The following information was submitted:
Transactions: WSEAS TRANSACTIONS ON SYSTEMS
Transactions ID Number: 28-381
Full Name: Li-xue Li
Position: Ph.D. Candidate
Age: ON
Sex: Male
Address: Room 237, telecommunications group Building, 800#, Dongchuan Road, Shanghai
Country: CHINA
Tel:
Tel prefix:
Fax:
E-mail address: lilixue@263.net
Other E-mails: lilixue@sjtu.edu.cn
Title of the Paper: Partial Discharge Diagnosis on GIS Based on Envelope Detection
Authors as they appear in the Paper:
Email addresses of all the authors:
Number of paper pages: 10
Abstract: In order to detect and identify the defects on GIS, the ultra-high frequency envelope detection circuit and high-speed data acquisition system was designed, and the tests of five typical defects for GIS were made in the laboratory and the envelope signal was acquired based on Ultra-high frequency (UHF) envelop detection circuit. And wavelet denoising technique was used to reduce the white noise of the measurement envelop signal. A large number of experiments show that time-domain characteristics of partial discharge signals generated by the same defect model are about the same, envelopes are nearly identical too. The time-domain characteristics of partial discharge signals generated by different defect models are different, and their envelope shapes are different too. A new method of pattern recognition was proposed which analyses the characteristic parameters of the envelope signal at time-domain with BP neural network. A large number of test data in Lab indicate !
that the method is effective
Keywords: GIS, partial discharge, pattern recognition, UHF, envelop detection, BP neural network
EXTENSION of the file: .doc
Special (Invited) Session:
Organizer of the Session:
How Did you learn about congress:
IP ADDRESS: 220.207.16.2
