Advertisement

Fault Diagnosis of Gas Turbine Fuel Systems Based on Improved SOM Neural Network

  • Zhe Chen
  • Yiyao Zhang
  • Hailei Gong
  • Xinyi Le
  • Yu ZhengEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11555)

Abstract

Considering the difficulties in constructing physical models to simulate fuel systems of gas turbines, we introduce an improved approach based on SOM neural network for the fault diagnosis of fuel systems. In this model the competitive layer structure is decided by an objective function, the parameter functions are selected with genetic algorithm, and the weight vectors are initialized with a pre-segmentation method. Meanwhile, before the data is inputted, PCA dimensional reduction is used to decrease the training consumption. Eventually, practical dataset verification suggests that this improved SOM neural network performs better in recognition rate than other classification algorithms and original SOM network in fault diagnosis of gas turbine fuel system.

Keywords

Fuel system Fault diagnosis SOM (Self-Organized Map) 

References

  1. 1.
    Isermann, R.: Fault-Diagnosis Systems: An Introduction from Fault Detection to Fault Tolerance. Springer Science & Business, Berlin (2006)Google Scholar
  2. 2.
    Yazici, B., Kliman, G.B.: An adaptive statistical time-frequency method for detection of broken bars and bearing faults in motors using stator current. IEEE Trans. Ind. Appl. 35(2), 442–452 (1999)Google Scholar
  3. 3.
    Yen, G.G., Lin, K.C.: Wavelet packet feature extraction for vibration monitoring. IEEE Trans. Ind. Electron. 47(3), 650–667 (2000)Google Scholar
  4. 4.
    Liu, B., Ling, S.F., Meng, Q.: Machinery diagnosis based on wavelet packets. J. Vib. Control 3(1), 5–17 (1997)Google Scholar
  5. 5.
    Muralidharan, V., Sugumaran, V.: Feature extraction using wavelets and classification through decision tree algorithm for fault diagnosis of mono-block centrifugal pump. Measurement 46(1), 353–359 (2013)Google Scholar
  6. 6.
    Hui, K.H., Ooi, C.S., Lim, M.H., Leong, M.S.: A hybrid artificial neural network with Dempster-Shafer theory for automated bearing fault diagnosis. J. Vibroeng. 18(7), 4409–4418 (2016)Google Scholar
  7. 7.
    FernáNdez-Francos, D., MartíNez-Rego, D., Fontenla-Romero, O., Alonso-Betanzos, A.: Automatic bearing fault diagnosis based on one-class ν-SVM. Comput. Ind. Eng. 64(1), 357–365 (2013)Google Scholar
  8. 8.
    Cai, B., Liu, Y., Fan, Q., Zhang, Y., Liu, Z., Yu, S., Ji, R.: Multi-source information fusion based fault diagnosis of ground-source heat pump using bayesian network. Appl. Energy 114, 1–9 (2014)Google Scholar
  9. 9.
    Jianmin, L., Yupeng, S., Xiaoming, Z., Shiyong, X., Lijun, D.: Fuel injection system fault diagnosis based on cylinder head vibration signal. Procedia Eng. 16, 218–223 (2011)Google Scholar
  10. 10.
    Albarbar, A., Gu, F., Ball, A.D.: Diesel engine fuel injection monitoring using acoustic measurements and independent component analysis. Measurement 43(10), 1376–1386 (2010)Google Scholar
  11. 11.
    Zhi-Ling, Y., Bin, W., Xing-Hui, D., Hao, L.I.U.: Expert system of fault diagnosis for gear box in wind turbine. Syst. Eng. Procedia 4, 189–195 (2012)Google Scholar
  12. 12.
    Amirat, Y., Choqueuse, V., Benbouzid, M.H.: Wind turbines condition monitoring and fault diagnosis using generator current amplitude demodulation. In: 2010 IEEE International Energy Conference, pp. 310–315 (2010)Google Scholar
  13. 13.
    Fengming, L.: Design and Implementation of Fault Diagnosis of Diesel Engine Fuel System Based on Wavelet Neural Network (in Chinese). Master’s thesis. Shandong University (2010)Google Scholar
  14. 14.
    Cheng, G., Cheng, Y.L., Shen, L.H., Qiu, J.B., Zhang, S.: Gear fault identification based on Hilbert-Huang transform and SOM neural network. Measurement 46(3), 1137–1146 (2013)Google Scholar
  15. 15.
    Jafari-Marandi, R., Khanzadeh, M., Smith, B.K., Bian, L.: Self-Organizing and Error Driven (SOED) artificial neural network for smarter classifications. J. Comput. Design Eng. 4(4), 282–304 (2017)Google Scholar
  16. 16.
    Delgado, S., Higuera, C., Calle-Espinosa, J., Morán, F., Montero, F.: A SOM prototype-based cluster analysis methodology. Expert Syst. Appl. 88, 14–28 (2017)Google Scholar
  17. 17.
    Li, W., Peng, M., Wang, Q.: False alarm reducing in PCA method for sensor fault detection in a nuclear power plant. Ann. Nucl. Energy 118, 131–139 (2018)Google Scholar
  18. 18.
    Jiang, X., Liu, K., Yan, J., Chen, W.: Application of improved SOM neural network in anomaly detection. Phys. Procedia 33, 1093–1099 (2012)Google Scholar
  19. 19.
    Guanglan, L., Tielin, S., Nan, J., Shiyuan, L.: Research on feature selection technology based on som network (in Chinese). J. Mech. Eng. 41(2), 46–50 (2005)Google Scholar
  20. 20.
    Burgas Nadal, L., Meléndez Frigola, J., Colomer Llinàs, J., Massana Raurich, J., Pous Sabadí, C.: N-dimensional extension of unfold-PCA for granular systems monitoring. Eng. Appl. Artif. Intell. 71, 113–124 (2018)Google Scholar
  21. 21.
    Yan, Y.: Research on Clustering and Data Analysis Method Based on One-Dimensional SOM Neural Network (in Chinese). Tianjin University, Diss (2010)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Zhe Chen
    • 1
  • Yiyao Zhang
    • 1
  • Hailei Gong
    • 1
  • Xinyi Le
    • 1
  • Yu Zheng
    • 1
    Email author
  1. 1.Institute of Intelligent Manufacturing and Information Engineering, School of Mechanical EngineeringShanghai Jiao Tong UniversityShanghaiChina

Personalised recommendations