Exploration of Forecasting the State of Metal Oxide Volt-Sensitive Protectors Based on Improve Recursive Neural Networks

Shuang De Zhang; Long Zhou; Hai Ping Guo

doi:10.4028/www.scientific.net/AMM.472.398

Paper Titles

Application of Mechanical Energy Storage in Micro-Fluid Turbine Design
p.374

Advanced Performance Estimation Model for Lithium-Ion Power Battery Used in Pure Electric Vehicles
p.379

Verification of Control System by Physical Simulation
p.389

Research on the Detail Design of Aircraft Wings
p.394

Exploration of Forecasting the State of Metal Oxide Volt-Sensitive Protectors Based on Improve Recursive Neural Networks
p.398

Based on Vibration and Improved GRNN Identify Eggshell Crack
p.404

Study of Establishment and Operation of Salt-Gradient Solar Pond
p.409

Irradiance and Temperature Dependence Characterization of Vacuum Glass BIPV Modules
p.413

AR Technology and its Application in Biomedical Engineering
p.421

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vol. 472Exploration of Forecasting the State of Metal...

Exploration of Forecasting the State of Metal Oxide Volt-Sensitive Protectors Based on Improve Recursive Neural Networks

Abstract:

In this paper, a method is put forward to forecast the MOVs state based on the improve recursive neural network. The result indicates that recursive network is more adapted to the state forecast of MOV. Because the running state of MOV is closely related to the system voltage and the environment, the state forecast method affected by multi-factors should be further considered.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volume 472)

Pages:

398-403

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.472.398

Citation:

Cite this paper

Online since:

January 2014

Authors:

Shuang De Zhang, Long Zhou, Hai Ping Guo

Keywords:

Forecast, Metal Oxide Volt-Sensitive Protectors (MOV), Recursive Neural Network

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

References

[1] Li Xueshi et al., The finding analysis on high voltage metal oxide arrester's condition. Insulators and Surge Arresters, 1992(2).

Google Scholar

[2] Linyi, The accident analysis and prevention on 110kv and upwards of MOV in China. Power System Technology, 1995. (3).

Google Scholar

[3] zhoulong et al., The foreast method of MOV's condition based on neural network, High Voltage Apparatus, 1997(3).

Google Scholar

[4] Werbo P. Ph Dissertation D. Committee on Applied Math. Harvard Univ. Cambridge, MA, (1974).

Google Scholar

[5] Ku C C, Lee K Y. System, identification and control using diagonal recurrent neural networks. Proc American Control Conf. Chichago, 545~549, (1992).

DOI: 10.23919/acc.1992.4792125

Google Scholar

[6] Parlos A G et al., Application of the Recurrent Multilayer pereeption in Modeling Complex Process Dynamies, IEEE Trans. Neural Networks, 5(2), (2003).

Google Scholar

[7] Huazhong electrical power testing institute, The analysis on spoil reason of 500KV metal oxide arrester in Gezhouba. 1994(11).

Google Scholar

[8] Ku C C, Lee K Y. System, identification and control using diagonal recurrent neural networks. Proc American Control Conf. Chichago, 545~549, (1992).

DOI: 10.23919/acc.1992.4792125

Google Scholar

[9] Parlos A G et al., Application of the Recurrent Multilayer pereeption in Modeling Complex Process Dynamies, IEEE Trans. Neural Networks, 5(2), (2003).

Google Scholar

[10] Huazhong electrical power testing institute, The analysis on spoil reason of 500KV metal oxide arrester in Gezhouba. 1994(11).

Google Scholar