Eingangsvektorbildungsverfahren bei neuronalen Netzwerken zur Auto-Identifikation einer partiellen Entladungsquelle

An input vector diagram method of a neuronal network involves forming a Phi n: Phi n-1; N-graph by using discharge signals measured by a partial discharge measuring device, followed by transformation with the Phi n: Phi n-1; N-graphs, obtaining the phase-dependent summation, and obtaining the phase...

Full description

Saved in:
Bibliographic Details
Main Authors KWAK, JOO SIK, GOO, SUN GEUN, YOON, JIN YUL, PARK, KI JUN
Format Patent
LanguageGerman
Published 07.10.2010
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online AccessGet full text

Cover

More Information
Summary:An input vector diagram method of a neuronal network involves forming a Phi n: Phi n-1; N-graph by using discharge signals measured by a partial discharge measuring device, followed by transformation with the Phi n: Phi n-1; N-graphs, obtaining the phase-dependent summation, and obtaining the phase independent summation, which can both be used as an input vector of the neuronal network device and inserting the two respective summations as an input vector into the neuronal network device.
Bibliography:Application Number: DE20061008482