Skip to main content
SpringerLink
Log in

Fault detection method for flexible DC grid based on CEEMDAN multiscale entropy and GA-SVM

  • Original Paper
  • Published:
Electrical Engineering Aims and scope Submit manuscript

Abstract

Compared with the traditional AC grid, the flexible DC grid has the advantages of low wire loss and large transmission capacity, but it is difficult to extract fault signals and diagnose various faults. Therefore, a fault detection method based on complete ensemble empirical mode decomposition with adaptive noise analysis (CEEMDAN) multiscale entropy (MSE) and genetic algorithm optimization support vector machine (GA-SVM) is proposed. Firstly, CEEMDAN is used to decompose the extracted fault line mode voltage signal into several intrinsic mode function (IMF). The IMF containing more fault information is selected to reconstruct the denoising signal. The MSE of the reconstructed signal is calculated and input into the GA-SVM classifier as the fault feature, and the fault line mode voltage signals of different fault types under different operating conditions are classified and recognized. A large number of simulation results prove that the proposed method has strong anti-interference ability and high reliability, and has high classification accuracy in the case of small sample data. Compared with Linear-SVM, PSO-SVM, KNN and Fine Tree intelligent algorithms, the proposed method shows a significantly improved accuracy, 93.8888% on average.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11

Similar content being viewed by others

Data availability

All data generated or analyzed during this study are included in this published article.

Abbreviations

MMC:

Modular multilevel converter

SM:

Sub-module

IMF:

Intrinsic mode function

MSE:

Multiscale entropy

SVM:

Support vector machine

GA:

Genetic algorithm

CEEMDAN:

Complete ensemble empirical mode decomposition with adaptive noise analysis

CEEMD:

Complete ensemble empirical mode decomposition

EEMD:

Ensemble empirical mode decomposition

EMD:

Empirical mode decomposition

CLR:

Current limiting reactor

HVDC:

High voltage direct current

L s :

Bridge arm inductance

U dc :

DC side voltage

i dc :

DC side current

U si :

Secondary side voltage of the external AC grid transformer (i = a, b, c)

I si :

Secondary side current of the external AC grid transformer (i = a, b, c)

U i :

Voltage output from the external AC grid to the converter station (i = a, b, c)

R :

Equivalent resistance of the AC side

L :

Equivalent inductance of the AC side

U ip, U in :

Voltage of upper and lower bridge arms (i = a, b, c)

I ip, I in :

Current flowing through the upper bridge arms respectively (i = a, b, c)

n ip, n in :

Number of SM input by the upper and lower bridge arms (i = a, b, c)

f i :

Fault location (i = a, b, c)

e i :

Electric potential in phase i (i = a, b, c)

u0 :

Zero-mode voltage and line-mode voltage of DC line

u p, u n :

Positive voltage and negative voltage of the DC line

x max(t):

Maximum value of original data x(t)

x min(t):

Minimum value of original data x(t)

M 1(t):

Mean of the envelope

H 1(t):

Intermediate condition function

E k[•]:

kth mode after EMD decomposition

δ k :

Signal-to-noise ratio

x signal :

Fault signal after IMF reconfiguration

X n’(t):

IMF component obtained by decomposition

X0’(t):

Original fault signal

TC :

Correlation coefficient threshold

CIMF :

Correlation coefficient between decomposed IMF and original signal

\(\overline{C} _{{{\text{IMF}}}}\) :

Average number of correlation coefficients between IMFs and original signals

m :

Embedding dimension, m ∈ N + 

r :

Similarity tolerance

τ :

Scale factor, τ ∈ N + , τ = [1,2,…, τmax]

c :

Penalty factor

w :

Weight vector

ξ :

Slack variable

b :

Basis

x i, y i :

Sample set elements

L(w,b,a):

: LAGRANGE function

α i, β i :

Lagrange multiplier

f(x):

Optimal classification function of SVM model

g :

Kernel function parameter

K(x,x i):

Kernel function

SD :

Standard deviation of the original signal

References

  1. Baran ME, Mahajan NR (2003) DC distribution for industrial systems: opportunities and challenges. IEEE Trans Ind Appl 39(6):1596–1601

    Article  Google Scholar 

  2. Adam GP, Vrana TK, Li R et al (2019) Review of technologies for DC grids–power conversion, flow control and protection. IET Power Electron 12(8):1851–1867

    Article  Google Scholar 

  3. Wang X, Gao J, Wei X et al (2022) Faulty feeder detection under high impedance faults for resonant grounding distribution systems. IEEE Trans Smart Grid 14:1880–1895

    Article  Google Scholar 

  4. Liu T, Wei Y, Wang P et al (2020) Efficiency analysis of high-order newton method for flexible DC power flow calculation. High Volt Eng 46(11):3837–3848

    Google Scholar 

  5. Zhang M, Guo R, Sun H (2020) Fault location of MMC-HVDC DC transmission line based on improved VMD and s transform[C]. In: 2020 4th international conference on HVDC (HVDC). IEEE, pp 792–796

  6. Wang S, Zhou L, Wang T et al (2021) Fast protection strategy for DC transmission lines of MMC-based MT-HVDC grid. Chin J Elect Eng 7(2):83–92

    Article  Google Scholar 

  7. Huang NE, Shen Z, Long SR et al (1971) The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc Royal Soc Math Phys Eng Sci 1998(454):903–995

    Google Scholar 

  8. Wei X, Zheng W (2019) An integrated approach for fetal heart rate estimation from abdominal electrocardiogram signal. Chin J Electron 28(6):1198–1203

    Article  Google Scholar 

  9. Wu Z, Huang NE (2009) Ensemble empirical mode decomposition: a noise-assisted data analysis method. Adv Adapt Data Anal 1(1):1–41

    Article  Google Scholar 

  10. Zhao Y, Zhang H (2020) Displacement measurement method based on laser self-mixing interference in the presence of speckle. Chin Opt Lett 18(5):15–19

    Article  Google Scholar 

  11. Wang F, Xing H, Duan S et al (2018) Fault diagnosis of bearings combining OEEMD with teager energy operator demodulation. J Vib Measur Diagn 38(1):87–91

    Google Scholar 

  12. Yeh JR, Shieh JS, Huang NE (2010) Complementary ensemble empirical mode decomposition: A novel noise enhanced data analysis method. Adv Adapt Data Anal 2(2):135–156

    Article  MathSciNet  Google Scholar 

  13. Dong L, Guo X, Zheng Y (2019) Wavelet packet de-noising algorithm for heart sound signals based on CEEMD. J Vib Shock 38(9):192–198

    Google Scholar 

  14. Jiang L, Tan H, Li X et al (2021) Cutting life model of hollow shaft based on dual-frequency vibration system. J Vib Measur Diag 41(1):33–40

    Google Scholar 

  15. Torres ME, Colominas MA, Schlotthauer G et al (2011) A complete ensemble empirical mode decomposition with adaptive noise. In: 2011 IEEE international conference on acoustics, speech, & signal processing, pp 4144–4147.

  16. Vanraj S, Dhami S, Pabla BS (2017) Non-contact incipient fault diagnosis method of fixed-axis gearbox based on CEEMDAN. Royal Soc Open Sci 4(8):2054–2073

    Article  Google Scholar 

  17. Zhang W, Qu Z, Zhang K et al (2017) A combined model based on CEEMDAN and modified flower pollination algorithm for wind speed forecasting. Energy Convers Manag 136:439–451

    Article  Google Scholar 

  18. Dokur E, Erdogan N, Kucuksari S (2022) EV fleet charging load forecasting based on multiple decomposition with CEEMDAN and swarm decomposition. IEEE Access 10:62330–62340

    Article  Google Scholar 

  19. Li Q, Liu Z, Zhao Y et al (2023) A portable microwave intracranial hemorrhage imaging system based on PSO-MCKD-CEEMDAN method. IEEE Trans Microw Theory Tech 71(2):773–793

    Article  Google Scholar 

  20. Wang X, Gao J, Wei X et al (2018) Single line to ground fault detection in a non-effectively grounded distribution network. IEEE Trans Power Deliv 33(6):3173–3186

    Article  Google Scholar 

  21. Han Z, Xu B, Zhu X et al (2016) Research on multi-fault diagnosis of rotor based on approximate entropy and EEMD. China Mechan Eng 27(16):2186–2189

    Google Scholar 

  22. Cui J, Zheng Q, Xin Y et al (2017) Feature extraction and classification method for switchgear faults based on sample entropy and cloud model. IET Gener Transm Distrib 11(11):2938–2946

    Article  Google Scholar 

  23. Guo J, Ma B, Zou T et al (2022) Composite multiscale transition permutation entropy-based fault diagnosis of bearings. Sensors 22(20):7809–7809

    Article  Google Scholar 

  24. Zheng J, Pan H, Cheng J et al (2017) Rolling bearing fault detection and diagnosis based on composite multiscale fuzzy entropy and ensemble support vector machines. Mech Syst Signal Process 85:746–759

    Article  Google Scholar 

  25. Costa M, Goldberger AL, Peng CK (2002) Multiscale entropy analysis of complex physiologic time series. Phys Rev Lett 89(6):068102

    Article  Google Scholar 

  26. Tang H, Yuan Z, Dai H et al (2020) Fault diagnosis of rolling bearing based on probability box theory and GA-SVM. IEEE Access 8:170872–170882

    Article  Google Scholar 

  27. Ye Y, Zhang M (2022) Bearing fault diagnosis model using improved Bayesian information criterion-based variational modal decomposition and IGA-SVM. Adv Mechan Eng 14(12):168

    Google Scholar 

  28. Lopes FV (2016) Settings-free traveling-wave-based earth fault location using unsynchronized two-terminal data. IEEE Trans Power Deliv 31(5):2296–2298

    Article  Google Scholar 

  29. Hu L, Wang L, Chen Y et al (2022) Bearing fault diagnosis using piecewise aggregate approximation and complete ensemble empirical mode decomposition with adaptive noise. Sensors 22(17):6599

    Article  Google Scholar 

  30. Xiao H, Chanwimalueang T, Mandic DP (2022) Multivariate multiscale cosine similarity entropy and its application to examine circularity properties in division algebras. Entropy 24(9):1287

    Article  MathSciNet  Google Scholar 

  31. Muzzammel R, Raza A (2020) A support vector machine learning-based protection technique for MT-HVDC systems. Energies 13(24):6668

    Article  Google Scholar 

  32. Huo W, Li W, Sun C et al (2022) Research on fuel cell fault diagnosis based on genetic algorithm optimization of support vector machine. Energies 15(6):2294

    Article  Google Scholar 

  33. Wu X, Wang D, Cao W et al (2019) A genetic-algorithm support vector machine and DS evidence theory based fault diagnostic model for transmission line. IEEE Trans Power Syst 34(6):4186–4194

    Article  Google Scholar 

Download references

Funding

This work are supported by NSFC (No. 61703144), Natural Science Foundation of Hainan and Henan (Nos. 521RC1110 and 212300410147) and Henan Provincial Science and Technology Research Project (222102220034).

Author information

Authors and Affiliations

  1. School of Electrical Engineering and Automation, Henan Polytechnic University, Jiaozuo, 454003, China

    Yanfang Wei, Jingwen Zhao & Zhihui Zeng

  2. Henan Key Laboratory of Intelligent Detection and Control of Coal Mine Equipment, Henan Polytechnic University, Jiaozuo, 454003, China

    Yanfang Wei

  3. Hainan Institute of Green Energy and Environmental Engineering Technology, Haikou, 570125, China

    Zhanye YANG

  4. State Grid Henan Electric Power Company Scientific Research Institute, Zhengzhou, 450052, China

    Peng Wang

  5. School of Electrical Engineering, Xi’an University of Technology, Xi’an, 710000, China

    Xiaowei Wang

Authors
  1. Yanfang Wei
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Jingwen Zhao
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Zhanye YANG
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Peng Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Zhihui Zeng
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Xiaowei Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

YW contributed to Project administration, Supervision, Review and Edit. YW, JZ, ZY and PW contributed to Methodology, Investigation, Formal analysis, Visualization, Writing Original Draft. ZZ and XW contributed to Investigation, formal analysis.

Corresponding author

Correspondence to Yanfang Wei.

Ethics declarations

Conflict of interest

The authors declare that there is no conflict of interests regarding the publication of this paper.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Wei, Y., Zhao, J., YANG, Z. et al. Fault detection method for flexible DC grid based on CEEMDAN multiscale entropy and GA-SVM. Electr Eng (2024). https://doi.org/10.1007/s00202-024-02349-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00202-024-02349-0

Keywords

Search

Navigation