Data Visual Analysis and Vitual Reality |
|
|
|
|
An aircraft fuel data missing value filling method with generative adversarial network |
GUO Yibo1, NIU Meng1, WANG Haidi1, CHEN Yanhua1, XUE Junxiao1, YUAN Yue1, HOU Lishuo1, XU Mingliang1, PAN Jun2 |
1.Information Engineering College, Zhengzhou University, Zhengzhou 450001, China 2.China Aviation Industry Corporation Jincheng Nanjing Electromechanical Hydraulic Engineering Research Center, Nanjing 211106, China |
|
|
Abstract The fuel data collected by aircraft sensors is the basis for various follow-up studies on aircraft. However, due to various factors, the data collected by sensors always have many missing values. The direct use of such data for subsequent processing will lead to a decrease in the accuracy of the algorithm. Therefore, the effect of processing missing values in the data is crucial. The existing missing value filling algorithm has two problems. On the one hand, it ignores the historical dependence of time series in the time dimension; on the other hand, some algorithms require a complete data set for model training. In order to solve the above problems, this paper uses a method of filling missing values based on adversarial networks. This method can effectively solve the problems of traditional methods, and can achieve the best filling effect compared with other algorithms.
|
Received: 07 December 2020
Published: 25 July 2021
|
|
|
Cite this article:
GUO Yibo, NIU Meng, WANG Haidi, CHEN Yanhua, XUE Junxiao, YUAN Yue, HOU Lishuo, XU Mingliang, PAN Jun. An aircraft fuel data missing value filling method with generative adversarial network. Journal of Zhejiang University (Science Edition), 2021, 48(4): 402-409.
URL:
https://www.zjujournals.com/sci/EN/Y2021/V48/I4/402
|
基于生成对抗网络的飞机燃油数据缺失值填充方法
飞机传感器采集的燃油数据是后续燃油测量的基础。在飞行过程中,由传感器采集的数据因存在部分缺失值,如直接进行后续处理将影响燃油测量精度。现有的缺失值填充方法存在两方面问题,一方面易忽视飞机燃油时序数据在时间维度上的上下文依赖关系;另一方面缺少完整的样本数据集进行模型训练。基于此,提出了一种基于生成对抗网络的缺失值填充方法,从而有效解决了传统方法难以处理的时序数据历史隐含规律及样本不完整的问题,且填充效果较其他算法更佳。
关键词:
循环神经网络,
生成对抗网络,
缺失值填充方法,
Seq2seq 模型
|
|
1 AMIRI M,JENSEN R. Missing data imputation using fuzzy-rough methods[J]. Neurocomputing,2016,205:152-164. DOI:10.1016/j.neucom.2016.04.015 2 PURWAR A,SINGH S K. Hybrid prediction model with missing value imputation for medical data[J]. Expert Systems with Applications,2015,42(13):5621-5631. DOI:10.1016/j.eswa.2015.02.050 3 KANTARDZIE M,SRIVASTAVA A N. Data mining:Concepts,models,methods,and algorithms[J]. Journal of Computing and Information Science in Engineering,2005,5(4):394-395. 4 MAZUMDER R,HASTIE T,TIBSHIRANI R. Spectral regularization algorithms for learning large incomplete matrices[J]. Journal of Machine Learning Research,2010,11:2287-2322. 5 HASTIE T,MAZUMDER R,LEE J,et al. Matrix completion and low-rank SVD via fast alternating least squares[J]. Journal of Machine Learning Research,2014,16(1):3367-3402. 6 GOLUB G H. Singular value decomposition and least squares solutions[J]. Numerische Mathematik,1970,14(5):403-420. DOI:10.1007/bf02163027 7 CHOW S C. Encyclopedia of Biopharmaceutical Statistics [M]. Britain:Informa,2003. 8 LEE D D,SEUNG H S. Learning the parts of objects by non-negative matrix factorization[J]. Nature,1999,401(6755):788-791. DOI:10.1038/44565 9 SALAKHUTDINOV R,MNIH A. Probabilistic matrix factorization[C]//20th Advances in Neural Information Processing Systems.Vancouver:MIT Press,2007:432-451. 10 NIKFALAZAR S,YEH C H,BEDINGFIELD S,et al. Missing data imputation using decision trees and fuzzy clustering with iterative learning[J]. Knowledge and Information Systems,2020,62:2419-2437. DOI:10.1007/S10115-019-01427-1 11 KHAN S I,HOQUE A S M L. SICE:An improved missing data imputation technique[J]. Journal of Big Data,2020,7(1):1-21. DOI:10.1186/s40537-020-00313-w 12 冯宪凯,黄树成. 基于DBSCAN的缺失值填充算法研究[J]. 计算机与数字工程,2020,48(7):1572-1575,1686. FENG X K,HUANG S C. Research on missing value filling algorithm based on DBSCAN [J]. Computer and Digital Engineering,2020,48(7):1572-1575,1686. 13 BATISTA G E,MONARD M C. An analysis of four missing data treatment methods for supervised learning[J]. Applied Artificial Intelligence,2003,17(5/6):519-533. 14 张楷卉,李鹏. 一种基于模糊C均值聚类的稀疏数据缺失值填充方法[J]. 黑龙江大学自然科学学报,2019,36(6):124-130. ZHANG K H,LI P. A missing data imputation method of sparse data based on fuzzy C-means clustering [J]. Journal of Natural Science of Heilongjiang University,2019,36(6):124-130. 15 CHE Z,PURUSHOTHAM S,CHO K,et al. Recurrent neural networks for multivariate time series with missing values[J]. Scientific Reports,2018,8(1):1-12. DOI:10.1038/s41598-018-24271-9 16 郝雨微. 基于深度学习的医疗时序数据补值模型研究[D]. 长春:吉林大学,2019. DOI:10.21661/r-497961 HAO Y W. Research on Deep Learning Based Imputation Model for Clinical Time Series[D]. Changchun:Jilin University,2019. DOI:10.21661/r-497961 17 FEDUS W,GOODFELLOW I,DAI A M. MaskGAN:Better text generation via filling in the—[C]// 6th International Conference on Learning Representations. Vancouver:ICLR,2018. 18 YOON J,JORDON J,SCHAAR M. GAIN:Missing data imputation using generative adversarial nets[C]// 35th International Conference on Machine Learning. Stockholm:ICML,2018:5689-5698. 19 SHANG C,PALMER A,SUN J W,et al. VIGAN:Missing view imputation with generative adversarial networks[C]//2017 IEEE International Conference on Big Data. Boston:IEEE,2017:766-775. DOI:10.1109/BigData.2017.8257992 20 罗永洪. 基于生成对抗网络的时序数据缺失值填充算法研究[D]. 天津:南开大学,2019. DOI:10.21661/r-497961 LUO Y H. Research on Multivariate Time Series Imputation with Generative Adversarial Network[D]. Tianjin:Nankai University,2019. DOI:10.21661/r-497961 21 LUO Y H,CAI X R,ZHANG Y,et al. Multivariate time series imputation with generative adversarial networks[C]// 32nd International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc,2018:1596-607. DOI:10. 23919/eusipco.2018.8553259 22 VASWANI A,SHAZEER N,PARMAR N,et al. Attention is all you need[C]// 31st International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc,2017:6000-6010. 23 HYLAND S,ESTEBAN C,RATSCH G. Real-Valued (Medical) Time Series Generation with Recurrent Conditional GANs[Z/OL].(2017-12-04). https://arxiv.org/pdf/1706.02633.pdf. 24 GOODFELLOW I J,POUGET-ABADIE J,MIRZA M,et al. Generative adversarial nets[C]// 27th International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc,2014:2672-2680. 25 ARJOVSKY M,CHINTALA S,BOTTOU L. Wasserstein GAN[Z/OL].(2017-12-06). https://arxiv.org/pdf/1701.07875.pdf. 26 SUTSKEVER I,VINYALS O,LE Q V. Sequence to sequence learning with neural networks[C]// 27th International Conference on Neural Information Processing Systems. Red Hook:Curran Associates Inc,2014:3104-3112. 27 SCHUSTER M,PALIWAL K K. Bidirectional recurrent neural networks[J]. IEEE Transactions on Signal Processing,1997,45(11):2673-2681. DOI:10.1109/78.650093 28 HOCHREITER S,SCHMIDHUBER J. Long short-term memory[J]. Neural Computation,1997,9(8):1735-1780. DOI:10.1162/neco.1997.9.8.1735 |
|
Viewed |
|
|
|
Full text
|
|
|
|
|
Abstract
|
|
|
|
|
Cited |
|
|
|
|
|
Shared |
|
|
|
|
|
Discussed |
|
|
|
|