Recognition of GIS Insulating Defect Types Based on Ultrasonic Detection

Fang Cheng Lv; Bo Zhang

doi:10.4028/www.scientific.net/AMR.898.725

Paper Titles

Neural Network Control for Uncertain Nonlinear Time-Delay Systems
p.705

Sorting Method Based on Rough Sets and its Application in Comprehensive Evaluation of Smart Grid
p.709

Model Predictive Control with on-off Input and its Application to Attitude Control
p.713

Analysis of Stability of Hopfield Neural Networks and Design of Impulsive Controller
p.720

Recognition of GIS Insulating Defect Types Based on Ultrasonic Detection
p.725

The Design of Online Water Pollution Monitoring System for Poultry Rearing
p.730

The Traceable Data Collection and Transmission Methods for Poultry Processing Quality
p.734

The Design of Shafting Condition Monitoring System for Rotating Machinery Based on Fiber Bragg Grating Sensor
p.738

A Software Platform for Water Environment Monitoring
p.743

HomeAdvanced Materials ResearchAdvanced Materials Research Vol. 898Recognition of GIS Insulating Defect Types Based...

Recognition of GIS Insulating Defect Types Based on Ultrasonic Detection

Abstract:

In this paper, high voltage conductor metal protrusions, suspended particles and immobilized metal particles on gas insulated switchgear (GIS) insulators were simulated in the GIS model. The high voltage conductor metal protrusions defect was simulated by a needle-plate model. The GIS model was filled with 0.4MPa SF₆gas. When the voltage was added to 60kV, the three models all had stable discharge. Ultrasonic sensor was used to measure the discharge waveform for 100 groups. The absolute value of difference between the amplitude of adjacent half wave as U_dif and the absolute sum of a cycle of the signal as U_tal were chosen as the characteristic parameters. The defect types were recognized with BP neural network and the recognition rate is about 80%.

You might also be interested in these eBooks

Applied Material Science and Related Technologies

View Preview

Info:

Periodical:

Advanced Materials Research (Volume 898)

Pages:

725-729

DOI:

https://doi.org/10.4028/www.scientific.net/AMR.898.725

Citation:

Cite this paper

Online since:

February 2014

Authors:

Fang Cheng Lv*, Bo Zhang

Keywords:

BP Neural Network (BPNN), Gas Insulated Switchgear (GIS), Type of Insulating Defect, Ultrasonic Detection

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] SUN Shu-guang, LU Jian-guo, YU Hui-zhong, et al. Measure and Analysis of GIS Partial Discharge Based on UHF Method. Electrical Measurement & Instrumentation, 2012, 49(556): 5-9, in Chinese.

Google Scholar

[2] QI Bo, LI Cheng-rong, HAO Zhen, et al. The surface partial discharge development phenomena and their characteristics of GIS insulator surface fixed metal particles. Proceedings of the CSEE, 2011, 34(4): 312-317, in Chinese.

Google Scholar

[3] A. Arora, H. Koch. Design features of GIS. IEEE Power Engineering Society General Meeting2005. San Francisco, California, United States: IEEE, 2005: 927~929.

Google Scholar

[4] C. Lindsay, M. Hick. Experience with SF6 gas-insulated substations and proposals for improved reliability. IEEE Transactions on Power Apparatus and Systems, 1984, 103(9): 2596-2604.

DOI: 10.1109/tpas.1984.318428

Google Scholar

[5] TANG Ju, LIN Jun-yi, ZHUO Ran, et al. Partial discharge type recognition based on support vector data description. High Voltage Engineering, 39(5): 1046-1053, in Chinese.

Google Scholar

[6] Chalimourda A, Scholkopf B, Smola A. Experimentally optimal v in support vector regression for different noise models and parameter settings. Neural Networks, 2004, 17: 127-141.

DOI: 10.1016/s0893-6080(03)00209-0

Google Scholar

[7] ZHOU Zhi-yu. Short-Term Load Forecasting Based on the EMD and GA-BP Neural Network. Electrical Measurement & Instrumentation, 2013, 50(568): 17-21, in Chinese.

Google Scholar