scholarly journals Detection of partial discharges in power cables by neural network

1996 ◽  
Vol 116 (7) ◽  
pp. 734-740
Author(s):  
Takehisa Hara ◽  
Noboru Hiraiwa ◽  
Kenichi Hirotsu ◽  
Sadao Fukunage
1998 ◽  
Vol 118 (11) ◽  
pp. 1271-1276
Author(s):  
Yoh YASUDA ◽  
Takehisa HARA ◽  
Kenichi HIROTSU ◽  
Min CHEN ◽  
Shigeki ISOSHIMA

2005 ◽  
Vol 152 (1) ◽  
pp. 24-30
Author(s):  
Yoh Yasuda ◽  
Takehisa Hara ◽  
Koji Urano ◽  
Min Chen

1989 ◽  
Vol 24 (4) ◽  
pp. 591-598 ◽  
Author(s):  
E. Harking ◽  
F.H. Kreuger ◽  
P.H.F. Morshuis

1990 ◽  
Vol 110 (3) ◽  
pp. 273-280 ◽  
Author(s):  
Makito Seki ◽  
Kazuyuki Aihara ◽  
Shigeru Kitai ◽  
Kenichi Hirotsu

2003 ◽  
Vol 123 (4) ◽  
pp. 506-512 ◽  
Author(s):  
Yoh Yasuda ◽  
Takehisa Hara ◽  
Koji Urano ◽  
Min Chen

Author(s):  
Patrick Janus ◽  
Hans Edin ◽  
Kruphalan Tamil Selva

<p>Partial Discharges (PD) on high-voltage alternating current (HVAC) cables insulated with cross-linked polyethylene (XLPE) has a low occurrence, but consequences are usually severe since PD ultimately results in cable failures. Up until now the only efficient way to monitor HVAC cables for PD has been to install large coupling devices which are able to measure PDs directly from the power cables in order to verify if they are fault-free. These installations, usually of a temporary nature, are troublesome for several reasons like safety issues, measurement uncertainty, labor intensity etc. <br />For the purpose to ultimately create a system that is able to be utilized for PD Detection by means of gas analysis, which is easily applicable in on site, on-line conditions, initial experiments were performed in order to investigate basic material properties of XLPE and to investigate the performance of tin oxide (SnO2) sensors for such an application. For this purpose a specialized test cell was developed in order to be able to investigate different conditions which can be expected in a cable insulation system.<br />It was found from the experiments that surface discharges are detectable by means of gas analysis and that these gases penetrate an XLPE sample. It was also demonstrated that the SnO2 based sensor system displays a good selectivity to the gases emitted by PD and remain inert towards other gases emitted from XLPE samples.</p>


Energies ◽  
2019 ◽  
Vol 12 (18) ◽  
pp. 3424 ◽  
Author(s):  
Ning Liu ◽  
Bo Fan ◽  
Xianyong Xiao ◽  
Xiaomei Yang

Incipient faults in power cables are a serious threat to power safety and are difficult to accurately identify. The traditional pattern recognition method based on feature extraction and feature selection has strong subjectivity. If the key feature information cannot be extracted accurately, the recognition accuracy will directly decrease. To accurately identify incipient faults in power cables, this paper combines a sparse autoencoder and a deep belief network to form a deep neural network, which relies on the powerful learning ability of the neural network to classify and identify various cable fault signals, without requiring preprocessing operations for the fault signals. The experimental results demonstrate that the proposed approach can effectively identify cable incipient faults from other disturbances with a similar overcurrent phenomenon and has a higher recognition accuracy and reliability than the traditional pattern recognition method.


Sign in / Sign up

Export Citation Format

Share Document