抗网络(GAN)强大的学习能力,采用深度卷积网络学习真实分布并对缺失数据进行填充处理,并结合Kolmogorov-Smirnov (K-S)非参数检验的思想以改善生成对抗网络训练不稳定、建模过于自由的缺点。在此基础上,利用双向长短时记忆网络(Bi-LSTM)建立了设备退化趋势预测模型,通过预测退化量超过失效阈值的时间实现了剩余寿命的预测。最后,基于锂电池退化数据对所提方法进行了应用验证,并且通过对比完整数据、生成数据以及缺失数据下剩余寿命预测结果进一步表现本文方法在解决数据缺失问题方面的优越性,同时可以提升剩余寿命预测对数据缺失的鲁棒性。

关键词： 大数据; 数据缺失; 深度卷积生成对抗网络(DCGAN); K-S非参数检验; 剩余寿命预测

本文引用格式

张晟斐 , 李天梅 , 胡昌华 , 杜党波 , 司小胜 . 基于深度卷积生成对抗网络的缺失数据生成方法及其在剩余寿命预测中的应用[J]. 航空学报, 2022 , 43(8) : 225708 -225708 . DOI: 10.7527/S1000-6893.2021.25708

Abstract

Data-driven Remaining Useful Life (RUL) prediction methods are designed to determine the remaining useful time of the equipment through analyzing and modeling the equipment operation monitoring data; hence, data quality is directly related to prediction accuracy. The development of sensor technology and popularization of the Internet of Things induce the exponential growth of the data scale; however, massive data often face the data missing problem, imposing critical impact on the accuracy of modeling and the reliability of decision-making. Aiming at the problem of RUL prediction with missing data, this paper proposes a generation method for missing data based on the Deep Convolutional Generative Adversarial Network (DCGAN). This method uses a deep convolutional network to learn the true distribution, fills in the missing data based on the powerful learning ability of the Generative Adversarial Network (GAN), and improves the network defects of unstable training and too free modeling in combination with the idea of the Kolmogorov-Smirnov (K-S) non-parametric test. A Bidirectional Long Short-Term Memory (Bi-LSTM) network is further adopted to establish a device degradation trend prediction model, and the RUL prediction is realized by prediction of the time for the degradation to exceed the failure threshold. The proposed method is validated based on the lithium battery degradation data. The RUL prediction results with the complete data, the generated data, as well as the missing data, respectively, are compared to further demonstrate the superiority of this method in solving the missing data problem. The robustness of the RUL prediction towards missing data can also be improved.

Key words： big data; data missing; Deep Convolutional Generative Adversarial Network (DCGAN); Kolmogorov-Smirnov non-parametric test; remaining useful life prediction

参考文献

[1] SHEPPARD J W, KAUFMAN M A, WILMER T J. IEEE standards for prognostics and health management[J]. IEEE Aerospace and Electronic Systems Magazine, 2009, 24(9): 34-41.
[2] JAVED K, GOURIVEAU R, ZERHOUNI N, et al. Enabling health monitoring approach based on vibration data for accurate prognostics[J]. IEEE Transactions on Industrial Electronics, 2015, 62(1): 647-656.
[3] 陈亚军, 刘辰辰, 王付胜. 预腐蚀和交替腐蚀作用下航空铝合金多轴疲劳行为及寿命预测[J]. 航空学报, 2019, 40(4): 222465. CHEN Y J, LIU C C, WANG F S. Multiaxial fatigue behavior and life prediction of aerospace aluminum alloy under pre-corrosion and alternate corrosion[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(4): 222465 (in Chinese).
[4] BROWN E R, MCCOLLOM N N, MOORE E E, et al. Prognostics and health management. A data-driven approach to supporting the F-35 lightning II[C]//2007 IEEE Aerospace Conference. Piscataway: IEEE Press, 2007: 1-12.
[5] VICHARE N M, PECHT M G. Prognostics and health management of electronics[J]. IEEE Transactions on Components and Packaging Technologies, 2006, 29(1): 222-229.
[6] LEI Y G, LI N P, GUO L, et al. Machinery health prognostics: A systematic review from data acquisition to RUL prediction[J]. Mechanical Systems and Signal Processing, 2018, 104: 799-834.
[7] 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): 223291. 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): 223291 (in Chinese).
[8] 任子强, 司小胜, 胡昌华, 等. 融合多传感器数据的发动机剩余寿命预测方法[J]. 航空学报, 2019, 40(12): 223312. REN Z Q, SI X S, HU C H, et al. Remaining useful life prediction method for engine combining multi-sensors data[J]. Acta Aeronautica et Astronautica Sinica, 2019, 40(12): 223312 (in Chinese).
[9] PENG W W, LI Y F, YANG Y J, et al. Bayesian degradation analysis with inverse Gaussian process models under time-varying degradation rates[J]. IEEE Transactions on Reliability, 2017, 66(1): 84-96.
[10] 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: 1-11.
[11] ZHU J, CHEN N, PENG W W. Estimation of bearing remaining useful life based on multiscale convolutional neural network[J]. IEEE Transactions on Industrial Electronics, 2019, 66(4): 3208-3216.
[12] CHEN J L, JING H J, CHANG Y H, et al. Gated recurrent unit based recurrent neural network for remaining useful life prediction of nonlinear deterioration process[J]. Reliability Engineering & System Safety, 2019, 185: 372-382.
[13] 孔祥芬, 蔡峻青, 张利寒, 等. 大数据在航空系统的研究现状与发展趋势[J]. 航空学报, 2018, 39(12): 022311. KONG X F, CAI J Q, ZHANG L H, et al. Research status and development trend of big data in aviation system[J]. Acta Aeronautica et Astronautica Sinica, 2018, 39(12): 022311 (in Chinese).
[14] TSIATIS A. Semiparametric theory and missing data[M]. Berlin:Springer Science & Business Media, 2007.
[15] KAISER J. Dealing with missing values in data[J]. Journal of Systems Integration, 2014: 42-51.
[16] WITTEN I, FRANK E. Data mining: Practical machine learning tools and techniques with Java implementations[M]. Francisco: Morgan Kaufmann Publishers Inc.,2000.
[17] LITTLE R J A. Regression with missing x’s: A review[J]. Journal of the American Statistical Association, 1992, 87(420): 1227-1237.
[18] AMIRI M, JENSEN R. Missing data imputation using fuzzy-rough methods[J]. Neurocomputing, 2016, 205: 152-164.
[19] SEAMAN S R, WHITE I R. Review of inverse probability weighting for dealing with missing data[J]. Statistical Methods in Medical Research, 2013, 22(3): 278-295.
[20] KIM J K. Parametric fractional imputation for missing data analysis[J]. Biometrika, 2011, 98(1): 119-132.
[21] BATISTA G E A P A, MONARD M C. An analysis of four missing data treatment methods for supervised learning[J]. Applied Artificial Intelligence, 2003, 17(5-6): 519-533.
[22] MAZUMDER R, HASTIE T, TIBSHIRANI R. Spectral regularization algorithms for learning large incomplete matrices[J]. Journal of Machine Learning Research: JMLR, 2010, 11: 2287-2322.
[23] FEDUS W, GOODFELLOW I, DAI A M. MaskGAN: Better text generation via filling in the_[EB/OL]. arXiv.preprint: 1801.077360,2018.
[24] GONDARA L, WANG K. MIDA: Multiple imputation using denoising autoencoders[C]//Advances in Knowledge Discovery and Data Mining, 2018.
[25] CHE Z P, PURUSHOTHAM S, CHO K, et al. Recurrent neural networks for multivariate time series with missing values[J]. Scientific Reports, 2018, 8: 6085.
[26] YOON J, JORDON J, VAN DER SCHAAR M. GAIN: Missing data imputation using generative adversarial nets[EB/OL]. arXiv.preprint: 1806.02920,2018.
[27] ZHENG S, FARAHAT A, GUPTA C. Generative adversarial networks for failure prediction[C]//Machine Learning and Knowledge Discovery in Databases, 2020.
[28] LUO Y H, CAI X R, ZHANG Y, et al. Multivariate time series imputation with generative adversarial networks[C]//NIPS'18: Proceedings of the 32nd International Conference on Neural Information Processing Systems, 2018: 1603-1614.
[29] GOODFELLOW I J, POUGET J, MIRZA M, et al.Generative adversarial networks[C]//International Conference on Neural Information Processing System, 2014.
[30] LEDIG C, THEIS L, HUSZÁR F, et al. Photo-realistic single image super-resolution using a generative adversarial network[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway: IEEE Press, 2017: 105-114.
[31] BAI Y C, ZHANG Y Q, DING M L, et al. SOD-MTGAN: Small object detection via multi-task generative adversarial network[C]//Computer Vision-ECCV 2018, 2018.
[32] YU L, ZHANG W, WANG J, et al. Seqgan: Sequence generative adversarial nets with policy gradient[C]//Proceedings of the AAAI Conference on Artificial Intelligence,2017.
[33] RADFORD A, METZ L, CHINTALA S. Unsupervised representation learning with deep convolutional generative adversarial networks[J]. arXiv preprint arXiv:1511.06434, 2015.
[34] HOLLANDER M. Practical nonparametric statistics[M]. 3rd ed. New York: Wiley, 1999.
[35] SCHUSTER M, PALIWAL K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing, 1997, 45(11): 2673-2681.
[36] ARJOVSKY M, BOTTOU L. Towards principled methods for training generative adversarial networks[J]. arXiv preprint arXiv:1701.04862, 2017.
[37] STEPANČI Č M, JURIČI D, BŠKOSKI P. Fault detection of fuel cell systems based on statistical assessment of impedance data[J]. Energy Conversion and Management, 2019, 195: 76-85.
[38] KINGMA D P, BA J. Adam: A method for stochastic optimization[J]. arXiv preprint arXiv:1412.6980, 2014.
[39] CHEN N G, LI C M. Hyperspectral image classification approach based on Wasserstein generative adversarial networks[C]//2020 International Conference on Machine Learning and Cybernetics (ICMLC). Piscataway: IEEE Press, 2020: 53-63.
[40] PECHT M. Battery degradation data[R]. CALCE Battery Research Group, 2017.
[41] XING Y J, MA E W M, TSUI K L, et al. An ensemble model for predicting the remaining useful performance of lithium-ion batteries[J]. Microelectronics Reliability, 2013, 53(6): 811-820.
[42] YU Y, HU C H, SI X S, et al. Averaged Bi-LSTM networks for RUL prognostics with non-life-cycle labeled dataset[J]. Neurocomputing, 2020, 402: 134-147.
[43] 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. Piscataway: IEEE Press, 2008: 1-9.

Options

文章导航

模态框（Modal）标题

摘要

本文引用格式

Abstract

参考文献