JACIII Vol.25 No.2 pp. 195-203
doi: 10.20965/jaciii.2021.p0195


Reconstruction Method for Missing Measurement Data Based on Wasserstein Generative Adversarial Network

Changfan Zhang, Hongrun Chen, Jing He, and Haonan Yang

College of Electrical and Information Engineering, Hunan University of Technology
No.89 Taishan Xi Road, Tianyuan District, Zhuzhou, Hunan 412007, China

Corresponding author

October 10, 2020
December 21, 2020
March 20, 2021
high-speed train, generative adversarial network, data dimensionality ascending, convolutional neural network, reconstruction accuracy

Focusing on the issue of missing measurement data caused by complex and changeable working conditions during the operation of high-speed trains, in this paper, a framework for the reconstruction of missing measurement data based on a generative adversarial network is proposed. Suitable parameters were set for each frame. Discrete measurement data are taken as the input of the frame for preprocessing the data dimensionality. The convolutional neural network then learns the correlation between different characteristic values of each device in an unsupervised pattern and constrains and improves the reconstruction accuracy by taking advantage of the context similarity of authenticity. It was determined experimentally that when there are different extents of missing measurement data, the model described in the present paper can still maintain a high reconstruction accuracy. In addition, the reconstruction data also conform well to the distribution law of the measurement data.

Reconstruction frame of high-speed train measurement data based on WGAN

Reconstruction frame of high-speed train measurement data based on WGAN

Cite this article as:
C. Zhang, H. Chen, J. He, and H. Yang, “Reconstruction Method for Missing Measurement Data Based on Wasserstein Generative Adversarial Network,” J. Adv. Comput. Intell. Intell. Inform., Vol.25 No.2, pp. 195-203, 2021.
Data files:
  1. [1] J. He, G. W. Liu, C. F. Zhang et al., “Maximum likelihood iden-tification method of adhesion performance parameters of Heavy-Duty locomotive,” J. of Electronic Measurement and Instrument, Vol.31, No.2, pp. 170-177, 2017.
  2. [2] H. Doreswamy, I. Gad, and B. R. Manjunatha, “Performance evaluation of predictive models for missing data imputation in weather data,” 2017 Int. Conf. on Advances in Computing, Communications and Informatics (ICACCI), pp. 1327-1334, 2017.
  3. [3] H. Y. Sun, Y. L. Li, Y. F. Zi et al., “Accelerating EM Missing Data Filling Algorithm Based on the K-Means,” 2018 4th Annual Int. Conf. on Network and Information Systems for Computers (ICNISC), pp. 401-406, 2018.
  4. [4] M. Pazhoohesh, Z. Pourmirza, and S. Walker, “A Comparison of Methods for Missing Data Treatment in Building Sensor Data,” 2019 IEEE 7th Int. Conf. on Smart Energy Grid Engineering (SEGE), pp. 255-259, 2019.
  5. [5] V. Miranda, J. Krstulovic, H. Keko et al., “Reconstructing Missing Data in State Estimation with Autoencoders,” IEEE Trans. on Power Systems, Vol.27, No.2, pp. 604-611, 2012.
  6. [6] C. F. Zhang, D. Z. Meng, and J. He, “VGG-16 Convolutional Neural Network-Oriented Detection of Filling Flow Status of Viscous Food,” J. Adv. Comput. Intell. Intell. Inform., Vol.24, No.4, pp. 568-575, 2020.
  7. [7] C. Zhao, “Research on Multiband Packet Fusion Algorithm for Hyperspectral Remote Sensing Images,” J. Adv. Comput. Intell. Intell. Inform., Vol.23, No.1, pp. 153-157, 2019.
  8. [8] J. He, B. C. Yang, C. F. Zhang et al., “Robust consensus braking algorithm for distributed EMUs with uncertainties,” IET Control Theory & Applications, Vol.13, No.17, pp. 2766-2774, 2019.
  9. [9] J. S. Jiang, H. R. Ren, and H. Y. Li, “Seismic data processing based on convolutional autoencoder,” J. of Zhejiang University (Engineering Science), Vol.54, No.5, pp. 978-984, 2020.
  10. [10] J. L. Zhou, M. Ye, J. Ding et al., “Rapid and robust traffic accident detection based on orientation map,” Optical Engineering, Vol.51, No.11, 117201, 2012.
  11. [11] J. He, C. F. Zhang, S. A. Mao et al., “Demagnetization fault detection in permanent magnet synchronous motors based on sliding observer,” J. of Nonlinear Science Application, Vol.9, No.5, pp. 2039-2048, 2016.
  12. [12] J. He, B. C. Yang, C. F Zhang et al., “Integrated cooperative braking algorithm of non-linear electric multiple units with external disturbance,” The J. of Engineering, Vol.2019, No.23, pp. 8937-8941, 2019.
  13. [13] S. A. Mao, H. M. Wu, M. H. Lu et al., “Multiple 3D Marker Localization and Tracking System in Image-Guided Radiotherapy,” Int. J. of Robotics and Automation, Vol.32, No.5, pp. 517-523, 2017.
  14. [14] P. Q. Tang, C. F. Zhang, H. H. Tan et al., “A Color Image Watermarking Algorithm Based on Sparse Representation,” The 21st IAPRI World Conf. on Packaging, pp. 364-371, 2018.
  15. [15] C. F. Zhang, G. P. Wu, J. He et al, “Fault-tolerant control for demagnetization faults in permanent magnet synchronous machine,” The 21st IAPRI World Conf. on Packaging, pp. 589-596, 2018.
  16. [16] K. D. B. Mudavathu, M. V. P. C. S. Rao, and K. V. Ramana, “Auxiliary Conditional Generative Adversarial Networks for Image Data Set Augmentation,” 2018 3rd Int. Conf. on Inventive Computation Technologies (ICICT), pp. 263-269, 2018.
  17. [17] N. M. Yao, Q. P. Guo, F. C. Qiao et al., “Robust Facial Expression Recognition With Generative Adversarial Networks,” Acta Automatica Sinica, Vol.44, No.5, pp 865-877, 2018.
  18. [18] X. Yao, H. Yang, and Y. Li, “Modulation Identification of Underwater Acoustic Communications Signals Based on Generative Adversarial Networks,” OCEANS 2019, pp. 1-6, 2019.
  19. [19] M. Arjovsky, S. Chintala, and L. Bottou, “Wasserstein GAN,” arXiv preprint, arXiv:, 2017.
  20. [20] S. X. Wang, H. W. Chen, Z. X. Pan et al., “A Reconstruction Method for Missing Data in Power System Measurement Using an Improved Generative Adversarial Network,” Proc. of the Chinese Society of Electrical Engineering (CSEE), Vol.39, No.1, pp. 56-64, 2019.
  21. [21] T. Ince, S. Kiranyaz, L. Eren et al., “Real-Time Motor Fault Det-ection by 1D Convolutional Neural Networks,” IEEE Trans. on Industrial Electronics, Vol.63, No.11, pp. 7067-7075, 2016.
  22. [22] B. Li, P.-L. Zhang, D.-S. Liu et al., “Feature extraction for rolling element bearing fault diagnosis utilizing generalized S transform and two-dimensional non-negative matrix factorization,” J. of Sound and Vibration, Vol.330, No.10, pp. 2388-2399, 2011.
  23. [23] L. Wen , X. Li, L. Gao et al., “A New Convolutional Neural Network-Based Data-Driven Fault Diagnosis Method,” IEEE Trans. on Industrial Electronics, Vol.65, No.7, pp. 5990-5998, 2018.
  24. [24] J. Chen, Z. Shu, J. Liu et al., “Structure-preserving shape completion of 3D point clouds with generative adversarial network,” Scientia Sinica Informationis, Vol.50, No.5, pp. 675-691, 2020.
  25. [25] C. Zhang, Y. Feng, B. Qiang, and J. Shang, “Wasserstein Generative Recurrent Adversarial Networks for Image Generating,” 2018 24th Int. Conf. on Pattern Recognition (ICPR), pp. 242-247, 2018.
  26. [26] H. Lou, Z. Qi, and J. Li. “One-dimensional data augmentation using a wasserstein generative adversarial network with supervised signal,” 2018 Chinese Control and Decision Conf. (CCDC), pp. 1896-1901, 2018,
  27. [27] Y. H. Luo, X. R. Cai, Y. Zhang et al., “Multivariate Time Series Imputation with Generative Adversarial Networks,” Advances in Neural Information Processing Systems 31 (NeurIPS 2018), pp. 1596-1607, 2018.
  28. [28] Y. Luo, Y. Zhang, X. Cai et al., “E2 GAN: End-to-End Generative Adversarial Network for Multivariate Time Series Imputation,” Proc. of the 28th Int. Joint Conf. on Artificial Intelligence (IJCAI-19), pp. 3094-3100, 2019.

*This site is desgined based on HTML5 and CSS3 for modern browsers, e.g. Chrome, Firefox, Safari, Edge, Opera.

Last updated on May. 28, 2024