Application of Data Fusion to External Insulation Strength of Contaminated-Insulator Assessment

Abstract:

An external insulation of contaminated-insulator assessment method is proposed based on a tri-level data fusion model of combining principal component analysis (PCA) method, artificial neural net (ANN) method and evidence theory in this paper. When contaminated-insulators partial discharge (PD) occur, much effective information obtained from the sound emitted with PD are synthesized to evaluate the external insulation strength of insulators in operation by the studied method. Firstly, nine characteristic parameters that can rapidly reflect the PD process are selected for image-level fusion of PCA to reduce dimension, which gets two new parameters. Then the new parameters are inputted to ANN for feature-level fusion. Finally, the feature-level fusion output is used as the input of decision-level fusion and fused by means of D-S evidence theory for further reducing the uncertainty of assessment. The artificial contamination experiments were explored to verify the proposed method. The result indicates that the proposed model is more precise than the ANN model under the same conditions.

• Periodical: Applied Mechanics and Materials (Volumes 263-266)
• Pages: 1947-1952
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.263-266.1947
• Online since: December 2012
• Authors: Chun Ming Pei, Ling Li
• Keywords: Artificial Neural Net, Contamination, Data Fusion, Evidence Theory, Insulator, Partial Charge, Principal Component Analysis (PCA)

References

[1] L. E. Lundgaard, "Partial discharge XIV: Acoustic partial discharge detection-practical application," IEEE Electrical Insulation Magazine, Vol.8, July/August, 1992, pp.34-43.

DOI: 10.1109/57.156943

[2] L. E. Lundgard. Practical discharge Part XIII: Acoustic partial discharge detection-Fundamental considerations [J]. IEEE Electrical Insulation Magazine, 1992, 8(4), pp: 25-31.

DOI: 10.1109/57.145095

[3] Wong, K.L., Shihab, S. Radiating signal model for broadband acoustic emission from high voltage equipment[J]. Power System Technology, 2002, 3: 1859-1862.

DOI: 10.1109/icpst.2002.1067854

[4] Teng Lin, Liu Wanshun, Yun Zhihao, et al. Study of real-time power system transient stability emergency control[J]．Proceedings of the CSEE，2003，23(1)：64-69．

[5] Xu Tao, He Renmu, Wang Peng, et al. Power system transient stability assessment based on statistical learning theory[J]．Proceedings of the CSEE，2003，23(11)：51-55．

[6] MaQian, Yang Yihan, Liu Wenying, et al. Power system transient stability assessment with combined SVM method mixing multiple input features[J]．Proceedings of the CSEE，2005, 25(6)：17-23．

[7] Hall D L，Linas J．A survey of techniques for CIS data fusion[C] ．UK IEEE Control and Communications and Management Information System，London，1987．

[8] W. Hung, A note on entropy of intuitionistic fuzzy sets, Int. J. Uncert. Fuzz. Knowledge-Based Syst. 11(2003)627–633.

DOI: 10.1142/s0218488503002375

[9] V. Oduguwa, R. Roy, D. Farrugia, "Development of a soft computing-based framework for engineering design optimization with quantitative and qualitative search spaces," Appl. Soft Comput. 7(2007)166–188.

DOI: 10.1016/j.asoc.2005.06.003

[10] Li Donghui, Zhou Weiwei. DC system grounding fault diagnosis method based on data fusion model of MRNN－BPN－DS [J]．Power System Technology，2004，28(24)：16-20.

[11] Pei Chun-ming, Shu Naiqiu. On-line monitoring of insulator contamination-causing flashover based on acoustic emission, 3rd International Conference on Deregulation and Restructuring and Power Technologies, Apr. 6-9 2008, pp.1667-1671.

DOI: 10.1109/drpt.2008.4523673

[12] Pei Chun-ming, Shu Naiqiu. An Acoustic Emission Method for On-line Monitoring the Contamination-causing Flashover of Insulator，11th International Conference on Electrical Machines and Systems，Oct. 2008.

[13] A. de la o, R. S. Gorur and J. W. Chang, "A clean fog tests on non- ceramic insulating materials and a comparison with ceramic," IEEE Transactions on Power Delivery, vol. 9, No. 4, October 1994, pp.2000-2008.

DOI: 10.1109/61.329532