logo

SCIENCE CHINA Information Sciences, Volume 64 , Issue 2 : 129204(2021) https://doi.org/10.1007/s11432-018-9613-2

Improved sparse representation based on local preserving projection for the fault diagnosis of multivariable system

More info
  • ReceivedJun 29, 2018
  • AcceptedSep 13, 2018
  • PublishedJun 11, 2020

Abstract

There is no abstract available for this article.


Acknowledgment

This work was supported by National Natural Science Foundation of China (Grant Nos. 61773080, 61673076, 61633005).


References

[1] Ge Z Q. Review on data-driven modeling and monitoring for plant-wide industrial processes. Chemometrics Intelligent Laboratory Syst, 2017, 171: 16-25 CrossRef Google Scholar

[2] Ge Z Q, Song Z, Ding S X. Data Mining and Analytics in the Process Industry: The Role of Machine Learning. IEEE Access, 2017, 5: 20590-20616 CrossRef Google Scholar

[3] Tang Q, Chai Y, Qu J. Fisher Discriminative Sparse Representation Based on DBN for Fault Diagnosis of Complex System. Appl Sci, 2018, 8: 795 CrossRef Google Scholar

[4] Huang S, Elgammal A, Huangfu L, et al. Globality-locality preserving projections for biometric data dimensionality reduction. In: Proceedings of Computer Vision and Pattern Recognition Workshops. New York: IEEE, 2014. 15--20. Google Scholar

[5] Zhan C J, Li S H, Yang Y P. Enhanced Fault Detection Based on Ensemble Global-Local Preserving Projections with Quantitative Global-Local Structure Analysis. Ind Eng Chem Res, 2017, 56: 10743-10755 CrossRef Google Scholar

[6] He X. Locality preserving projections. Advances in Neural Information Processing Systems, 2003, 16: 186-197. Google Scholar

[7] Clemmensen L, Hastie T, Witten D. Sparse Discriminant Analysis. Technometrics, 2011, 53: 406-413 CrossRef Google Scholar

[8] Yu W, Zhao C. Sparse Exponential Discriminant Analysis and Its Application to Fault Diagnosis. IEEE Trans Ind Electron, 2018, 65: 5931-5940 CrossRef Google Scholar

  • Table 1  

    Table 1Classification accuracy (%) of 15 faults in TE process with different methods

    ISLPPSDA SEDA
    Fault #182.7181.67 81.46
    Fault #282.0879.37 80.42
    Fault #317.718.54 11.46
    Fault #472.7113.02 20.21
    Fault #582.0857.6 35.63
    Fault #683.3375.42 77.19
    Fault #783.3380.10 76.98
    Fault #843.9629.48 29.27
    Fault #1237.9219.27 20.21
    Fault #1334.7927.81 25.62
    Fault #1517.7115.42 13.44
    Fault #1751.6744.79 46.98
    Fault #1870.4238.33 62.40
    Fault #1967.087.5 21.67
    Fault #2057.2940.21 34.79