Advertisement

Cluster Computing

, Volume 22, Supplement 3, pp 7525–7537 | Cite as

Cost-sensitive large margin distribution machine for fault detection of wind turbines

  • Mingzhu TangEmail author
  • Steven X. Ding
  • Chunhua Yang
  • Fanyong Cheng
  • Yuri A. W. Shardt
  • Wen Long
  • Daifei Liu
Article

Abstract

Given the importance of the class-imbalanced data and misclassified unequal costs in large wind turbine datasets, this paper proposes a cost-sensitive large margin distribution machine (CLDM) for fault detection of wind turbines. The margin mean and margin variance are use to characterize the margin distribution. The objective function and constraints of the large margin distribution machine (LDM) are modified to be cost-sensitive. The class-imbalanced data and misclassified unequal costs are solved by selecting the appropriately cost-sensitive parameters. Then CLDM is designed to train and test data from wind turbines in a wind farm. In order to verify the effectiveness of CLDM, it is compared with support vector machine (SVM), cost-sensitive SVM, and LDM. Comprehensive experiments on 7 datasets from a benchmark model of wind turbines and 5 datasets from a real wind farm show that CLDM has better sensitivity, gMean and average misclassified cost than the other methods.

Keywords

Margin distribution Fault detection Class-imbalanced problem Misclassified unequal cost Wind turbine 

Notes

Acknowledgements

This work was partially supported by the National Natural Science Foundation of China (# 61403046, # 61463009, # 51674042),the Major Program of the National Natural Science Foundation of China under Grant (# 61490702), the Natural Science Foundation of Hunan Province, China (# 2015JJ3005), China Scholarship Council, the Key Laboratory of Renewable Energy Electric-Technology of Hunan Province, the Key Laboratory of Efficient & Clean Energy Utilization of Hunan Province, Hubei Key Laboratory of Power System Design and Test for Electrical Vehicle, Open Project Funding of Fujian Key Laboratory of Information Processing and Intelligent Control (MJUKF201737), and Hunan Province 2011 Collaborative Innovation Center of Clean Energy and Smart Grid.

References

  1. 1.
    Zhang, X., Chen, W., Wang, B., Chen, X.: Intelligent fault diagnosis of rotating machinery using support vector machine with ant colony algorithm for synchronous feature selection and parameter optimization. Neurocomputing 167, 260–279 (2015)CrossRefGoogle Scholar
  2. 2.
    Houari, T., Moamar, S.M.: Hybrid dynamic classifier for drift-like fault diagnosis in a class of hybrid dynamic systems: application to wind turbine converters. Neurocomputing 171, 1496–1516 (2016)CrossRefGoogle Scholar
  3. 3.
    Yin, Z., Hou, J.: Recent advances on svm based fault diagnosis and process monitoring in complicated industrial processes. Neurocomputing 174, 643–650 (2016)CrossRefGoogle Scholar
  4. 4.
    Kusiak, A., Li, W.: The prediction and diagnosis of wind turbine faults. Renew. Energy 36(1), 16–23 (2011)CrossRefGoogle Scholar
  5. 5.
    Dao, P.B., Staszewski, W.J., Barszcz, T., Uhl, T.: Condition monitoring and fault detection in wind turbines based on cointegration analysis of scada data. Renew. Energy 116, 107–122 (2017)CrossRefGoogle Scholar
  6. 6.
    Badihi, H., Zhang, Y., Hong, H.: Fault-tolerant cooperative control in an offshore wind farm using model-free and model-based fault detection and diagnosis approaches. Appl. Energy 201, 284–307 (2017)CrossRefGoogle Scholar
  7. 7.
    de Bessa, I.V., Palhares, R.M., D’Angelo, M.F.S.V., Chaves Filho, J.E.: Data-driven fault detection and isolation scheme for a wind turbine benchmark. Renew. Energy 87(1), 634–645 (2016)CrossRefGoogle Scholar
  8. 8.
    Sebastian, T.S., Carlos, O.M., Puig, V.: Robust fault diagnosis of nonlinear systems using interval constraint satisfaction and analytical redundancy relations. IEEE Trans. Syst. Man Cybern. Syst. 44(1), 18–29 (2014)CrossRefGoogle Scholar
  9. 9.
    Krüger, M., Ding, S.X., Haghani, A., Engel, P., Jeinsch, T.: A datadriven approach for sensor fault diagnosis in gearbox of wind energy conversion system. In: 2013 10th IEEE International Conference on Control and Automation (ICCA). IEEE, pp. 227–232 (2013)Google Scholar
  10. 10.
    Chen, W., Ding, S.X., Haghani, A., Naik, A., Khan, A.Q., Yin, S.: Observer-based fdi schemes for wind turbine benchmark. IFAC Proc. Vol. 44(1), 7073–7078 (2011)CrossRefGoogle Scholar
  11. 11.
    Badihi, H., Zhang, Y., Hong, H.: Wind turbine fault diagnosis and fault-tolerant torque load control against actuator faults. IEEE Trans. Control Syst. Technol. 23(4), 1351–1372 (2015)CrossRefGoogle Scholar
  12. 12.
    Tabatabaeipour, S.M., Odgaard, P.E., Bak, T., Stoustrup, J.: Fault detection of wind turbines with uncertain parameters: a set-membership approach. Energies 5(7), 2224–2248 (2012)CrossRefGoogle Scholar
  13. 13.
    Badihi, H., Zhang, Y., Hong, H.: Fuzzy gain-scheduled active fault tolerant control of a wind turbine. J. Frankl. Inst. 351(7), 3677–3706 (2014)CrossRefGoogle Scholar
  14. 14.
    Sun, P., Li, J., Wang, C., Lei, X.: A generalized model for wind turbine anomaly identification based on scada data. Appl. Energy 168, 550–567 (2016)CrossRefGoogle Scholar
  15. 15.
    Chawla, N.V., Japkowicz, N., Kotcz, A.: Editorial: special issue on learning from imbalanced data sets. ACM Sigkdd Explor. Newsl. 6(1), 1–6 (2004)CrossRefGoogle Scholar
  16. 16.
    Sun, Y., Kamel, M.S., Wong, A.K., Wang, Y.: Cost-sensitive boosting for classification of imbalanced data. Pattern Recognit. 40(12), 3358–3378 (2007)CrossRefGoogle Scholar
  17. 17.
    Charte, F., Rivera, A.J., del Jesus, M.J., Herrera, F.: MLSMOTE: approaching imbalanced multilabel learning through synthetic instance generation. Knowl. Based Syst. 89, 385–397 (2015)CrossRefGoogle Scholar
  18. 18.
    Dez Pastor, J.F., Rodrguez, J.J., Garca Osorio, C., Kuncheva, L.I.: Random balance: ensembles of variable priors classifiers for imbalanced data. Knowl. Based Syst. 85, 96–111 (2015)CrossRefGoogle Scholar
  19. 19.
    Masnadi-Shirazi, H., Vasconcelos, N., Iranmehr, A.: Cost-sensitive support vector machines. arXiv:1212.0975 (2012)
  20. 20.
    Ling, C.X., Sheng, V.S.: Cost-Sensitive Learning, pp. 231–235. Springer, New York (2011)Google Scholar
  21. 21.
    Davenport, M.A.: The 2nu-SVM: a cost-sensitive extension of the nu-SVM. DTIC Document, Report (2005)Google Scholar
  22. 22.
    Gu, X., Chung, F.L., Ishibuchi, H.: Imbalanced TSK fuzzy classifier by cross-class Bayesian fuzzy clustering and imbalance learning. IEEE Trans. Syst. Man Cybernet. Syst. 47, 2005–2020 (2017)CrossRefGoogle Scholar
  23. 23.
    Galar, M., Fernandez, A., Barrenechea, E., Bustince, H., Herrera, F.: A review on ensembles for the class imbalance problem: bagging, boosting, and hybrid-based approaches. IEEE Trans. Syst. Man Cybernet. Part C 42(4), 463–484 (2012)CrossRefGoogle Scholar
  24. 24.
    Khoshgoftaar, T.M., Hulse, J.V., Napolitano, A.: Comparing boosting and bagging techniques with noisy and imbalanced data. IEEE Trans. Syst. Man Cybernet. Part A 41(3), 552–568 (2011)CrossRefGoogle Scholar
  25. 25.
    Seiffert, C., Khoshgoftaar, T.M., Hulse, J.V., Napolitano, A.: Rusboost: a hybrid approach to alleviating class imbalance. IEEE Trans. Syst. Man Cybernet. Part A 40(1), 185–197 (2010)CrossRefGoogle Scholar
  26. 26.
    Gu, B., Sun, X., Sheng, V.S.: Structural minimax probability machine. IEEE Trans. Neural Netw. Learn. Syst. 28, 1646–1656 (2017)MathSciNetCrossRefGoogle Scholar
  27. 27.
    Yuan, C., Sun, X., Lv, R.: Fingerprint liveness detection based on multi-scale LPQ and PCA. China Commun. 13(7), 60–65 (2016)CrossRefGoogle Scholar
  28. 28.
    Xia, Z., Wang, X., Sun, X., Wang, B.: Steganalysis of least significant bit matching using multi-order differences. Secur. Commun. Netw. 7(8), 1283–1291 (2014)CrossRefGoogle Scholar
  29. 29.
    Xia, Z., Wang, X., Sun, X., Liu, Q., Xiong, N.: Steganalysis of LSB matching using differences between nonadjacent pixels. Multimed. Tools Appl. 75(4), 1947–1962 (2016)CrossRefGoogle Scholar
  30. 30.
    Cheng, F., Zhang, J., Wen, C.: Cost-sensitive large margin distribution machine for classification of imbalanced data. Pattern Recognit. Lett. 80, 107–112 (2016)CrossRefGoogle Scholar
  31. 31.
    Vapnik, V.N.: The Nature of Statistical Learning Theory. Springer, Heidelberg (1995)CrossRefGoogle Scholar
  32. 32.
    Scholkopf, B., Smola, A.J.: Learning with Kernels: Support Vector Machines, Regularization, Optimization, and Beyond. MIT press, Cambridge (2001)Google Scholar
  33. 33.
    Sun, J., Li, H., Adeli, H.: Concept drift-oriented adaptive and dynamic support vector machine ensemble with time window in corporate financial risk prediction. IEEE Trans. Syst. Man Cybernet. Syst. 43(4), 801–813 (2013)CrossRefGoogle Scholar
  34. 34.
    Gu, B., Sheng, V.S.: A robust regularization path algorithm for support vector classification. IEEE Trans. Neural Netw. Learn. Syst. 28, 1241–1248 (2017)CrossRefGoogle Scholar
  35. 35.
    Gu, B., Sheng, V.S., Tay, K.Y., Romano, W., Li, S.: Incremental support vector learning for ordinal regression. IEEE Trans. Neural Netw. Learn. Syst. 26(7), 1403 (2015)MathSciNetCrossRefGoogle Scholar
  36. 36.
    Gu, B., Sheng, V.S., Wang, Z., Ho, D., Osman, S., Li, S.: Incremental learning for support vector regression. Neural Netw. 67, 140–150 (2015)CrossRefGoogle Scholar
  37. 37.
    Wymore, M.L., Van Dam, J.E., Ceylan, H., Qiao, D.: A survey of health monitoring systems for wind turbines. Renew. Sustain. Energy Rev. 52, 976–990 (2015)CrossRefGoogle Scholar
  38. 38.
    Liu, W., Wang, Z., Han, J., Wang, G.: Wind turbine fault diagnosis method based on diagonal spectrum and clustering binary tree SVM. Renew. Energy 50, 1–6 (2013)CrossRefGoogle Scholar
  39. 39.
    Chang, C., Lin, C.: LIBSVM: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)Google Scholar
  40. 40.
    Zhang, T., Zhou, Z.: Large margin distribution machine. In: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, New York, pp. 313–322 (2014)Google Scholar
  41. 41.
    Gao, W., Zhou, Z.: On the doubt about margin explanation of boosting. Artif. Intell. 203, 1–18 (2013)MathSciNetCrossRefGoogle Scholar
  42. 42.
    Yuan, G., Ho, C., Lin, C.: Recent advances of large-scale linear classification. Proc. IEEE 100(9), 2584–2603 (2012)CrossRefGoogle Scholar
  43. 43.
    Chang, K., Hsieh, C., Lin, C., Keerthi, S., Sundararajan, S.: A dual coordinate descent method for large-scale linear SVM. In: Proceedings of the 25th International Conference on Machine Learning, Conference Proceedings. ACM, New York (2008)Google Scholar
  44. 44.
    Odgaard, P.F., Stoustrup, J., Kinnaert, M.: Fault-tolerant control of wind turbines: a benchmark model. IEEE Trans. Control Syst. Technol. 21(4), 1168–1182 (2013)CrossRefGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Mingzhu Tang
    • 1
    • 2
    • 3
    Email author
  • Steven X. Ding
    • 2
  • Chunhua Yang
    • 3
  • Fanyong Cheng
    • 4
  • Yuri A. W. Shardt
    • 5
  • Wen Long
    • 6
  • Daifei Liu
    • 1
  1. 1.School of Energy and Power EngineeringChangsha University of Science & EngineeringChangshaChina
  2. 2.Institute for Automatic Control and Complex Systems (AKS)University of Duisburg-EssenDuisburgGermany
  3. 3.School of Information Science and EngineeringCentral South UniversityChangshaChina
  4. 4.College of Electrical EngineeringAanhui Politechnical UniversityWuhuChina
  5. 5.Department of Chemical EngineeringUniversity of WaterlooWaterlooCanada
  6. 6.Guizhou Key Laboratory of Economics System SimulationGuizhou University of Finance & EconomicsGuiyangChina

Personalised recommendations