Cluster Computing

, Volume 22, Supplement 3, pp 6043–6057 | Cite as

Study on fault diagnosis algorithm in WSN nodes based on RPCA model and SVDD for multi-class classification

  • Qiao-yan Sun
  • Yu-mei Sun
  • Xue-jiao Liu
  • Ying-xin Xie
  • Xiang-guang ChenEmail author


For characteristics of the wireless sensor network (WSN) nodes data streaming in the application environment, the limitations of conventional principal component analysis (PCA) method which depend on the static model in practical application are discussed, an online fault diagnosis algorithm in WSN nodes based on recursive PCA (RPCA) model and support vector data description (SVDD) for multi-class classification is proposed in this paper. The main contents of the method include:The algorithm first applies recursive eigenvalue decomposition techniques based on first-order perturbation (FOP) analysis to update the PCA model adaptively and realize the online fault detection, and then uses SVDD based multi-class classification algorithm to diagnose the fault types. Experimental results show that the algorithm can satisfy the real time needs of data stream processing, but also can track the data changes well. The experimental results based on data sets in real field and experimental data off our typical node failures demonstrate the effectiveness of the proposed algorithm. The algorithm proposed in this paper would improve the safety factor of monitoring sites and it can allows us to know the working state of the node in time and repair or replace it at first time.


Wireless sensor network (WSN) WSN node Fault diagnosis Recursive principal component analysis (RPCA) Support vector data description (SVDD) Data stream processing 



This work was financially supported by Natural Science Foundation (No. ZR2016FM28) of Shandong Province in 2016. Scientific research in this paper was also supported by China Postdoctoral Science Foundation (No. 20100480208).


  1. 1.
    Fall, K.: Disruption tolerant networking for heterogeneous ad hoc networks. IEEE Mil. Commun. Conf. Atl. 4(1), 2195–2201 (2005)Google Scholar
  2. 2.
    Chong, C.Y., Kumar, S.P.: Sensor networks: evolution, opportunities, and challenges. Proc. IEEE 91(8), 1247–1256 (2003)Google Scholar
  3. 3.
    Geng, J.T., Zhou, X.J., Zhang, B.: An atmosphere environment monitor system based on wireless sensor network. J. Xihua Univ. 26(4), 44–46 (2007)Google Scholar
  4. 4.
    Guangzhao, C., Song, J.: An agricultural environment monitor system based on wireless sensor network. Commun. Technol. 41(12), 287–289 (2008)Google Scholar
  5. 5.
    Park C., Chou P. H., Bai Y., et al: An ultra-wearable, wireless, low power ECG monitoring system. Biomedical Circuits and Systems Conference, London, pp. 241–244 (2006)Google Scholar
  6. 6.
    Fei, J., Xia, L.: Design of monitoring system for home environment based on zigBee technology. Comput. Dev. Appl. 21(2), 55–59 (2008)Google Scholar
  7. 7.
    Jing, X., Wang, W., Hei, L.: Application of wireless sensor networks in coal mine safety intelligent monitoring system. Coal Technol. 28(4), 93–97 (2009)Google Scholar
  8. 8.
    Wenjie, C., Lifeng, C., Zhanglong, C., et al.: A realtime dynamic traffic control system based on wireless sensor network. In: Proceedings of the 2005 International Conference on Parallel Processing Workshops (ICPPW’05), pp. 258–264 (2005)Google Scholar
  9. 9.
    Ren, F., Huang, H., Lin, C.: Wireless sensor networks. J. Softw. 14(7), 1282–1291 (2003)zbMATHGoogle Scholar
  10. 10.
    Akyildiz, I.F., Su, W., Sankarasubramaniam, Y.: A survey on sensor networks. IEEE Commun. Mag. 8, 102–114 (2002)Google Scholar
  11. 11.
    Zheng, J., Qu, Y., Zhao, B.: Embedded self-organized communication protocol stack for wireless sensor networks. J. Beijing Univ. Posts Telecommun. 32, 84–87 (2009)Google Scholar
  12. 12.
    Li, J.Z., Li, J.B., Shi, S.F.: Concepts, issues and advance of sensor networks and data management of sensor networks. J. Softw. 10, 1717–1725 (2003)zbMATHGoogle Scholar
  13. 13.
    Mahapatro, A., Khilar, P.M.: Online fault diagnosis of wireless sensor networks. Cent. Eur. J. Comput. Sci. 4(1), 30–44 (2014)Google Scholar
  14. 14.
    Lo, C., Lynch, J.P., Liu, M.: Distributed model-based nonlinear sensor fault diagnosis in wireless sensor networks. Mech. Syst. Signal Process. 66–67, 470–484 (2016)Google Scholar
  15. 15.
    Chanak, P., Banerjee, I., Sherratt, R.S.: Mobile sink based fault diagnosis scheme for wireless sensor networks. J. Syst. Softw. 119, 45–57 (2016)Google Scholar
  16. 16.
    Panda, M., Khilar, P.M.: Distributed self fault diagnosis algorithm for large scale wireless sensor networks using modified three sigma edit test. Ad Hoc Netw. 25, 170–184 (2015)Google Scholar
  17. 17.
    Aydın, I., Karaköse, M., Akın, E.: Combined intelligent methods based on wireless sensor networks for condition monitoring and fault diagnosis. J. Intell. Manuf. 26(4), 717–729 (2015)Google Scholar
  18. 18.
    Garai, B.C., Das, P.: A novel approach for fault diagnosis in wireless sensor networks. Commun. Netw. 05(2), 169–177 (2013)Google Scholar
  19. 19.
    Yugeng, S., Jing, Z., Yongjin, S.: Wireless self-organized sensor network. J. Trans. Technol. 17(2), 331–348 (2004)Google Scholar
  20. 20.
    Wu, M.Y., Dong, H., Xingting, D.: DC/DC power module minimization technology study. Power Electron. 45(9), 76–78 (2011)Google Scholar
  21. 21.
    Qian, Z.: Research and Application on High Performance Data Flow Pattern Discovery Algorithm. Zhejiang University, Zhejiang (2008)Google Scholar
  22. 22.
    Wold, S.: Exponentially weighted moving principal component analysis and projection to latent structures. Chemom. Intell. Lab. Syst. 23(1), 149–161 (1994)Google Scholar
  23. 23.
    Weihua, Li, Yue, H., Valle-Cervantes, S., et al.: Recursive PCA for adaptive process monitoring. Process Control 10, 471–486 (2000)Google Scholar
  24. 24.
    Martin, E.B., Morris, A.J.: Adaptive multivariate statistical process control for monitoring time-varying processes. Ind. Eng. Chem. Res. 45(9), 3108–3118 (2006)Google Scholar
  25. 25.
    Champagne, B.: Adaptive eigen decomposition of data covariance matrices based on first-order perturbations. IEEE Trans. Signal Process. 42(10), 2758–2770 (1994)Google Scholar
  26. 26.
    Peddaneni, H., Erdogmus, D., Rao, Y.N., et al.: Recursive principal components analysis using eigenvector matrix perturbation. Eurasip J. Adv. Signal Process. 13, 2034–2041 (2004)Google Scholar
  27. 27.
    Wang, X., Kruger, U., Irwin, G.W.: Process monitoring approach using fast moving window PCA. Ind. Eng. Chem. Res. 44(15), 5691–5702 (2005)Google Scholar
  28. 28.
    Zhisong, M.Z.M.P., Lu-wen, Y.W.W.Z.: New multi-class classification based on support vector date description. Comput. Sci. 36(3), 65–68 (2009)Google Scholar
  29. 29.
    Du, J.: Study on Theory and Methods of Intelligent Fault Diagnosis Based on Kernel AlgorithmStudy on Theory and Methods of Intelligent Fault Diagnosis Based on Kernel Algorithm. Xi‘an University of Science and Technology, Xi‘an (2006)Google Scholar
  30. 30.
    Qing, Z., Guanghua, X., Jing, W.: Dynamic multi-fault diagnosis model based on support vector domain description. J. Xi’an Jiaotong Univ. 41(5), 593–597 (2007)Google Scholar
  31. 31.
    Yu, L.U.O., Wende, Y.I., Dake, H.E., et al.: Fast reduction for large-scale training data set. J. Southwest Jiaotong Univ. 42(7), 468–472 (2007)zbMATHGoogle Scholar

Copyright information

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

Authors and Affiliations

  • Qiao-yan Sun
    • 1
  • Yu-mei Sun
    • 1
  • Xue-jiao Liu
    • 2
  • Ying-xin Xie
    • 3
  • Xiang-guang Chen
    • 2
    Email author
  1. 1.College of Electronic EngineeringYantai Nanshan UniversityLongkouChina
  2. 2.School of Chemistry and Chemical EngineeringBeijing Institute of TechnologyBeijingChina
  3. 3.North China Institute of Science & TechnologyLangfangChina

Personalised recommendations